CN116088538B

CN116088538B - Vehicle track information generation method, device, equipment and computer readable medium

Info

Publication number: CN116088538B
Application number: CN202310356085.6A
Authority: CN
Inventors: 包鹏; 李�浩; 丁璟; 王一舟; 倪凯
Original assignee: HoloMatic Technology Beijing Co Ltd
Current assignee: Heduo Technology Guangzhou Co ltd
Priority date: 2023-04-06
Filing date: 2023-04-06
Publication date: 2023-06-13
Anticipated expiration: 2043-04-06
Also published as: CN116088538A

Abstract

Embodiments of the present disclosure disclose a vehicle track information generation method, apparatus, device, and computer readable medium. One embodiment of the method comprises the following steps: acquiring an obstacle track information set and a vehicle track information set; preprocessing an obstacle track information set and a vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set; for each target vehicle track information: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; generating track cost information based on the target vehicle track information, the first price score and the second cost score; selecting one piece of track cost information as target track cost information; and determining the target vehicle track information corresponding to the target track cost information as vehicle track information. This embodiment can improve the efficiency and safety of the running of the vehicle.

Description

Vehicle track information generation method, device, equipment and computer readable medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a vehicle track information generating method, apparatus, device, and computer readable medium.

Background

The vehicle track information generation method plays an important role in path planning and decision making of the automatic driving vehicle. Currently, in generating vehicle track information, the following methods are generally adopted: and generating vehicle track information for running of the vehicle according to the perception information acquired by the vehicle by a decision model based on a neural network or a decision method based on rules.

However, the inventors found that when the vehicle track information is generated in the above manner, there are often the following technical problems:

firstly, because the decision model based on the neural network is difficult to adjust parameters in real time in continuous planning, the interpretability is poor, and meanwhile, the decision method based on the rules can only process the predicted track of the own vehicle, but cannot process a plurality of predicted tracks of the obstacle vehicle, so that the accuracy of the track information of the vehicle is easily insufficient, and the running efficiency and the running safety of the vehicle are reduced;

secondly, since there may be a plurality of uncertain predicted trajectories of the obstacle vehicles, if the collision cost between the own vehicle and the obstacle vehicles is set to infinity, it is difficult to determine one own vehicle trajectory capable of avoiding all the obstacle vehicles, thereby easily causing failure in generating vehicle trajectory information; alternatively, even if the own vehicle trajectory can be determined, the own vehicle trajectory will cause the own vehicle to fail to normally advance due to continuous deceleration and braking, thereby reducing the efficiency of the vehicle running.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a vehicle track information generation method, apparatus, device, and computer-readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a vehicle track information generating method, the method including: acquiring an obstacle track information set and a current vehicle track information set; preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set; for each target vehicle track information in the target vehicle track information set, executing the following steps: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; generating track cost information based on the target vehicle track information, the first price score and the second cost score; selecting one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information; and determining the target vehicle track information corresponding to the target track cost information as vehicle track information.

In a second aspect, some embodiments of the present disclosure provide a vehicle track information generating apparatus, the apparatus including: an acquisition unit configured to acquire an obstacle trajectory information set and a vehicle trajectory information set of a current vehicle; the preprocessing unit is configured to preprocess the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set; an execution unit configured to execute, for each target vehicle track information in the target vehicle track information set, the steps of: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; generating track cost information based on the target vehicle track information, the first price score and the second cost score; the selection unit is configured to select one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information; and the determining unit is configured to determine the target vehicle track information corresponding to the target track cost information as vehicle track information.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantageous effects: by the vehicle track information generation method, accuracy of the vehicle track information can be improved, and efficiency and safety of vehicle running can be improved. Specifically, the lack of accuracy of the vehicle trajectory information is caused, and the efficiency and safety of the vehicle running are reduced because: the decision model based on the neural network is difficult to adjust parameters in real time in continuous planning, the interpretability is poor, and meanwhile, the decision method based on the rule can only process the predicted track of the own vehicle, but cannot process a plurality of predicted tracks of the obstacle vehicle. Based on this, the vehicle track information generating method of some embodiments of the present disclosure first acquires an obstacle track information set and a vehicle track information set of the current vehicle. Therefore, the method is convenient for planning an optimal track with the lowest running cost for the current vehicle according to the predicted track of the current vehicle and the obstacle vehicle. And secondly, preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set. Therefore, the predicted track data of the current vehicle and the obstacle vehicle can be converted into track data under the path-speed decomposition frame, so that cost estimation can be conveniently carried out on each predicted track of the current vehicle in the follow-up process. Then, for each target vehicle track information in the target vehicle track information set, the following steps are performed: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; and generating track cost information based on the target vehicle track information, the first price score and the second cost score. Therefore, the final driving cost corresponding to the vehicle track can be obtained by carrying out rule-based cost estimation on the current vehicle and interactive cost estimation of the current vehicle and the obstacle vehicle aiming at each vehicle track. And finally, selecting one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information. And determining the target vehicle track information corresponding to the target track cost information as vehicle track information. Therefore, the vehicle track with the lowest running cost can be determined according to the track cost information corresponding to each vehicle track. Therefore, the vehicle track information generation method disclosed by the invention is combined with the rule-based decision method, and the running cost of the vehicle is determined according to the vehicle track, and meanwhile, the interaction cost corresponding to the collision risk possibly existing between the current vehicle and the obstacle vehicle is fully considered, so that the vehicle track with the lowest running cost can be determined for the vehicle to run. Thus, the accuracy of the vehicle track information is improved. Further, the efficiency and safety of the vehicle running are improved.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of a vehicle track information generation method according to the present disclosure;

FIG. 2 is a schematic structural view of some embodiments of a vehicle track information generating device according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a flow 100 of some embodiments of a vehicle track information generation method according to the present disclosure. The vehicle track information generating method comprises the following steps:

Step 101, acquiring an obstacle track information set and a current vehicle own track information set.

In some embodiments, the execution subject (e.g., the whole vehicle controller) of the vehicle track information generation method may acquire the obstacle track information set and the own track information set of the current vehicle through a wired connection manner or a wireless connection manner. The obstacle track information in the obstacle track information set may be information of motion tracks of all obstacle vehicles around the current vehicle within a preset time period in the future, which is output by the track prediction module. The preset time period may be a preset time period value. For example, the preset time period may be 5 seconds. The obstacle trajectory information in the obstacle trajectory information set may include, but is not limited to, at least one of: obstacle identification, obstacle track identification, track collision confidence, an obstacle track point information sequence and the like. The obstacle identifier may be an identifier of an obstacle vehicle. The above-mentioned obstacle vehicle may be an obstacle of a vehicle type. The obstacle identifiers are in one-to-one correspondence with the obstacle vehicles. The obstacle track identifier may be an identifier of an obstacle track. The obstacle trajectory may be a movement trajectory of an obstacle vehicle. The obstacle track identifiers are in one-to-one correspondence with the obstacle tracks. The trajectory collision confidence may be a confidence of collision risk between a motion trajectory of the current vehicle and a motion trajectory of the obstacle vehicle. The above-described obstacle trajectory point information sequence may characterize a predicted obstacle trajectory. The obstacle track point information in the obstacle track point information sequence corresponds to the track points one by one. The obstacle trajectory point information in the obstacle trajectory point information sequence may include a first time point, a pose matrix, acceleration, and jerk. The first time point may be a time point when the obstacle vehicle travels to a corresponding track point. The track prediction module may be a module for predicting a motion track of the obstacle vehicle within a preset duration according to a historical motion track of the obstacle vehicle. The above-described historical motion trajectory may be a motion trajectory of the obstacle vehicle over a period of time. The vehicle track information in the vehicle track information set may be information of a motion track of the current vehicle within a preset time length in the future, which is output by the decision planning module. For example, the vehicle track information in the vehicle track information set may include, but is not limited to, at least one of the following: a self-vehicle track mark, an initial track point information sequence and the like. The vehicle track identifier may be an identifier of a vehicle track. The vehicle track may be a planned current vehicle movement track. The vehicle track marks are in one-to-one correspondence with the vehicle tracks. The initial track point information in the initial track point information sequence can represent track points on the track of the vehicle. The initial track point information in the initial track point information sequence corresponds to the track points one by one. The initial trajectory point information in the initial trajectory point information sequence may include a second time point and positioning coordinates. The second time point may be a time point when the current vehicle travels to the corresponding track point. The positioning coordinates may be GPS (Global Positioning System ) coordinates. The decision planning module may be a module for planning a motion track of the current vehicle to avoid the static obstacle in a preset time period. The static obstacle may be an obstacle whose position does not change with time.

It should be noted that one obstacle vehicle may correspond to a plurality of predicted obstacle trajectories. The current vehicle may correspond to a plurality of planned own vehicle trajectories.

Step 102, preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set.

In some embodiments, the executing body may preprocess the obstacle track information set and the vehicle track information set in various manners to obtain a target vehicle track information set and a target obstacle track information set. The target vehicle track information in the target vehicle track information set can represent a planned vehicle track. The target vehicle track information in the target vehicle track information set may include, but is not limited to, the following items: a self-vehicle track mark, a self-vehicle track point information sequence and the like. The information of the own vehicle track point in the information sequence of the own vehicle track point can represent the information of the planned current vehicle at one track point on the own vehicle track. The vehicle track point information in the vehicle track point information sequence may include, but is not limited to, at least one of the following: the vehicle time, the vehicle speed value, the vehicle acceleration value, the vehicle jerk value and the like. The vehicle-by time may be a time point when the current vehicle travels from the current position to the corresponding track point, assuming that the current time is 0. The above-mentioned own vehicle speed value may be a speed value of the current vehicle at the corresponding track point. The vehicle position value may be a distance value that the current vehicle moves from the current position to the corresponding track point. The above-mentioned own vehicle acceleration value may be an acceleration value of the current vehicle at the corresponding track point. The vehicle jerk value may be a jerk value of the current vehicle at the corresponding track point. The target obstacle trajectory information in the target obstacle trajectory information set may represent an obstacle trajectory at risk of collision with the current vehicle. The target obstacle trajectory information in the target obstacle trajectory information set may include, but is not limited to, the following: obstacle track identification, an obstacle track point information sequence and the like. The obstacle trajectory point information in the above-described obstacle trajectory point information sequence may be information of the obstacle vehicle at the trajectory point. The obstacle trajectory point information in the above-described obstacle trajectory point information sequence may include, but is not limited to, at least one of: travel time, upper displacement limit, lower displacement limit, and travel speed. The travel time may be a time point when the obstacle vehicle travels from the current position to the corresponding track point, assuming that the current time is 0. The displacement upper limit value and the displacement lower limit value may be critical displacement values at which the own vehicle collides after the obstacle vehicle moves to a locus point corresponding to the travel time. The start position may be a position where the obstacle is located at time 0. The travel speed may be a speed value of the obstacle vehicle at the corresponding locus point.

In some optional implementations of some embodiments, the executing body may preprocess the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set by:

and firstly, performing collision detection on the obstacle track information set and the vehicle track information set to obtain a target collision track information set. The target collision track information in the target collision track information set can represent an obstacle track with collision risk with the current vehicle. For each obstacle track information in the obstacle track information set, collision detection can be performed on the obstacle track information and the vehicle track information set through a preset collision detection method, so as to obtain target collision track information.

As an example, the collision detection method described above may include, but is not limited to, at least one of: a circumscribed circle collision detection method, a SAT (Separating Axis Theorem, separation axiom) collision detection method, a GJK (Gilbert-Johnson-Keerthi) collision detection method, and the like.

And a second step of generating a target vehicle track information set and a target obstacle track information set based on the vehicle track information set and the target collision track information set. The execution subject may generate the target vehicle track information set and the target obstacle track information set based on the vehicle track information set and the target collision track information set in various ways.

In some optional implementations of some embodiments, the executing entity may generate the target vehicle track information set and the target obstacle track information set based on the vehicle track information set and the target collision track information set by:

step one, for each vehicle track information in the vehicle track information set, executing the following steps to generate target vehicle track information in the target vehicle track information set:

and step one, mapping the vehicle track information to obtain a vehicle position time information set. The vehicle position time information in the vehicle position time information group may represent a track point on a vehicle track in the ST chart under a frame coordinate system established with a preset reference path. The predetermined reference path may be a path of a selected one of the tracks of the vehicle. The coordinate system corresponding to the ST graph may be a coordinate system having a horizontal axis and a vertical axis with respect to time and a displacement. The vehicle position time information in the vehicle position time information group may include a vehicle time and a vehicle position value. First, for each initial track point information in the initial track point information sequence included in the self-vehicle track information, mapping the initial track point information to an ST diagram under a frenet natural coordinate system according to a second time point and positioning coordinates included in the initial track point information, and obtaining self-vehicle position time information. And then, sequencing the obtained vehicle position time information according to the time sequence of the initial track point information by a preset sequencing algorithm to obtain a vehicle position time information group.

As an example, the ranking algorithm described above may include, but is not limited to, at least one of: quick ordering, bubble ordering, insert ordering.

And secondly, carrying out fusion processing on the vehicle track information and the vehicle space time information group to obtain target vehicle track information. The fusion processing can be performed to obtain the target vehicle track information by the following steps:

and step 1, updating the vehicle parking space time information set to obtain an updated vehicle parking space time information set. The updated vehicle position time information in the updated vehicle position time information group may be information including a speed, an acceleration, and a jerk of the current vehicle corresponding to the vehicle time. For each of the above-described vehicle position time information sets, first, a vehicle speed value, a vehicle acceleration value, and a vehicle jerk value may be generated from the vehicle position time information by a dynamics model. And then, adding the generated vehicle speed value, the vehicle acceleration value and the vehicle jerk value into corresponding vehicle position time information to obtain updated vehicle position time information.

And 2, determining the vehicle track mark included in the vehicle track information and the updated vehicle position time information group as target vehicle track information.

Step two, for each target collision track information in the target collision track information set, executing the following steps to generate target obstacle track information in the target obstacle track information set:

and step one, mapping the target collision track information to obtain an obstacle displacement time information set. Wherein the obstacle displacement time information in the obstacle displacement time information set may characterize one trajectory point on an obstacle trajectory in the ST view under the frenet coordinate system established with the reference path. The obstacle displacement time information in the obstacle displacement time information set may include a travel time, an upper displacement limit value, and a lower displacement limit value. Firstly, for each obstacle track point information in the obstacle track point information sequence included in the target collision track information, according to a first time point and a pose matrix included in the obstacle track point information, projecting a surrounding frame of a corresponding obstacle to a natural coordinate system, moving a current vehicle and the projected surrounding frame along a reference path to obtain a critical displacement value of a workshop collision, and projecting the critical displacement value to an ST diagram under a frame coordinate system to obtain obstacle displacement time information of the corresponding time point. And then, sequencing the obtained displacement time information of each obstacle according to the time sequence of the track point information of each obstacle by the sequencing algorithm to obtain an obstacle displacement time information group.

And secondly, carrying out fusion processing on the target collision track information and the obstacle displacement time information group to obtain target obstacle track information. The fusion process may be performed to obtain target obstacle trajectory information by:

and step 1, updating the obstacle displacement time information set to obtain an updated obstacle displacement time information set. Wherein the updated vehicle position time information in the updated obstacle displacement time information group may be information including the speed of the obstacle vehicle. For each obstacle displacement time information in the obstacle displacement time information set, first, one obstacle trajectory point information matching the obstacle displacement time information is selected from an obstacle trajectory point information sequence included in the target collision trajectory information. Wherein, the matching with the obstacle displacement time information can be: the first preset displacement duration is the same as the second preset displacement duration corresponding to the obstacle displacement time information. The first preset displacement duration may be a duration between a first time point corresponding to the obstacle track point information and an obstacle track start time. The second preset displacement period may be a period between a travel time and a start time included in the obstacle displacement time information. Then, a running speed value may be generated from the acceleration included in the selected obstacle trace point information through a dynamic formula. And finally, adding the generated running speed value to the corresponding obstacle displacement time information to obtain updated obstacle displacement time information.

And 2, determining the obstacle track mark and the track collision confidence coefficient included in the updated obstacle displacement time information set and the target collision track information as target obstacle track information.

Step 103, for each target vehicle track information in the target vehicle track information set, executing the following steps:

and step 1031, analyzing and processing the target vehicle track information to obtain a first price value.

In some embodiments, the executing body may analyze the target vehicle track information in various manners to obtain a first price value. The first price score may measure a difference between a corresponding vehicle track and an expected track. For example, the larger the first price score, the larger the difference between the own vehicle track and the desired track.

In some optional implementations of some embodiments, the executing body may analyze the target vehicle track information to obtain a first price value by:

the first step, for each vehicle track point information in the vehicle track point information sequence included in the target vehicle track information, executing the following steps:

And a first sub-step of determining one piece of self-vehicle track point information meeting a preset next moment condition in the self-vehicle track point information sequence as next moment track point information in response to determining that the self-vehicle track point information meets a preset sequence number condition. The preset sequence number condition may be that a sequence number corresponding to the track point information of the vehicle is smaller than a maximum value of each sequence number corresponding to the track point information sequence of the vehicle. The preset next time condition may be the vehicle track point information having a sequence number value greater than a sequence number corresponding to the vehicle track point information by 1 in the vehicle track point information sequence.

And a second sub-step of generating a position difference cost score, a speed difference cost score and an acceleration difference cost score based on the next moment track point information and the vehicle track point information. Wherein the location difference cost score may characterize a difference between a location at an adjacent time instant and a location based on dynamics. The velocity difference cost score may characterize the difference between the velocity at adjacent times and the dynamics-based velocity. The acceleration difference cost score may characterize the difference between the acceleration at adjacent times and the dynamics-based acceleration. And generating a position difference cost score, a speed difference cost score and an acceleration difference cost score based on the next moment track point information and the vehicle track point information according to the longitudinal dynamics model. The position difference cost score, the velocity difference cost score, and the acceleration difference cost score may be expressed by the following formulas:

。

Wherein, the liquid crystal display device comprises a liquid crystal display device,

the initial value of the time point corresponding to the vehicle track point information is 0./>

The time point of the next time corresponding to the track point information of the next time is shown. />

Representation->

Time and->

The difference in time. />

Representing the location difference cost score. />

Representation->

The vehicle position value at the moment. />

Representation->

The vehicle position value at the moment. />

Representation->

A vehicle speed value at the moment. />

Representation->

And (5) a self-vehicle acceleration value at the moment. />

Representation->

And (5) a self-vehicle jerk value at the moment. />

Representing the speed differential cost score. />

Representation->

A vehicle speed value at the moment. />

Representing the acceleration difference cost score. />

Representation->

And (5) a self-vehicle acceleration value at the moment.

And a third sub-step of generating a comprehensive difference cost score based on the position difference cost score, the speed difference cost score, and the acceleration difference cost score. The comprehensive difference cost score can represent the cost of the difference between the vehicle track at the adjacent moment and the vehicle track based on dynamics. First, the product of the position difference cost value and a preset position weight value is determined as a target position cost value. The preset position weight value may be a weight value corresponding to a preset vehicle position. And secondly, determining the product of the speed difference cost value and a preset speed weight value as a target speed cost value. The preset speed weight value may be a weight value corresponding to a preset speed of the vehicle. And then, determining the product of the acceleration difference cost value and a preset acceleration weight value as a target acceleration cost value. The preset acceleration weight value may be a weight value corresponding to a preset acceleration. And finally, determining the sum of the target position cost score, the target speed cost score and the target acceleration cost score as a comprehensive difference cost score.

And secondly, determining the sum of the generated comprehensive difference cost scores as a track difference cost score. The track difference cost score can represent the dynamics cost corresponding to the vehicle track. The dynamic cost may be a cost corresponding to a gap between the predicted trajectory and the dynamics-based trajectory.

And thirdly, determining a preset dynamic cost value as a first price value in response to determining that the trajectory difference cost value is smaller than a preset difference threshold. The preset difference threshold may be an upper limit value of a dynamic cost of the track. The preset dynamic cost score can represent that the corresponding vehicle track accords with a dynamic model. For example, the kinetic cost score may be 0.001.

Optionally, the executing body determines the preset second dynamic cost score as the first generation cost score in response to determining that the trajectory difference cost score is not less than a preset difference threshold. The preset second dynamic cost score may represent that the corresponding vehicle track does not conform to the dynamic model. For example, the dynamic cost score may be infinity.

Optionally, the executing body may further analyze the target vehicle track information to obtain a first price value through the following steps:

and a first sub-step of determining a difference between a preset reference speed value and a vehicle speed value included in the vehicle track point information as a speed error value. The preset reference speed value may be dynamically set according to the road speed limit condition. For example, the road speed limit condition may be that the road is provided with a specific speed limit value, and the above-mentioned reference speed value may be the speed limit value of the road; the road speed limit may be a speed value set by the driver, and the reference speed value may be a speed value set by the driver.

And a second sub-step, determining the product of the preset efficiency weight value and the speed error value as an efficiency cost value. The preset efficiency weight value may be a preset weight value of driving efficiency. The above-described running efficiency may be a difference between the speed of the vehicle and the desired speed. The smaller the difference value is, the higher the driving efficiency is; the larger the difference, the lower the driving efficiency. The efficiency cost score may characterize the speed difference between the corresponding vehicle track and the desired track at various times.

And secondly, determining the sum of the obtained efficiency cost scores as a first price score.

and a first sub-step of determining the square of the vehicle acceleration value included in the vehicle track point information as a first comfort cost value, and determining the product of a preset first comfort weight value and the first comfort cost value as a first comfort value. The preset first comfort weight value may be a weight value occupied by a preset acceleration affecting comfort cost. Wherein the comfort penalty may be a ride comfort penalty.

And a second sub-step of determining the square of the jerk value included in the vehicle track point information as a second comfort cost value, and determining the product of a preset second comfort weight value and the second comfort cost value as a second comfort value. The preset second comfort level weight value may be a weight value occupied by a preset jerk that affects comfort level cost.

And a third sub-step of determining the sum of the first comfort score and the second comfort score as a comfort cost score. The comfort cost score may represent a difference between the comfort level of the corresponding vehicle track and the desired track.

And secondly, determining the sum of the obtained comfort cost scores as a first price score.

Optionally, the executing entity may also randomly combine the dynamics cost, the efficiency cost and the riding comfort cost, and determine a result obtained by the random combination as the first price score. For example, the dynamic cost and the efficiency cost are combined, and the sum of the dynamic cost score and the efficiency cost score is determined as the first price score.

Step 1032, generating a second cost score based on the target vehicle track information and the target obstacle track information set.

In some embodiments, the executing entity may generate the second cost score based on the target vehicle track information and the target obstacle track information set in various manners. The second cost score may be a cost value of interaction between the corresponding vehicle track and the obstacle track.

In some optional implementations of some embodiments, the executing entity may generate the second cost score based on the target vehicle track information and the target obstacle track information set by:

first, for each target obstacle trajectory information in the target obstacle trajectory information set, the following steps are performed:

and a first sub-step, detecting the target obstacle track information to obtain an uncorrupted time group and a collision time group. The non-collision time group may be a set of respective times when the current vehicle and the obstacle vehicle do not collide. The above-described collision time group may be a set of respective times at which the present vehicle collides with the obstacle vehicle. For each updated obstacle displacement time information in the updated obstacle displacement time information set included in the target obstacle trajectory information, detection processing may be performed to obtain an uncorrupted time or a collision time by:

and 1, selecting updated vehicle position time information matched with the updated obstacle displacement time information from the updated vehicle position time information group included in the target vehicle track information as matched vehicle position time information. Wherein, the matching with the updated obstacle displacement time information may be: the vehicle time corresponding to the updated vehicle time information is the same as the travel time corresponding to the updated obstacle displacement time information.

And 2, determining the running time corresponding to the updated obstacle displacement time information as the collision time in response to determining that the matching vehicle displacement time information meets the preset displacement interval condition. The preset displacement interval condition may be: and the vehicle position value corresponding to the matched vehicle position time information is between the displacement upper limit value and the displacement lower limit value corresponding to the updated obstacle displacement time information.

And 3, in response to determining that the matched vehicle displacement time information does not meet the preset displacement interval condition, determining the running time corresponding to the updated obstacle displacement time information as the non-collision time.

And a second sub-step of generating an uncorrupt cost score based on the uncorrupt time group, the target vehicle track information, and the target obstacle track information. The non-collision cost score may be a cost value of collision interaction between the corresponding vehicle track and one obstacle track. The execution subject may generate the non-collision cost score based on the non-collision time group, the target vehicle trajectory information, and the target obstacle trajectory information in various ways.

In some optional implementations of some embodiments, the target vehicle track information may include a sequence of vehicle track point information. The target obstacle trajectory information may include an obstacle trajectory point information sequence. The execution subject may generate an uncorrupt cost score based on the uncorrupt time group, the target vehicle trajectory information, and the target obstacle trajectory information by:

step one, for each uncorrupt time in the uncorrupt time group, executing the following steps:

and step one, selecting one vehicle track point information matched with the non-collision moment from the vehicle track point information sequence included in the target vehicle track information as first vehicle track point information. The matching with the non-collision time may be that the vehicle time corresponding to the vehicle track point information is the same as the non-collision time.

And a second sub-step of selecting one obstacle track point information matched with the non-collision moment from the obstacle track point information sequence included in the target obstacle track information as first obstacle track point information. The travel time corresponding to the obstacle trajectory point information may be the same as the non-collision time.

And thirdly, generating a target non-collision cost value based on the first vehicle track point information and the first obstacle track point information. The target non-collision cost score may be a cost value of a current vehicle and an obstacle vehicle that do not collide at a time point. First, the sum of the upper displacement limit value and the lower displacement limit value included in the first obstacle track point information is determined as a track displacement multiple value. Next, a difference between the upper limit value of displacement and the lower limit value of displacement included in the first obstacle trajectory point information is determined as a trajectory region value. Then, the quotient of the track displacement multiple value and the preset multiple is determined as the track displacement value. The preset multiple may be a preset value. For example, the preset multiple may be 2. And then, determining the quotient of the track area value and the preset multiple as a track interval value. Then, an absolute value of a difference between the vehicle position value included in the first vehicle track point information and the track displacement value is determined as an inter-track distance value. The distance value between the tracks may be a distance value between the current vehicle and the obstacle vehicle at the same time. And finally, generating a target non-collision cost value based on a preset distance threshold value, a preset distance weight value, the distance value between tracks and the track interval value. The preset distance threshold may be a preset distance value between the current vehicle and the obstacle vehicle. The distance threshold can be dynamically set according to working condition requirements. For example, the above-mentioned preset distance threshold may be set to a fixed value, or to a speed-related value, or to a vehicle type-related value, or to a driver-desired following distance value. The preset distance weight value may be a preset following distance weight value. Specifically, in response to determining that the inter-track distance value is greater than the distance threshold, a preset first collision-free interaction cost score is determined as a target collision-free cost score. The preset collision-free interaction cost value may be a preset value. For example, the collision-free interaction cost score may be 0.001.

Optionally, the execution body may first determine a product of the inter-track distance value and the distance weight value as the target inter-track distance value in response to determining that the inter-track distance value is greater than the track interval value and less than or equal to the distance threshold. Then, a function value based on e and an index of the opposite number of the distance values between the target trajectories is determined as a target non-collision cost score.

And step two, determining the sum of the generated non-collision cost scores of the targets as a non-collision cost score.

And a third sub-step of generating a collision cost score based on the collision time group, the target vehicle track information, and the target obstacle track information. The collision cost score may be a cost value of collision interaction between the corresponding vehicle track and one obstacle track. The execution subject may generate the collision cost score based on the collision time group, the target vehicle trajectory information, and the target obstacle trajectory information in various ways.

In some optional implementations of some embodiments, the target obstacle trajectory information may further include a trajectory collision confidence. The execution body may generate the collision cost score based on the collision time group, the target vehicle trajectory information, and the target obstacle trajectory information by:

And step one, determining a product of a preset confidence weight value and the track collision confidence included in the target obstacle track information as a confidence cost score. The preset confidence weight value may be a preset weight value of the confidence of the track collision. The confidence cost score may be a cost value of a confidence that the current vehicle collides with the obstacle vehicle. For example, the lower the confidence of a track collision, the less the confidence cost of the track collision correspondence.

And step two, generating a time cost value based on a preset collision time weight value, a preset collision time quantity weight value, a track end time value and the collision time group. The preset collision time weight value may be a weight value corresponding to a difference between a preset collision time and a current time. The number of collision time weight values may be weight values corresponding to the number of collision times at which a collision is expected to occur, which are set in advance. The track end point time value may be a preset vehicle time corresponding to the last track point of the planned vehicle track. The time cost score may be a time cost value of each moment when the current vehicle collides with the obstacle vehicle. For example, the closer the time of the collision is to the current time, the larger the time cost value, and the larger the number of time of the collision is, the larger the time cost value is. The time cost score may be expressed by the following formula:

。

representing the time cost score. />

The collision time group is shown. />

The number is indicated, and the initial value is 0./>

Representing the above-mentioned collision time group->

Middle->

Collision time of each. />

Representing the above-mentioned collision time group->

In the number of crash moments.

Indicating the track endpoint time value. />

Representing the collision moment weight value. />

And the number weight value of the collision time is represented.

Step three, for each collision time in the above-mentioned group of collision times, the following steps are performed:

and step one, selecting one vehicle track point information matched with the collision moment from the vehicle track point information sequence included in the target vehicle track information as second vehicle track point information.

And a second sub-step of selecting one obstacle track point information matched with the collision moment from the obstacle track point information sequence included in the target obstacle track information as second obstacle track point information.

And thirdly, generating a target collision cost value based on the second vehicle track point information and the second obstacle track point information. The target collision cost value may be a cost value of a collision between the current vehicle and the obstacle vehicle at a collision moment. For example, at a collision time, the closer the vehicle is located to the center position of the obstacle locus point between the upper and lower boundaries of the corresponding displacement in the ST map, the larger the target collision cost score is. First, the sum of the displacement upper limit value and the displacement lower limit value included in the second obstacle track point information is determined as a second track displacement multiple value. And secondly, determining the quotient of the second track displacement multiple value and the preset multiple as a second track displacement value. Then, an absolute value of a difference between the vehicle position value included in the second vehicle track point information and the second track displacement value is determined as a second inter-track distance value. Wherein the second inter-track distance value may represent a distance value between the current vehicle and the obstacle track point at a corresponding vehicle time. And finally, generating a target collision cost value based on a preset collision weight value and the distance value between the second tracks. The preset collision weight value may be a preset collision time when the current vehicle collides with the obstacle vehicle, or a corresponding weight value. The target collision cost score may be expressed by the following formula:

。

representing the target collision cost score. />

Representing the collision weight value. />

Representing a second inter-track distance value.

Expressed as natural constant->

An exponential function of the base.

And step four, determining the sum of the generated target collision cost scores as a collision position cost score. The collision position cost score can represent the coincidence degree of the positions of the current vehicle and the obstacle vehicle at each collision moment.

And fifthly, determining the sum of the confidence cost score, the time cost score and the collision position cost score as a collision cost score.

And a fourth sub-step of determining the sum of the non-collision cost score and the collision cost score as a single track cost score.

And a second step of determining the sum of the determined single track cost scores as a second cost score.

Step 1033, generating track cost information based on the target vehicle track information, the first price score and the second cost score.

In some embodiments, the executing entity may generate the track cost information based on the target vehicle track information, the first cost score, and the second cost score. The track cost information may be information of penalty cost corresponding to a difference between the corresponding own vehicle track and the expected track. First, the sum of the first price score and the second cost score is determined as a vehicle track cost score. And then, determining the self-vehicle track cost value and the self-vehicle track mark included in the target self-vehicle track information as track cost information.

The second cost score generating step and the related content are taken as an invention point of the embodiment of the disclosure, so that the technical problem that the vehicle track information cannot be generated and the running efficiency of the vehicle is reduced in the second technical problem mentioned in the background art is solved. Factors that cause failure to generate vehicle track information and reduce the efficiency of vehicle travel are often as follows: since the obstacle vehicles may have a plurality of uncertain predicted tracks, if the collision cost between the own vehicle and the obstacle vehicles is set to infinity, it is difficult to determine one own vehicle track capable of avoiding all the obstacle vehicles, thereby easily causing the failure to generate vehicle track information; alternatively, even if the own vehicle trajectory can be determined, the own vehicle trajectory will cause the own vehicle to fail to normally advance due to continuous deceleration and braking, thereby reducing the efficiency of the vehicle running. If the factors are solved, the effects of generating the vehicle track information and improving the vehicle running efficiency can be achieved. To achieve this effect, for each vehicle track, an interaction cost between the vehicle track and each obstacle track is determined, and each interaction cost is determined as a second cost score corresponding to the vehicle track. Specifically, for the own vehicle track and any one of the obstacle tracks, first, an uncorrupted time group and a collision time group corresponding to the obstacle track are determined according to whether the obstacle vehicle and the current vehicle are expected to collide at respective times. Then, based on the distance between the current vehicle's trajectory point and the obstacle's vehicle's trajectory point at each instant, the combined uncorrupted cost corresponding to each uncorrupted instant vehicle's trajectory and obstacle's trajectory can be determined. Then, the comprehensive collision cost corresponding to the vehicle track and the obstacle track at each collision time can be determined according to the track collision confidence of the obstacle track, the time interval between the collision time and the current time, the number of collision times and the distance between the current vehicle track point and the center of the upper and lower boundaries of the running displacement of the obstacle. And finally, determining the comprehensive non-collision cost and collision cost as the interaction cost of the vehicle track and one obstacle track. Therefore, the interaction cost between the vehicle track and the obstacle track is considered from the two angles of the collision time and the non-collision time, and the collision cost between the vehicle and the obstacle vehicle is not set to be infinity, but the collision cost between the vehicle track and the obstacle track is determined according to the known information of the track collision confidence degree of the obstacle track and the relative position between the vehicle and the obstacle vehicle, so that the interaction cost between the vehicle corresponding to each vehicle track and the obstacle vehicle is more accurate. Thus, it is convenient to determine the own vehicle trajectory with a smaller potential collision risk as the vehicle trajectory information. Further, the efficiency of vehicle running is improved.

And 104, selecting one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information.

In some embodiments, the execution body may select, as the target track cost information, track cost information that satisfies a preset cost condition from the generated track cost information. The preset cost condition may be: the track cost information comprises the track cost scores of the vehicles, which are the minimum value of the track cost scores of the vehicles.

And 105, determining the target vehicle track information corresponding to the target track cost information as vehicle track information.

In some embodiments, the executing body may determine the target vehicle track information corresponding to the target track cost information as the vehicle track information. The vehicle track information can represent a vehicle track with the minimum driving cost. The target vehicle track information set may be the same as the vehicle track identifier included in the target track cost information, and the target vehicle track information set may be determined as the vehicle track information.

Optionally, the executing body may further send the vehicle track information to a vehicle control module for controlling movement of the vehicle. The vehicle control module may be a module that controls movement of the vehicle by various instructions. The above instructions may include, but are not limited to, at least one of: acceleration instructions, deceleration instructions, braking instructions, etc.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a vehicle track information generating apparatus, which correspond to those method embodiments shown in fig. 1, and which are particularly applicable to various electronic devices.

As shown in fig. 2, the vehicle track information generating apparatus 200 of some embodiments includes: an acquisition unit 201, a preprocessing unit 202, an execution unit 203, a selection unit 204, and a determination unit 205. Wherein the acquiring unit 201 is configured to acquire an obstacle track information set and a vehicle track information set of a current vehicle; a preprocessing unit 202 configured to preprocess the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set; an execution unit 203 configured to execute, for each target vehicle track information in the target vehicle track information set, the following steps: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; generating track cost information based on the target vehicle track information, the first price score and the second cost score; a selecting unit 204 configured to select one piece of track cost information satisfying a preset cost condition from the generated track cost information as target track cost information; the determining unit 205 is configured to determine target own-vehicle track information corresponding to the target track cost information as vehicle track information.

It will be appreciated that the elements described in the apparatus 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and resulting benefits described above for the method are equally applicable to the apparatus 200 and the units contained therein, and are not described in detail herein.

With further reference to fig. 3, a schematic structural diagram of an electronic device 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be embodied in the apparatus; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring an obstacle track information set and a current vehicle track information set; preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set; for each target vehicle track information in the target vehicle track information set, executing the following steps: analyzing the target vehicle track information to obtain a first price value; generating a second cost score based on the target vehicle track information and the target obstacle track information set; generating track cost information based on the target vehicle track information, the first price score and the second cost score; selecting one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information; and determining the target vehicle track information corresponding to the target track cost information as vehicle track information.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, a preprocessing unit, an execution unit, a selection unit, and a determination unit. The names of these units do not constitute limitations on the unit itself in some cases, and the acquisition unit may also be described as "a unit that acquires an obstacle trajectory information set and a vehicle trajectory information set of the current vehicle", for example.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A vehicle track information generation method, comprising:

acquiring an obstacle track information set and a current vehicle track information set;

preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set;

for each target vehicle track information in the target vehicle track information set, executing the following steps:

analyzing the target vehicle track information to obtain a first price value, wherein the first price value is a cost value of the difference between the corresponding vehicle track and the expected track;

generating a second cost score based on the target vehicle track information and the target obstacle track information set, wherein the second cost score is a cost value of interaction between the corresponding vehicle track and the obstacle track;

generating track cost information based on the target vehicle track information, the first price score and the second cost score, wherein the track cost information is information of punishment cost corresponding to the difference between the corresponding vehicle track and the expected track;

selecting one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information;

And determining the target vehicle track information corresponding to the target track cost information as vehicle track information.

2. The method of claim 1, wherein the method further comprises:

and sending the vehicle track information to a vehicle control module for controlling the movement of the vehicle.

3. The method of claim 1, wherein the preprocessing the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set comprises:

performing collision detection on the obstacle track information set and the vehicle track information set to obtain a target collision track information set;

and generating a target vehicle track information set and a target obstacle track information set based on the vehicle track information set and the target collision track information set.

4. The method of claim 3, wherein the generating a target vehicle track information set and a target obstacle track information set based on the vehicle track information set and the target collision track information set comprises:

for each of the set of vehicle track information, performing the steps of:

Mapping the vehicle track information to obtain a vehicle position time information set;

carrying out fusion processing on the vehicle track information and the vehicle position time information group to obtain target vehicle track information;

for each target collision trajectory information in the set of target collision trajectory information, performing the steps of:

mapping the target collision track information to obtain an obstacle displacement time information set;

and carrying out fusion processing on the target collision track information and the obstacle displacement time information group to obtain target obstacle track information.

5. The method of claim 1, wherein the generating a second cost score based on the target vehicle trajectory information and the target obstacle trajectory information set comprises:

for each target obstacle trajectory information in the set of target obstacle trajectory information, performing the steps of:

detecting the target obstacle track information to obtain an uncorrupted time group and a collision time group;

generating a non-collision cost score based on the non-collision time group, the target vehicle track information and the target obstacle track information;

Generating a collision cost score based on the collision time group, the target vehicle track information and the target obstacle track information;

determining the sum of the non-collision cost score and the collision cost score as a single track cost score;

the sum of the determined individual single-track cost scores is determined as a second cost score.

6. The method of claim 5, wherein the target vehicle track information comprises a vehicle track point information sequence and the target obstacle track information comprises an obstacle track point information sequence; and

the generating an uncorrupt cost score based on the uncorrupt time group, the target vehicle track information, and the target obstacle track information includes:

for each uncorrupt time in the set of uncorrupt time instants, performing the steps of:

selecting one vehicle track point information matched with the non-collision moment from a vehicle track point information sequence included in the target vehicle track information as first vehicle track point information;

selecting one obstacle track point information matched with the non-collision moment from an obstacle track point information sequence included in the target obstacle track information as first obstacle track point information;

Generating a target non-collision cost score based on the first vehicle track point information and the first obstacle track point information;

and determining the sum of the generated non-collision cost scores of the targets as the non-collision cost score.

7. The method of claim 6, wherein the target obstacle trajectory information further comprises a trajectory collision confidence; and

the generating a collision cost score based on the collision time group, the target vehicle track information and the target obstacle track information includes:

determining a product of a preset confidence coefficient weight value and a track collision confidence coefficient included in the target obstacle track information as a confidence coefficient cost value;

generating a time cost value based on a preset collision time weight value, a preset collision time quantity weight value, a preset track end time value and a preset collision time group;

for each collision time in the set of collision times, performing the steps of:

selecting one vehicle track point information matched with the collision moment from a vehicle track point information sequence included in the target vehicle track information as second vehicle track point information;

selecting one obstacle track point information matched with the collision moment from an obstacle track point information sequence included in the target obstacle track information as second obstacle track point information;

Generating a target collision cost score based on the second vehicle track point information and the second obstacle track point information;

determining the sum of the generated target collision cost scores as a collision position cost score;

and determining the sum of the confidence cost score, the time cost score and the collision position cost score as a collision cost score.

8. A vehicle track information generating apparatus comprising:

an acquisition unit configured to acquire an obstacle trajectory information set and a vehicle trajectory information set of a current vehicle;

the preprocessing unit is configured to preprocess the obstacle track information set and the vehicle track information set to obtain a target vehicle track information set and a target obstacle track information set;

an execution unit configured to execute, for each target vehicle track information in the target vehicle track information set, the steps of:

the selection unit is configured to select one piece of track cost information meeting a preset cost condition from the generated track cost information as target track cost information;

and the determining unit is configured to determine the target vehicle track information corresponding to the target track cost information as vehicle track information.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.

10. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-7.