CN115179948B

CN115179948B - Decision-making method, device, equipment and medium based on parallel running of vehicles

Info

Publication number: CN115179948B
Application number: CN202211107526.0A
Authority: CN
Inventors: 张宁; 陈敏锐
Original assignee: Beijing PonyAi Science And Technology Co ltd
Current assignee: Beijing PonyAi Science And Technology Co ltd
Priority date: 2022-09-13
Filing date: 2022-09-13
Publication date: 2023-01-31
Anticipated expiration: 2042-09-13
Also published as: CN115179948A

Abstract

The application relates to a decision-making method, a decision-making device, decision-making equipment and a decision-making medium based on side-by-side driving of vehicles. The method comprises the following steps: acquiring at least one target vehicle on an adjacent lane of a current vehicle and the distance between the current vehicle and each target vehicle in the driving direction; obtaining at least one target interval based on each interval distance, wherein the target interval is used for keeping the interval distance between the current vehicle and the target vehicle within a preset safety threshold interval; obtaining expected acceleration and predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle; and guiding the current vehicle to drive according to the predicted cost and the expected acceleration. By adopting the method, the phenomenon that the current vehicle and the target vehicle on the adjacent lane run side by side can be improved, and the potential safety hazard is reduced to a certain extent.

Description

Decision-making method, device, equipment and medium based on parallel running of vehicles

Technical Field

The application relates to the technical field of automatic driving, in particular to a decision-making method, a decision-making device, decision-making equipment and a decision-making medium based on side-by-side driving of vehicles.

Background

The automatic driving system comprises three core parts of perception, planning and control. An automatic driving system generally senses surrounding obstacles, travelable areas, traffic rules and other environmental information by fusing data acquired by various sensors such as a laser radar, a camera, a millimeter wave radar, a laser range finder and the like; then, according to the sensed environmental information and the high-precision map, planning tasks, behaviors and actions so as to obtain a decision capable of realizing a certain target; and then controlling the automatic driving vehicle to execute the behaviors and actions in the decision according to the planned decision.

However, in the current planning made by the automatic driving system, only the relative speed and the relative distance between the front vehicle and the automatic driving vehicle, whether the orientation of the vehicle in the adjacent lane can bring interference to the automatic driving vehicle, and other factors are generally considered, and the situation that the automatic driving vehicle and the vehicle in the adjacent lane run side by side for a long time is not considered.

Particularly, under the condition that the automatic driving vehicle and a large vehicle run side by side, once an emergency occurs, serious traffic accidents can be caused, so that great potential safety hazards exist when the automatic driving vehicle and the vehicles on adjacent lanes run side by side.

Disclosure of Invention

Based on the method, the device, the equipment and the medium for decision-making based on side-by-side driving of the vehicles, potential safety hazards are reduced when the automatic driving vehicles and the vehicles on the adjacent lanes drive side by side.

In a first aspect, a decision-making method based on side-by-side driving of vehicles is provided, the method comprising:

acquiring at least one target vehicle on a lane adjacent to a current vehicle and the spacing distance between the current vehicle and each target vehicle in the driving direction;

obtaining at least one target interval based on each separation distance, wherein the target interval is used for keeping the separation distance between the current vehicle and the target vehicle within a preset safety threshold interval;

obtaining expected acceleration and predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle;

acquiring a preset first time length, and acquiring the current speed of the current vehicle;

and guiding the current vehicle to drive according to the predicted cost and the expected acceleration.

With reference to the first aspect, in a first implementable manner of the first aspect, the step of acquiring a separation distance in a traveling direction between the current vehicle and each of the target vehicles includes:

collecting the position information of each target vehicle, and mapping the position information of each target vehicle to a current lane;

establishing a longitudinal coordinate system by taking the current vehicle as a coordinate origin and taking the distance between the target vehicle and the current vehicle as a longitudinal coordinate;

and obtaining a first coordinate of each target vehicle and a spacing distance comprising the first coordinate according to the coordinate origin and the position information of each target vehicle mapped to the current lane.

With reference to the first aspect, in a second possible implementation manner of the first aspect, the obtaining at least one target interval based on each of the separation distances includes:

according to the direction close to the current vehicle, each target vehicle is subjected to gradually increased numbering processing;

acquiring a first distance, a second distance and the length of each target vehicle of the current vehicle, wherein the first distance is used for indicating the distance from the rear axle center of the current vehicle to the tail of the vehicle, and the second distance is used for indicating the distance from the rear axle center of the current vehicle to the head of the vehicle;

at an initial time, obtaining a corresponding first travel section according to the first distance, the second distance, each of the interval distances and the length of each of the target vehicles, wherein the mathematical expression of the first travel section includes:

（

）

s is the spacing distance, i is the number of each target vehicle, L is the length of the target vehicle, m is an interval coefficient, R is the first distance, and F is the second distance;

and comparing each first driving interval with a preset driving interval threshold value to obtain at least one target interval, wherein the range of the target interval is larger than that of the first driving interval.

With reference to the first aspect, in a third possible implementation manner of the first aspect, the step of obtaining at least one target interval based on each of the separation distances further includes:

acquiring a preset second time length, and acquiring a first speed of each target vehicle;

obtaining a second coordinate of each target vehicle after the second duration and a spacing distance comprising the second coordinate according to the first coordinate and the first speed of each target vehicle;

obtaining a corresponding second driving interval according to the first distance, the second distance, each spacing distance and the length of each target vehicle, wherein the mathematical expression of the second driving interval comprises:

（

）

m is the spacing distance, i is the number of each target vehicle, t is the second duration, L is the length of the target vehicle, M is an interval coefficient, R is the first distance, and F is the second distance;

and comparing each second driving interval with a preset driving interval threshold value to obtain at least one target interval, wherein the range of the target interval is larger than that of the second driving interval.

With reference to the first aspect, in a fourth implementable manner of the first aspect, the obtaining, according to a preset first duration and a current speed of the current vehicle, a predicted cost corresponding to the current vehicle reaching each of the target intervals includes:

obtaining a first cost of the corresponding target interval through weighting calculation based on each target interval and the corresponding expected acceleration;

obtaining the expected speed corresponding to the current vehicle according to the current speed, the first time length and each expected acceleration;

obtaining a second cost corresponding to the target interval through weighting calculation based on each first cost and the expected speed;

obtaining a third cost corresponding to the target interval through weighting calculation based on each second cost, the expected speed and the first speed;

acquiring a third time length of the current vehicle following the current target interval, and obtaining a fourth cost corresponding to the target interval through weighting calculation based on each third cost and the third time length;

and combining the first cost, the second cost, the third cost and the fourth cost corresponding to each target interval to obtain a predicted cost corresponding to the target interval.

With reference to the first aspect, in a fifth implementable manner of the first aspect, the step of obtaining, through a weighted calculation, a first cost of a corresponding target interval based on each target interval and a corresponding desired acceleration includes:

obtaining a pre-assigned first weight, wherein the first weight is used for indicating the importance degree of the interval distance relative to the prediction cost;

acquiring a preset minimum spacing distance and a preset maximum acceleration;

according to the first weight, the lowest interval distance, the maximum acceleration, each target interval and the corresponding expected acceleration, performing weighting calculation to obtain a first cost, wherein the mathematical expression of the first cost comprises:

in order to achieve the first cost,

in order to be said first weight, the first weight,

max is the right end point of the target interval, min is the left end point of the target interval, T is the maximum acceleration, and a is the expected acceleration.

With reference to the first aspect, in a sixth implementable manner of the first aspect, the step of obtaining, by a weighted calculation, a second cost of a corresponding target interval based on each of the first cost and the desired speed includes:

acquiring a pre-distributed second weight and a preset road limit speed, wherein the second weight is used for indicating the importance degree of the expected speed relative to the predicted cost;

and performing weighting calculation according to the second weight, the road speed limit, each first price and the expected speed to obtain a second cost, wherein the mathematical expression of the second cost comprises:

in order to achieve the second cost, the first cost,

in order to achieve the first cost,

is a function of the second weight, and is,

in order for the desired speed to be said,

the speed is limited for the road.

With reference to the first aspect, in a seventh implementable manner of the first aspect, the step of obtaining, by a weighted calculation, a third cost of a corresponding target interval based on each of the second cost, the desired speed, and the first speed includes:

obtaining a pre-assigned third weight, wherein the third weight is used for indicating the importance degree of the difference between the expected speed and the first speed relative to the predicted cost;

obtaining a preset speed difference threshold, and performing weighted calculation according to the third weight, the speed difference threshold, each second cost, the expected speed and the first speed to obtain a third cost, wherein the mathematical expression of the third cost comprises:

in order for the third cost to be the same,

in order to achieve the second cost, the first cost,

in order to be said third weight, the first weight,

in order for the desired speed to be said,

in order to be said first speed, the speed of the motor is,

is the speed difference threshold.

With reference to the first aspect, in an eighth implementable manner of the first aspect, the step of obtaining, based on each of the third costs and the third duration, a fourth cost of a corresponding target interval through weighting calculation includes:

obtaining a pre-assigned fourth weight, wherein the fourth weight is used for indicating the importance degree of the third duration relative to the predicted cost;

performing weighted calculation according to the fourth weight, each third cost and the third duration to obtain a fourth cost, wherein a mathematical expression of the fourth cost includes:

in order for the fourth cost to be the same,

in order for the third cost to be the same,

for the third duration, n is a cost factor,

is the fourth weight.

With reference to the first aspect, in a ninth implementable manner of the first aspect, the step of guiding the current vehicle driving according to the predicted cost and the desired acceleration includes:

comparing the prediction costs to obtain the lowest prediction cost and a target interval and an expected acceleration corresponding to the lowest prediction cost;

and guiding the current vehicle to drive according to the target interval corresponding to the lowest prediction cost and the expected acceleration.

With reference to the first aspect, in a tenth implementable manner of the first aspect, the obtaining, according to a preset first time duration and a current speed of the current vehicle, a desired acceleration corresponding to the current vehicle reaching each of the target intervals includes:

sampling each target interval to obtain a corresponding distance to be traveled;

and obtaining the expected acceleration of the current vehicle reaching the corresponding target interval according to the current speed, the first time length and each distance to be driven.

In a second aspect, a decision device based on side-by-side driving of vehicles is provided, the device comprising:

the sensing unit is used for acquiring at least one target vehicle on a lane adjacent to a current vehicle and the distance between the current vehicle and each target vehicle in the driving direction;

the first preprocessing unit is used for obtaining at least one target interval based on each interval distance, wherein the target interval is used for keeping the interval distance between the current vehicle and the target vehicle within a preset safety threshold interval;

the second preprocessing unit is used for obtaining expected acceleration and prediction cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle;

a control unit to direct the current vehicle drive according to the predicted cost and the desired acceleration.

In a third aspect, a computer device is provided, which includes a memory, a processor and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the decision method based on vehicle side-by-side driving according to the first aspect or any one of the embodiments described in conjunction with the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a decision method based on vehicle side-by-side driving according to the first aspect or any one of the embodiments described in connection with the first aspect.

According to the decision-making method, the decision-making device, the decision-making equipment and the decision-making medium based on the parallel running of the vehicles, when the current vehicle runs on a road, particularly an expressway, and runs parallel to the vehicles on adjacent lanes, particularly large vehicles, once the large vehicles have an emergency, the current vehicle may not be capable of taking measures in time, and great potential safety hazards exist. The method comprises the steps of collecting at least one target vehicle on a lane adjacent to a current vehicle and the distance between the current vehicle and each target vehicle in the driving direction; obtaining at least one target interval based on each separation distance, wherein the target interval is used for keeping the separation distance between the current vehicle and the target vehicle within a preset safety threshold interval; obtaining expected acceleration and predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle; and guiding the current vehicle to drive according to the predicted cost and the expected acceleration. By the decision method, at least one target interval is obtained, the current vehicle can select the target interval to be reached by obtaining the expected acceleration and the prediction cost required by the current vehicle to reach each target interval, and the current vehicle can drive in the target interval after reaching the selected target interval based on the two indexes of the expected acceleration and the prediction cost; when the current vehicle reaches and follows the target driving interval, the separation distance between the current vehicle and the target vehicle is kept in a safety threshold interval, so that the phenomenon that the current vehicle and the target vehicle on an adjacent lane drive side by side is improved, and potential safety hazards are reduced to a certain extent.

Drawings

FIG. 1 is a schematic flow chart of a decision-making method based on side-by-side driving of vehicles in one embodiment;

FIG. 2 is a diagram of an application environment of a decision method based on side-by-side driving of vehicles in one embodiment;

FIG. 3 is a diagram of an application environment of a decision method based on side-by-side driving of vehicles in one embodiment;

FIG. 4 is a schematic flow chart of the step of obtaining the predicted cost in one embodiment;

FIG. 5 is a block diagram of a decision-making device based on side-by-side driving of vehicles according to an embodiment;

FIG. 6 is a diagram of the internal structure of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present application, and the drawings only show the components related to the present application rather than the number, shape and size of the components in actual implementation, and the type, quantity and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.

The structures, proportions, sizes, and other dimensions shown in the drawings and described in the specification are for understanding and reading the content of the present disclosure, and are not intended to limit the scope of the present disclosure, which is defined in the claims and the appended claims, and therefore, they do not have the essential meaning in the art, and any structural modification, changes in proportions, or adjustments in size, should not affect the performance or performance of the disclosure, but fall within the scope of the disclosure.

References in this specification to "upper", "lower", "left", "right", "middle", "longitudinal", "lateral", "horizontal", "inner", "outer", "radial", "circumferential", etc., indicate orientations and positional relationships based on those shown in the drawings, and are for convenience only to simplify the description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

At present, the automatic driving system only uses the running state of other vehicles in the lane and whether other vehicles in the adjacent lane can interfere the running of the automatic driving vehicle as input factors for planning and decision making, and the condition that other vehicles in the adjacent lane and the automatic driving vehicle keep running side by side for a long time is not considered. Particularly, when the vehicle runs on a highway and the vehicles on the adjacent lanes are large vehicles, once an emergency situation occurs, for example, goods loaded by the large vehicles drop off, or the large vehicles roll over or change lanes suddenly, etc., it may be difficult for the current vehicle to take timely countermeasures, resulting in a serious traffic accident, and thus there is a great potential safety hazard when the autonomous vehicle and other vehicles on the adjacent lanes run.

Therefore, the application provides a decision-making method, a decision-making device, decision-making equipment and a decision-making medium based on side-by-side driving of vehicles. Acquiring at least one target vehicle on an adjacent lane of a current vehicle and the spacing distance between the current vehicle and each target vehicle in the driving direction to obtain at least one target interval; by obtaining the expected acceleration and the prediction cost required by the current vehicle to reach each target interval, the current vehicle can select the target interval which the current vehicle wants to reach based on two indexes of the expected acceleration and the prediction cost, and the current vehicle can drive in the target interval after reaching the selected target interval; when the current vehicle reaches and follows the target driving interval, the separation distance between the current vehicle and the target vehicle is kept in a safety threshold interval, so that the phenomenon that the current vehicle and the target vehicle on an adjacent lane drive side by side is improved, and potential safety hazards are reduced to a certain extent.

It should be noted that the decision method of the present application is applied to a scenario where a current vehicle and a target vehicle on an adjacent lane run side by side, and the present application does not improve the step of determining whether the target vehicle and the current vehicle run side by side, so the present application does not describe this; however, it is clear that the specific steps of how to determine whether the target vehicle and the current vehicle are running side by side are well known to those skilled in the art, and therefore, the related description is omitted, and the implementability of the present solution is not affected, and the details are not described below.

In one embodiment, as shown in fig. 1, there is provided a decision method based on side-by-side driving of vehicles, comprising the steps of:

s101: the method comprises the steps of collecting at least one target vehicle on a lane adjacent to a current vehicle and the distance between the current vehicle and each target vehicle in the driving direction.

With reference to fig. 2, in the driving process of the current vehicle, a sensing range of the current vehicle is obtained, at least one target vehicle on an adjacent lane in the sensing range is collected, and a distance between the current vehicle and each target vehicle in the driving direction is acquired. The separation distance refers to a distance between a center of the current vehicle and a center of the target vehicle in the traveling direction, with the traveling direction of the vehicle as a reference direction.

It should be noted that, for simplicity of description, fig. 2 shows a scenario in which only the adjacent lane is located at the right of the current lane and the target vehicle is three, and this description takes this scenario as an example to describe the decision method based on the side-by-side driving of vehicles; it should be understood that the present application is also applicable to a scenario in which adjacent lanes are located on both sides of a current lane, and the target vehicle is in other number, and the method applied in the scenario should also be considered as a range recorded in the present specification, and details are not described below.

S102: and obtaining at least one target interval based on each separation distance, wherein the target interval is used for keeping the separation distance between the current vehicle and the target vehicle within a preset safety threshold interval.

Based on each of the separation distances and the vehicle length of the target vehicle that is further back in the traveling direction, the traveling distance between the two adjacent target vehicles can be found; the method comprises the steps of obtaining all running distances and obtaining at least one target interval based on all the running distances, wherein when a current vehicle runs into the target interval, the distance between the current vehicle and the target vehicle in the running direction is kept within a safety threshold interval, namely the current vehicle runs along the running distance between two adjacent target vehicles, and the purpose of preventing the current vehicle and the target vehicle from running side by side is achieved.

S103: and obtaining expected acceleration and predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle.

After the target interval is obtained in step S102, obtaining a preset first time length, where the first time length is a time length required for the current vehicle to reach the target interval; and then based on the current speed of the current vehicle, obtaining the expected acceleration of the current vehicle after the first time length and required for reaching each target interval, and making cost evaluation on each decision combination to obtain corresponding prediction cost. Since the distances to be traveled by the current vehicle to reach the target intervals are different, the expected accelerations and the prediction costs obtained under the condition of the same first time duration are also different. The prediction cost is an index used for evaluating a decision that the current vehicle reaches the corresponding target interval with each expected acceleration, and the lower the prediction cost is, the better the corresponding decision is.

S104: and guiding the current vehicle to drive according to the predicted cost and the expected acceleration.

By obtaining the prediction cost of each target interval, the current vehicle can determine and select a decision, rather than making a decision singly, so as to adapt to more driving scenes. According to the predicted cost and the expected acceleration, the current vehicle can be guided to make a decision which is more suitable for the current driving situation, for example, if the current vehicle is expected to run in a common mode and the aim of preventing the current vehicle from running side by side with the target vehicle is achieved, a target interval with relatively low corresponding predicted cost can be selected from the relatively gentle expected acceleration, and the current vehicle is guided to drive; for another example, if the current vehicle is expected to travel in a sport mode and the target vehicle is prevented from traveling alongside, a target section with a relatively high corresponding prediction cost may be selected from among relatively fast expected accelerations, and the current vehicle may be guided to drive.

By the decision method, at least one target interval is obtained, the current vehicle can select the target interval to be reached by obtaining the expected acceleration and the prediction cost required by the current vehicle to reach each target interval, and the current vehicle can drive in the target interval after reaching the selected target interval based on the two indexes of the expected acceleration and the prediction cost; when the current vehicle reaches and follows the target driving interval, the separation distance between the current vehicle and the target vehicle is kept within a safety threshold interval, so that the phenomenon that the current vehicle and the target vehicle on an adjacent lane drive side by side is improved, and potential safety hazards are reduced to a certain extent. And the corresponding prediction cost is obtained by evaluating each target interval and the corresponding expected acceleration, so that the current vehicle can make a more appropriate decision according to a specific driving scene, rather than only obtaining a unique decision, and the scene adaptability is improved.

As a specific implementation manner of the foregoing embodiment, as shown in fig. 3, the step of acquiring a distance between the current vehicle and each of the target vehicles in the traveling direction includes:

For convenience of description, a longitudinal coordinate system as shown in fig. 3 is established, where O is an origin of coordinates, i.e., the current vehicle, C1, C2, and C3 are numbers of corresponding target vehicles, respectively, and S1, S2, and S3 are first coordinates, i.e., corresponding separation distances, of the corresponding target vehicles, respectively.

As a specific implementation manner of the foregoing embodiment, the step of obtaining at least one target interval based on each of the separation distances includes:

according to the direction close to the current vehicle, gradually increasing numbering processing is carried out on each target vehicle;

（

）

At the initial time of establishing the longitudinal coordinate system, the first travel section needs to satisfy any one of the following conditions: for example, if the current vehicle is expected to avoid running alongside the target vehicle numbered C1, the current vehicle needs to run ahead of the target vehicle numbered C1, and the right end point of the first running section is

With the running of the current vehicle and the continuous collection of the environmental information, the environmental information in front of the target vehicle with the number C1 may be collected, thereby further determining the corresponding first running section.

If the current vehicle is expected to avoid running alongside the target vehicles numbered C1 and C2, respectively, the current vehicle needs to run to an interval between two target vehicles numbered C1 and C2, respectively, and then the first running section includes: (

) (ii) a Similarly, if the current vehicle is expected to avoid traveling alongside target vehicles numbered C2 and C3, respectively, the first travel interval includes: (

）。

If the current vehicle is expected to avoid running in parallel with the target vehicle with the number C3, the left end point of the first running interval is

In general, the current vehicle tends to consider the first driving zone ahead, and less the first driving zone behindIn order to consider the target section, the target vehicle behind the current vehicle may be collected along with the deceleration of the current vehicle, so as to further determine the corresponding first driving section.

In summary, the obtaining of the mathematical expression of the first travel interval includes: (

) Where m is an interval coefficient, and for example, m may take a value of 0.5. And comparing each first driving interval with the driving interval threshold value to obtain a target interval with the range larger than the driving interval threshold value, wherein the target interval is obtained based on the driving distance between two adjacent target vehicles, so that the situation that the current vehicle and the target vehicle drive side by side is avoided and the current vehicle drives along with the vacancy between the two target vehicles is avoided. The reason for comparing the first travel section with the travel section threshold value is that the travel safety of the current vehicle is higher when the vacancy followed by the current vehicle is larger, and conversely, if the vacancy followed by the current vehicle is smaller, a larger potential safety hazard exists.

As a specific implementation manner of the foregoing embodiment, the step of obtaining at least one target interval based on each of the separation distances further includes:

（

）

and comparing each second driving interval with a preset driving interval threshold value to obtain at least one target interval, wherein the range of the target interval is greater than that of the second driving interval.

In the above step of obtaining the target section, in an initial stage of establishing the longitudinal coordinate system, coordinates of the current vehicle and each target vehicle are changed along with traveling of the current vehicle and each target vehicle, and a second coordinate of each target vehicle after the second time period is obtained by taking a position of the current vehicle as an origin of coordinates when the longitudinal coordinate system is established. Specifically, a first speed of each target vehicle is collected, wherein the first speed is used for indicating the current running speed of the target vehicle; and according to the product of the first speed of the target vehicle and the second time length, superposing the product and the first coordinate to obtain a second coordinate, namely the spacing distance, of the target vehicle after the second time length.

In a manner similar to the manner of obtaining the first travel section described above, in the present embodiment, the mathematical expression of the second travel section includes: (

) Where M is a separation distance obtained according to the first coordinate, the first speed, and the second duration, and M is an interval coefficient, which can be 0.5 in an exemplary description. And comparing each first driving interval with the driving interval threshold value to obtain a target interval with the range larger than the driving interval threshold value. If it is

Is greater than

If so, it indicates that the second time length does not exist, and the current vehicle is avoidedThe vehicle and the target vehicle run side by side, the second duration of other values can be obtained again, and the steps of the embodiment are continuously executed, so that the purpose of avoiding the current vehicle and the target vehicle from running side by side is achieved.

As a specific implementation manner of the foregoing embodiment, as shown in fig. 4, the step of obtaining the predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time and the current speed of the current vehicle includes:

s201: and obtaining a first cost of the corresponding target interval through weighting calculation based on each target interval and the corresponding expected acceleration.

Specifically, the step of obtaining the first cost of the corresponding target interval through weighting calculation based on each target interval and the corresponding expected acceleration includes:

acquiring a preset minimum spacing distance and a preset maximum acceleration;

in order to achieve the first cost,

in order to be said first weight, the first weight,

It should be noted that the first weight is used to indicate the importance degree of the separation distance relative to the predicted cost, and since the separation distance is used to obtain the target section, and the target section is used to keep the separation distance between the current vehicle and the target vehicle in the driving direction within a preset safety threshold section, the first weight is actually used to indicate the importance degree of the target section relative to the predicted cost. And the importance degree of the target interval relative to the prediction cost is higher, therefore, in the present application, the value of the first weight is the highest, and exemplarily, the value of the first weight may be assigned to 20.

The range of the target section expected by the application is large, namely, the distance between two target vehicles corresponding to the target section followed by the current vehicle is large, so that the minimum spacing distance is set. The minimum separation distance is the expected distance between two adjacent target vehicles, the higher the distance is, the better the decision is made, and illustratively, the minimum separation distance may be 50 meters, and more preferably more than 50 meters. When the current vehicle runs along the interval, the acceleration and deceleration operation with large amplitude is not needed, the running is stable, and the experience feeling for passengers is higher. The maximum acceleration is thus set, which means that the acceleration at which the current vehicle is expected to reach the target zone is as small as possible.

S202: and obtaining the expected speed corresponding to the current vehicle according to the current speed, the first time length and each expected acceleration.

It should be noted that, if the expected speed obtained in step S202 is less than zero or exceeds the road speed limit, the decision is considered to be unreasonable, and a negative minimum value is returned as the prediction cost corresponding to the target interval and the expected acceleration.

S203: and obtaining a second cost corresponding to the target interval through weighting calculation based on the first costs and the expected speed.

Specifically, the step of obtaining a second cost corresponding to the target interval through weighting calculation based on each of the first cost and the expected speed includes:

acquiring a pre-distributed second weight and a preset road limit speed, wherein the second weight is used for indicating the importance degree of the expected speed relative to the prediction cost;

in order to achieve the second cost, the first cost,

in order to achieve the first cost,

is a function of the second weight, and is,

in order for the desired speed to be said,

the speed is limited for the road.

It should be noted that the second weight is used to indicate the importance degree of the desired speed relative to the prediction cost. The second weight is set because, in order to ensure traffic efficiency, the application is more inclined to obtain a higher expected speed so that the current vehicle runs faster. Illustratively, the value of the second weight may be assigned to 5. Under the condition of ensuring that the current vehicle can run quickly, the speed limit condition of the road needs to be considered, so that when the second cost is calculated, the decision is considered to be in a reasonable range only under the condition that the expected speed is greater than zero and less than the road speed limit.

S204: and obtaining a third cost corresponding to the target interval through weighting calculation based on the second costs, the expected speed and the first speed.

The step of obtaining a third cost corresponding to the target interval through weighting calculation based on each of the second cost, the expected speed, and the first speed includes:

obtaining a preset speed difference threshold, and performing weighting calculation according to the third weight, the speed difference threshold, each second cost, the expected speed and the first speed to obtain a third cost, wherein the mathematical expression of the third cost includes:

in order for the third cost to be the same,

in order to achieve said second cost, the first cost,

in order to be said third weight, the first weight,

in order for the desired speed to be said,

in order to be said first speed, the speed of the motor is,

is the speed difference threshold.

It should be noted that the third weight is used to indicate the importance of the difference between the desired speed and the first speed relative to the predicted cost. The third weight is set because the present application prefers to obtain a desired speed having a smaller difference from the first speed. If the expected speed far exceeds the first speed, the current vehicle needs to do acceleration operation when the current vehicle wants to reach the distance to be traveled corresponding to the expected speed; after the distance to be traveled is reached, the current vehicle needs to perform deceleration operation in order to travel along the vacancy between the two corresponding target vehicles, otherwise the current vehicle cannot follow the vacancy, and the possibility that the current vehicle exceeds the vacancy and travels alongside the target vehicle in front of the vacancy occurs. If the difference between the expected speed and the first speed is large, the amplitude of the acceleration operation and the deceleration operation performed by the current vehicle in the process is large, so that the vehicle may run not smoothly enough, and lower riding experience is brought to passengers. Illustratively, the value of the third weight may be assigned to 3.

S205: and acquiring a third time length of the current vehicle following the current target interval, and obtaining a fourth cost corresponding to the target interval through weighting calculation based on each third cost and the third time length.

Specifically, the step of obtaining a fourth cost corresponding to the target interval through weighting calculation based on each third cost and the third duration includes:

in order for the fourth cost to be the above-mentioned,

in order for the third cost to be the same,

for the third duration, n is a cost factor,

is the fourth weight.

It should be noted that the fourth weight is used to indicate the importance degree of the third duration with respect to the predicted cost. The fourth weight is set because the present application prefers to obtain a decision that follows the target interval in a shorter time, wherein the target interval is obtained according to the distance between two adjacent target vehicles, i.e. the gap between two adjacent target vehicles; the longer the time to follow the vacancy, the higher the potential safety hazard. Illustratively, the value of the fourth weight may be assigned to 5.

S206: and combining the first cost, the second cost, the third cost and the fourth cost corresponding to each target interval to obtain a predicted cost corresponding to the target interval.

And obtaining corresponding prediction cost based on the first cost, the second cost, the third cost and the fourth cost, so that the current vehicle can make a more appropriate decision according to a specific driving scene and the obtained prediction cost, rather than only obtaining a unique decision, and the scene adaptability is improved.

As a preferable implementation manner of the above embodiment, the step of guiding the current vehicle driving according to the predicted cost and the desired acceleration includes:

Preferably, in the present embodiment, a way of obtaining an optimal decision is provided, that is, a lowest prediction cost is obtained by comparing the obtained prediction costs, and a target interval and a desired acceleration corresponding to the lowest prediction cost are used as a decision of the current vehicle in the next driving process.

As a specific implementation manner of the foregoing embodiment, the step of obtaining, according to a preset first time period and a current speed of the current vehicle, a desired acceleration corresponding to the current vehicle reaching each of the target intervals includes:

In other embodiments, the operation of sampling the target interval may be performed twice or more, for example, values such as a median, a maximum, and a minimum of the target interval may be obtained by sampling and taken as the corresponding distance to be traveled. A plurality of distances to be traveled are obtained through multiple sampling, a plurality of expected accelerations are obtained based on the distances to be traveled, and corresponding prediction costs are obtained, a plurality of selection modes are provided for making a decision of the current vehicle, and a decision more suitable for the current driving condition is obtained.

It should be understood that although the steps in the flowcharts of fig. 1 and 4 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1 and 4 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 5, there is provided a decision making device based on side-by-side driving of vehicles, comprising: perception unit, first preprocessing unit, second preprocessing unit and control unit, wherein:

the sensing unit is used for acquiring at least one target vehicle on a lane adjacent to a current vehicle and the spacing distance between the current vehicle and each target vehicle in the driving direction;

the second preprocessing unit is used for obtaining expected acceleration and predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle;

The decision device based on the parallel running of the vehicles can be used as a part of an automatic driving system and embedded in the automatic driving system of the current vehicle; or as a separate part, communicate with an automatic driving system of the current vehicle to guide the current vehicle to drive. The sensing unit can acquire information through vehicle-mounted sensors such as a laser radar, a millimeter wave radar, a camera and an ultrasonic radar, and the acquired information is fused by taking a camera as a main sensor and other sensors as auxiliary sensors, or the acquired information is fused by taking the laser radar as a main sensor and other sensors as auxiliary sensors, so that at least one target vehicle on an adjacent lane of the current vehicle and information such as the spacing distance between the current vehicle and each target vehicle in the driving direction are obtained.

Specifically, the step of acquiring, by the sensing unit, the distance between the current vehicle and each of the target vehicles in the traveling direction includes:

and obtaining a first coordinate of each target vehicle and an interval distance comprising the first coordinate according to the coordinate origin and the position information of each target vehicle mapped to the current lane.

Specifically, the step of obtaining, by the first preprocessing unit, at least one target interval based on each of the separation distances includes:

（

）

Specifically, the step of obtaining at least one target interval by the first preprocessing unit based on each of the separation distances further includes:

（

）

Specifically, the step of obtaining, by the second preprocessing unit, the predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time and the current speed of the current vehicle includes:

obtaining a third cost of the corresponding target interval through weighting calculation based on each second cost, the expected speed and the first speed;

Specifically, the step of obtaining the first cost of the corresponding target interval through weighting calculation by the second preprocessing unit based on each target interval and the corresponding expected acceleration includes:

acquiring a preset minimum spacing distance and a preset maximum acceleration;

according to the first weight, the lowest separation distance, the maximum acceleration, each target interval and the corresponding expected acceleration, performing weighting calculation to obtain a first cost, wherein the mathematical expression of the first cost comprises:

in order to achieve the first cost,

in order to be said first weight, the first weight,

Specifically, the step of obtaining, by the second preprocessing unit, a second cost corresponding to the target interval through weighting calculation based on each of the first costs and the expected speed includes:

in order to achieve said second cost, the first cost,

in order to achieve the first cost,

in order to be said second weight, the first weight,

in order for the desired speed to be said,

the speed is limited for the road.

Specifically, the step of obtaining, by the second preprocessing unit, a third cost corresponding to the target interval through weighting calculation based on each of the second cost, the expected speed, and the first speed includes:

in order for the third cost to be the same,

in order to achieve the second cost, the first cost,

in order to be said third weight, the first weight,

in order for the desired speed to be said,

in order to be said first speed, the speed of the motor is,

is the speed difference threshold.

Specifically, the step of obtaining, by the second preprocessing unit, a fourth cost corresponding to the target interval through weighting calculation based on each of the third costs and the third duration includes:

according to the fourth weight, each third cost and the third duration, performing weighted calculation to obtain a fourth cost, wherein a mathematical expression of the fourth cost includes:

for the fourth cost, for the third cost,

for the third duration, n is a cost factor,

is the fourth weight.

Preferably, the step of guiding the current vehicle driving by the control unit according to the predicted cost and the desired acceleration includes:

Specifically, the step of obtaining, by the second preprocessing unit, the expected acceleration corresponding to the current vehicle reaching each of the target intervals according to a preset first duration and the current speed of the current vehicle includes:

and obtaining the expected acceleration of the current vehicle reaching the corresponding target interval according to the current speed, the first time length and each distance to be traveled.

For specific definition of the decision device based on vehicle side-by-side driving, reference may be made to the above definition of the decision method based on vehicle side-by-side driving, and details are not repeated here. The modules in the decision device based on the side-by-side driving of the vehicles can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a decision method based on side-by-side driving of vehicles. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

In other embodiments, the processor, when executing the computer program, further performs the steps of any one of the embodiments or implementations of the decision method based on side-by-side driving of vehicles as described above.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

obtaining expected acceleration and prediction cost corresponding to the current vehicle reaching each target interval according to a preset first time length and the current speed of the current vehicle;

In other embodiments, the computer program when executed by the processor further performs the steps of any one of the embodiments or implementations of the decision method based on side-by-side driving of vehicles as described above.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile 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 a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A decision-making method based on side-by-side driving of vehicles is characterized by comprising the following steps:

sensing at least one target vehicle on an adjacent lane of a current vehicle, and collecting the distance between the current vehicle and each target vehicle in the driving direction;

2. The vehicle side-by-side driving-based decision-making method according to claim 1, wherein the step of collecting the distance between the current vehicle and each target vehicle in the driving direction comprises:

3. The vehicle side-by-side driving based decision method according to claim 2, wherein the step of deriving at least one target interval based on each of the separation distances comprises:

（

）

and comparing each first driving interval with a preset driving interval threshold value to obtain at least one target interval, wherein the range of the target interval is greater than that of the driving interval threshold value.

4. The vehicle side-by-side driving based decision method according to claim 3, wherein the step of deriving at least one target interval based on each of the separation distances further comprises:

according to the first coordinates and the first speed of each target vehicle, obtaining second coordinates of each target vehicle after the second duration and a spacing distance comprising the second coordinates;

（

）

and comparing each second driving interval with a preset driving interval threshold value to obtain at least one target interval, wherein the range of the target interval is larger than the range of the driving interval threshold value.

5. The vehicle side-by-side driving-based decision-making method according to claim 1, wherein the step of obtaining the predicted cost corresponding to the current vehicle reaching each target interval according to a preset first time duration and the current speed of the current vehicle comprises:

acquiring the first speed of each target vehicle, and obtaining a third cost corresponding to a target interval through weighting calculation based on each second cost, the expected speed and the first speed;

6. The vehicle side-by-side driving based decision method according to claim 5, wherein the step of obtaining the first cost of the corresponding target interval through weighting calculation based on each target interval and the corresponding expected acceleration comprises:

acquiring a preset minimum spacing distance and a preset maximum acceleration;

in order to achieve the first cost,

in order to be said first weight, the first weight,

7. The vehicle side-by-side driving based decision method according to claim 6, wherein the step of obtaining a second cost of a corresponding target interval through weighting calculation based on each first cost and the expected speed comprises:

is said secondThe cost is that the cost of the product,

in order to achieve the first cost,

in order to be said second weight, the first weight,

in order for the desired speed to be said,

the speed is limited for the road.

8. The vehicle side-by-side driving based decision method according to claim 7, wherein the step of obtaining a third cost of a corresponding target interval through weighting calculation based on each of the second cost, the desired speed and the first speed comprises:

in order for the third cost to be the same,

in order to achieve said second cost, the first cost,

in order to be said third weight, the first weight,

in order for the desired speed to be said,

in order to be said first speed, the speed of the motor is,

is the speed difference threshold.

9. The vehicle side-by-side driving based decision method according to claim 8, wherein the step of obtaining a fourth cost of a corresponding target interval through weighting calculation based on each third cost and the third duration comprises:

in order for the fourth cost to be the same,

in order for the third cost to be the same,

for the third duration, n is a cost factor,

is the fourth weight.

10. The vehicle side-by-side driving based decision method according to claim 1, wherein the step of guiding the current vehicle driving according to the predicted cost and the desired acceleration comprises:

11. The vehicle side-by-side driving-based decision-making method according to claim 1, wherein the step of obtaining the expected acceleration corresponding to the current vehicle reaching each target interval according to a preset first time duration and the current speed of the current vehicle comprises:

12. A decision-making device based on side-by-side driving of vehicles, the device comprising:

the sensing unit is used for sensing at least one target vehicle on a lane adjacent to a current vehicle and acquiring the distance between the current vehicle and each target vehicle in the driving direction;

a first preprocessing unit, configured to obtain at least one target interval based on each of the separation distances, where the target interval is used to keep a separation distance between the current vehicle and the target vehicle within a preset safety threshold interval;

a control unit to direct the current vehicle to drive according to the predicted cost and the desired acceleration.

13. 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 a method for vehicle side-by-side driving based decision making according to any one of claims 1 to 11.

14. 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 vehicle side-by-side driving based decision method according to any one of claims 1 to 11.