CN112824198B

CN112824198B - Track decision method, device, equipment and storage medium

Info

Publication number: CN112824198B
Application number: CN201911151252.3A
Authority: CN
Inventors: 李柏
Original assignee: Beijing Jingdong Qianshi Technology Co Ltd
Current assignee: Beijing Jingdong Qianshi Technology Co Ltd
Priority date: 2019-11-21
Filing date: 2019-11-21
Publication date: 2023-05-02
Anticipated expiration: 2039-11-21
Also published as: CN112824198A

Abstract

The embodiment of the invention discloses a track decision method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a road passing area of a structured road to be driven by a target vehicle; determining the track information to be selected of each track to be selected in the road passing area, wherein the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information; and determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the information of the candidate tracks. By the technical scheme provided by the embodiment of the invention, the accuracy of track decision can be improved.

Description

Track decision method, device, equipment and storage medium

Technical Field

The embodiment of the invention relates to an automatic driving technology, in particular to a track decision method, a track decision device, track decision equipment and a storage medium.

Background

Typically, a vehicle may be driven automatically in a structured road. Track decisions (i.e., operational decisions) are often required before a vehicle is routed to determine which side the vehicle is traversing obstacles and whether to preempt or let.

At present, track decision is often performed by using a decision mode of path+speed, and a specific decision process is as follows: firstly, deciding a running path, then, based on the running path, matching corresponding speeds, deciding a rough running track, and then, carrying out smoothing treatment on the running track during track planning.

However, in the process of implementing the present invention, the inventors found that at least the following problems exist in the prior art:

in the existing path+speed decision mode, when a path is decided, any factor related to speed is not considered, namely the situation of dynamic obstacles is not considered, and then when the speed is decided, the situation that the reasonable speed cannot be matched due to the fact that the dynamic obstacles exist on the decided path are more, so that the vehicle cannot reach a destination can not be obtained, a reasonable and feasible decision track can not be obtained, and the accuracy of track decision is greatly reduced.

Disclosure of Invention

The embodiment of the invention provides a track decision method, a track decision device, track decision equipment and a storage medium, so as to improve the accuracy of track decision.

In a first aspect, an embodiment of the present invention provides a track decision method, including:

acquiring a road passing area of a structured road to be driven by a target vehicle;

Determining the track information to be selected of each track to be selected in the road passing area, wherein the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information;

and determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the candidate track information.

In a second aspect, an embodiment of the present invention further provides a track decision device, including:

the road passing area acquisition module is used for acquiring a road passing area of a structured road to be driven by the target vehicle;

the system comprises a track information determining module, a track information selecting module and a track information selecting module, wherein the track information determining module is used for determining track information to be selected of each track to be selected in the road traffic area, the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information;

and the target track determining module is used for determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the candidate track information.

In a third aspect, an embodiment of the present invention further provides an apparatus, including:

One or more processors;

a memory for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the trajectory decision method as provided by any embodiment of the present invention.

In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a trajectory decision method as provided by any of the embodiments of the present invention.

According to the embodiment of the invention, the track information to be selected of each track to be selected in the road passing area of the structured road is determined, and the track information to be selected comprises the path information and preset parameter information, namely the time information or the speed information, so that when the target track of the target vehicle is determined according to the obstacle distribution data in the road passing area and the track information to be selected, the track decision can be carried out simultaneously on the basis of the factors of the path and the speed or the time, the more accurate, reasonable and feasible target track is obtained, and the decision accuracy is greatly improved.

Drawings

FIG. 1 is a flowchart of a track decision method according to a first embodiment of the present invention;

FIG. 2 is an example of determining a candidate trajectory according to a first embodiment of the present invention;

FIG. 3 is a flowchart of a track decision method according to a second embodiment of the present invention;

FIG. 4 is a flowchart of a track decision method according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a track decision device according to a fourth embodiment of the present invention;

fig. 6 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.

Detailed Description

The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.

Example 1

Fig. 1 is a flowchart of a track decision method according to an embodiment of the present invention, where the embodiment is applicable to a situation of track decision for an automatically driven vehicle on a structured road. The method may be performed by a trajectory decision device, which may be implemented in software and/or hardware, integrated in a device with autopilot functionality, such as any type of vehicle. As shown in fig. 1, the method specifically includes the following steps:

S110, acquiring a road passing area of a structured road to be driven by the target vehicle.

The target vehicle may refer to any type of vehicle for which a trajectory decision is currently to be made. The structured road may refer to a road with a driving rule on which the target vehicle is to be driven. Illustratively, the structured road may be a road having a guide wire to indicate a traveling direction, such as an urban road, or the like. The road traffic area may refer to a passable area range in the structured road, which may be a road area surrounded by left and right boundaries of the structured road.

S120, determining the track information to be selected of each track to be selected in the road traffic area, wherein the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information.

The candidate trajectory may be a trajectory that the target vehicle can travel in the road traffic area. The preset parameter may be a parameter for directly or indirectly characterizing a driving speed condition of the target vehicle, and may be a speed parameter or a time parameter. The track information to be selected comprises path information for representing the running route of the target vehicle and preset parameter information for representing the running speed condition of the target vehicle, so that when track decision is made based on the track information to be selected, factors of the path and the speed or time can be considered at one time, and the track decision is more accurate.

Specifically, all the candidate trajectories in the road traffic area and the candidate trajectory information of each candidate trajectory may be determined based on a preset hierarchical sampling manner. Illustratively, S120 may include: layering the guide lines in the road passing area according to the preset layer number, and taking the normal line at the intersection point position of each layer and the guide lines as a boundary line of the corresponding layer; dividing the dividing line of each layer according to the number of preset nodes, and taking each divided node as a driving node of the target vehicle on the dividing line; determining each parameter value to be selected when the target vehicle runs to the running node according to the preset parameter value quantity; and selecting a driving node on the boundary line of each layer, selecting a parameter value to be selected for each driving node, and taking each driving node and each parameter value to be selected as track information to be selected of a track to be selected.

The preset number of layers may be preset, and the total number of layers divided along the guide line in the road traffic area may be set. The preset number of nodes may be preset, and the total number of running nodes divided on the demarcation line of each layer. The travel node may refer to a position where the vehicle is located when traveling on the demarcation line. The number of values of the preset parameters may be preset, and the total number of all the values of the preset parameters is set within the maximum allowable range.

Specifically, in the road traffic area, the guiding lines in the road traffic area may be layered into a preset number of layers at equal intervals or unequal intervals of mileage, and a normal line of the guiding lines is constructed at the intersection position of each layer and the guiding lines, and the normal line is used as a boundary line of the corresponding layer. Dividing the boundary line of each layer into preset node numbers at equal intervals or unequal intervals, and taking each divided node as a driving node of the target vehicle on the boundary line. When the preset parameter is a speed parameter, that is, an average longitudinal speed of the target vehicle moving from the current layer to the next layer, a value of which the number is the value of the preset parameter can be set for the average longitudinal speed based on the allowable maximum longitudinal speed. When the preset parameter is a time parameter, that is, a time interval consumed by the target vehicle moving from the current layer to the next layer, the time interval may be set to a value equal to the value of the preset parameter based on the length (i.e., the mileage) of the guide wire and the allowable maximum longitudinal speed. Wherein, the longitudinal direction refers to the direction along the guiding line, and the corresponding transverse direction refers to the direction perpendicular to the guiding line. Selecting one driving node from all driving nodes on the boundary line of each layer, selecting one parameter value to be selected from all parameter values to be selected for each driving node, taking each driving node and each parameter value to be selected as track information to be selected of a track to be selected, and carrying out the same circulation until track information to be selected of all different tracks to be selected is determined.

Exemplary, FIG. 2 shows a determinationExamples of candidate trajectories. The index lines in fig. 2 can be represented in a cartesian coordinate system (i.e., a rectangular coordinate system) as: Γ (x(s), y (s)), where s ε [0, L ]]And corresponding to a longitudinal mileage interval related to the track decision. The guide line can be divided into a preset layer number N at equal intervals according to mileage _layer The corresponding mileage of the kth layer is that

The intersection point position of the kth layer and the finger leads is P _k ＝(x(s _k ),y(s _k ) And P on the index line _k The normal at which is taken as the dividing line k of the kth layer. Setting a preset node number N on the boundary line of each layer _node Equidistant driving nodes. The starting point position of the target vehicle may be set to Q ₀ = (x (0), y (0)), which may correspond to a travel node on layer 0. By selecting a driving node Q on each layer _k And based on the layer sequence, sequentially connecting each selected driving node to obtain a broken line section ++>

As a complete candidate path in a cartesian coordinate system.

When the preset parameter is the average longitudinal speed of the target vehicle moving from the current layer to the next layer, the average longitudinal speed of each node on the kth layer

Is composed of the sets of values +.>

The method comprises the following steps:

/>

wherein v is _max Representing the maximum allowable longitudinal speed; n (N) _par The preset parameter value number is indicated. When j=0, the number of the groups,

0, indicating that the target vehicle does not reach the kth layer, which reaches the kth-1 layer furthest, as far as the target vehicle can reach the kth-1 layer, an average longitudinal speed from the front layer is required +.>

And (5) determining.

Similarly, when the preset parameter is the time interval consumed by the target vehicle moving from the current layer to the next layer, the set ψ of the respective values of the time interval Δt of each node on the kth layer _t The method comprises the following steps:

when j=0, the number of the groups,

for 0, i.e. Δt to go to infinity, indicating that the target vehicle will not reach the k-th floor, which is furthest to the k-1 th floor, as far as the target vehicle can reach the k-1 th floor, it is determined by the time interval Δt of the preceding floor.

It should be noted that, since the driving node on each layer and the parameter value to be selected of each driving node are independently selected, it is possible to obtain

And the track information to be selected of different tracks to be selected.

S130, determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the information of the candidate tracks.

The obstacle distribution data may refer to position information of each static obstacle and each dynamic obstacle in the road traffic area. The target trajectory may refer to a decision trajectory obtained after trajectory decision.

Specifically, for each track to be selected, the track cost value of the track to be selected, that is, the unreasonable degree of the track to be selected planning, can be determined based on the track information to be selected of the track to be selected and the obstacle distribution data in the road traffic area. And according to the track cost value of each track to be selected, the track to be selected with the minimum track cost value can be used as the target track.

Illustratively, each candidate track in this embodiment, while being different, may exist in the same sub-structure. For example, if two candidate trajectories only differ in the selection of the travel node of the kth layer, the cost value of the broken line segment 0 from the 0 th layer to the kth-1 th layer and the cost value of the line segment a from the kth-1 th layer need to be determined when the quality of one candidate trajectory is evaluated, the cost value of the broken line segment 0 from the 0 th layer to the kth-1 th layer and the cost value of the line segment b from the kth-1 th layer need to be determined when the quality of the other trajectory is evaluated, and therefore, the cost value of the broken line segment 0 is repeatedly calculated a plurality of times, so that the situation that the cost value of the line segment 0 is repeatedly calculated a plurality of times can be avoided based on a recursive manner, that is, the embodiment can determine the target trajectory of the target vehicle travel from each candidate trajectory according to the obstacle distribution data in the road passing area and the information of each candidate trajectory based on the dynamic planning (Dynamic Programming, DP) manner, thereby improving the decision efficiency while ensuring accuracy. Wherein, the determination mode of dynamic programming DP can solve the complexity from that required by adopting an enumeration mode

Reduced to O (N) _layer ·(N _par ·N _node ) ² ) The track decision efficiency is greatly improved.

According to the technical scheme, the track information to be selected of each track to be selected in the road passing area of the structured road is determined, the track information to be selected comprises the path information and preset parameter information, namely the time information or the speed information, so that when the target track of the target vehicle is determined according to the obstacle distribution data in the road passing area and the track information to be selected, the track decision can be carried out once and simultaneously based on the factors of the path and the speed or the time, the more accurate, reasonable and feasible target track is obtained, and the decision accuracy is greatly improved.

Based on the above technical solution, S130 may include: determining at least one punishment parameter value corresponding to each candidate track according to the barrier distribution data in the road traffic area and the information of each candidate track; determining the track cost value corresponding to each track to be selected according to each punishment parameter value; and determining the target track of the target vehicle according to the cost value of each track.

Wherein the penalty parameter value may be a degree for reflecting that the candidate trajectory violates a certain condition in the trajectory decision. The penalty parameter may be one or more, and the corresponding penalty parameter value may also be one or more. When there is only one penalty parameter value, the penalty parameter value may be directly taken as the track cost value. The unreasonable degree of each track to be selected can be accurately estimated through the track cost value, and the track to be selected with the minimum track cost value is used as the target track, so that a more accurate target track can be obtained.

Example two

Fig. 3 is a flowchart of a track decision method according to a second embodiment of the present invention, where the present embodiment optimizes "determining at least one penalty parameter value corresponding to each candidate track according to the obstacle distribution data in the road traffic area and the information of each candidate track" based on the above embodiment. Wherein the same or corresponding terms as those of the above-described embodiments are not explained in detail herein.

Referring to fig. 3, the track decision method provided in this embodiment specifically includes the following steps:

s210, acquiring a road passing area of a structured road to be driven by the target vehicle.

S220, determining the track information to be selected of each track to be selected in the road traffic area, wherein the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information.

S230, determining a first punishment parameter value of each track to be selected for collision according to the obstacle distribution data in the road traffic area and the path information in the track to be selected.

The first penalty parameter value may be used as a safety indicator, and is used to represent a risk degree of collision with an obstacle when the target vehicle runs along the track to be selected, that is, the smaller the first penalty parameter value is, the smaller the risk degree of collision is.

Specifically, the embodiment can consider the situation that the target vehicle collides with the obstacle in practice and the situation that the target vehicle approaches the obstacle or enters the blind area although the target vehicle does not collide, so that the determined first penalty parameter value is more accurate and has a reference value.

Illustratively, S230 may include: determining a punishment value corresponding to each pre-divided space-time grid in the road passing area according to the obstacle distribution data in the road passing area, wherein the collision punishment value of the collision space-time grid where the obstacle in the road passing area is located is the largest; determining each target space-time grid covered by each track to be selected according to the path information in the track to be selected information; determining a target penalty value corresponding to each target space-time grid according to the penalty value corresponding to each space-time grid; and determining a first punishment parameter value of each candidate track collision according to each target punishment value.

Specifically, in order to uniformly consider two cases of actual collision and potential collision, the X-Y-T space corresponding to the road traffic area may be discretized into three-dimensional space-time grids. According to the position information and the speed information of each obstacle in the obstacle distribution data, determining the space-time grid occupied by each obstacle as a collision space-time grid, and presetting the collision penalty value of each collision space-time grid as C _collision . The penalty value for other spatiotemporal meshes in the vicinity of each collision spatiotemporal mesh may decrease, e.g., exponentially decaying, as the spatiotemporal distance between them increases, so that a corresponding penalty value for each spatiotemporal mesh may be obtained. For each track to be selected, determining each space-time grid covered by the track to be selected based on the path information of the track to be selected as a target space-time grid. According to the corresponding relation between the space-time grid and the punishment valueAnd obtaining a target penalty value corresponding to each target space-time grid. In this embodiment, all the target penalty values may be added, and the added result is used as the first penalty parameter value for the collision of the candidate track; all the target penalty values may be averaged, and the obtained average value may be used as the first penalty parameter value for the collision of the candidate track. For example, the first penalty parameter value J for a collision of the candidate trajectory may be determined by the following formula ₁ ：

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

refers to the kth target penalty value; n (N) _sample Refers to the number of target penalty values.

In the construction of the three-dimensional space-time cost map, the collision penalty value C is used _collision The first penalty parameter value is used for punishing the situation that the collision actually occurs, so that the value of the first penalty parameter value is large enough to ensure that the first penalty parameter value of all the candidate trajectories which do not actually occur are smaller than the first penalty parameter value of any one of the candidate trajectories which occur the collision.

S240, determining a second punishment parameter value of discomfort of each track to be selected according to the node coordinates of each running node in the track to be selected, the transverse offset of the running node on each layer relative to the intersection point position and preset parameter information.

The intersection point may be a position where the boundary line of each layer intersects with the guide line. The lateral offset refers to the distance of the travel node on each level from the intersection location. The second penalty parameter value may be used as a comfort index for characterizing the discomfort level of the target vehicle when driving along the candidate trajectory, i.e. the smaller the second penalty parameter value, the smaller the discomfort level. For example, the second penalty parameter value may be used to penalize the situation in which the curvature of the trajectory to be selected is too large and the lateral offset and the longitudinal speed of the trajectory to be selected are frequently changed, which may be characterized in particular by a curvature penalty parameter value, an offset penalty parameter value and a speed penalty parameter value, respectively.

Illustratively, S240 may include the following steps S241-S244:

s241, determining the curvature of the running nodes on each layer except the last layer in the track to be selected according to the node coordinates of every adjacent three running nodes in the track to be selected, and determining curvature penalty parameter values according to the curvatures.

Wherein the curvature penalty parameter value may be used to characterize the degree of curvature of the candidate trajectory so as to penalize the situation of the curvature of the candidate trajectory being too large.

Specifically, a travel path constituted by travel nodes on each layer

On the trace of the folded line segment, every adjacent three driving nodes Q _k-1 -Q _k -Q _k+1 Can determine the traveling node Q _k Curvature at kappa (Q) _k )(k＝1,...,N _layer -1). In this embodiment, the reciprocal of the radius of the unique arc of the three-point driving node may be the curvature. For example, according to Q _k-1 、Q _k And Q _k+1 The node coordinates of the three driving nodes can determine Q _k-1 Q _k 、Q _k Q _k+1 And Q _k-1 Q _k+1 I.e., euclidean distance, and can be determined at traveling node Q by the following formula _k Curvature at:

wherein a, b and c are each Q _k-1 Q _k 、Q _k Q _k+1 And Q _k-1 Q _k+1 Is a length of (c). When determining the curvature of the running node on each layer except the last layer, adding all the curvatures, and taking the added result as a curvature penalty parameter value; all curvatures may be averaged, and the average value obtained may be used as the curvaturePenalty parameter values. For example, the curvature penalty parameter value J may be determined by the following formula _curvature ：

S242, determining an offset penalty parameter value according to the transverse offset of the driving node on each layer in the track information to be selected relative to the intersection point position.

The offset penalty parameter value may be used to characterize a degree of frequent change of the lateral offset of the selected track, so as to penalize a situation in which the lateral offset of the selected track frequently changes.

Specifically, the difference value of the lateral offset on two adjacent layers can be determined according to the lateral offset of the driving node on each layer relative to the intersection point position in the track information to be selected, and the offset penalty parameter value is determined according to each difference value. Illustratively, all the differences may be added, with the addition result being the offset penalty parameter value; all the differences may be averaged, and the obtained average value may be used as the offset penalty parameter value. For example, the offset penalty parameter value J may be determined by the following formula _lateral ：

Wherein lat _k Is the travel node Q on the kth layer _k A lateral offset relative to the intersection location; lat _k-1 Is the traveling node Q on the k-1 layer _k-1 Lateral offset relative to the intersection position.

S243, determining a speed penalty parameter value according to preset parameter information of each driving node in the track information to be selected.

The speed penalty parameter value may be used to characterize a degree of frequent change in the longitudinal speed of the candidate trajectory, so as to penalize a situation in which the longitudinal speed of the candidate trajectory frequently changes.

Specifically, when the preset parameter information is a time interval, an average longitudinal speed corresponding to each driving node may be determined based on the time interval. For example, the average longitudinal speed corresponding to the traveling node may be determined by the following formula:

is the travel node Q on the kth layer _k Is a mean longitudinal velocity of (2); delta T _k Is a traveling node Q _k Is a time interval of (a) for a time period of (b). And determining the difference value of the average longitudinal speeds of two adjacent driving nodes according to the average longitudinal speed of each driving node in each track to be selected, and determining a speed penalty parameter value according to each difference value. Illustratively, all the differences may be added, with the addition result being the speed penalty parameter value; all the differences may be averaged, and the average value obtained may be used as the speed penalty parameter value. For example, the speed penalty parameter value J may be determined by the following formula _longitudinal ：

is the travel node Q on the kth layer _k Is a mean longitudinal velocity of (2); />

Is the traveling node Q on the k-1 layer _k-1 Is used for the longitudinal velocity of the vehicle. In this embodiment, k may start from 2 or 1. When k=1, +.>

Is the target vehicle startThe average longitudinal speed at location, which needs to be determined based on historical travel information. When k in the embodiment starts from 2, the history running information is not required, so that the calculation is more convenient.

S244, determining a second punishment parameter value of discomfort of each candidate track according to the curvature punishment parameter value, the offset punishment parameter value and the speed punishment parameter value.

Specifically, the second penalty parameter value J for each candidate trajectory discomfort may be determined by the following formula ₂ ：

J ₂ ＝w _curvature ·J _curvature +w _lateral ·J _lateral +w _longitudinal ·J _longitudinal

Wherein J is _curvature Refers to the curvature penalty parameter value of the trajectory to be selected; j (J) _lateral The offset penalty parameter value of the track to be selected; j (J) _longitudinal Is the speed penalty parameter value of the track to be selected; w (w) _curvature Curvature weight values that are curvature penalty parameter values; w (w) _lateral An offset weight value that is an offset penalty parameter value; w (w) _longitudinal Is the speed weight value of the speed penalty parameter value. w (w) _curvature 、w _lateral And w _longitudinal Are all values greater than zero.

For each candidate trajectory, the second penalty parameter value for discomfort to the candidate trajectory may be determined using the operations of steps S241-S244 described above.

S250, determining a third penalty parameter value that each track to be selected does not reach the last layer according to preset parameter information in the track to be selected.

The third penalty parameter value may be used as an integrity indicator to represent the incompleteness of the candidate track, i.e. punish the candidate track that finally fails to reach the last layer. The smaller the third penalty parameter value, the smaller the degree of imperfections of the trajectory to be selected.

In particular, there may be an infinite or average longitudinal velocity of the time interval Δt in the time dimension on a layer, such as the kth layer

A 0 means that the target vehicle cannot reach the driving node on the next layer, i.e. the k+1th layer, within the allowed time, so that it is necessary to detect that Δt is infinity for the first time or that the average longitudinal speed +.>

For a stop layer ordinal number of 0, a corresponding third penalty parameter value can be determined according to the stop layer ordinal number, i.e. the larger the stop layer ordinal number, the closer the stop position is to the end point, and the smaller the third penalty parameter value.

Illustratively, S250 may include: according to preset parameter information in the track information to be selected, determining a stop layer ordinal number with zero average longitudinal speed or infinite time interval appearing in each track to be selected; and determining a third penalty parameter value that each track to be selected does not reach the last layer according to the stop layer number, the preset layer number and the single-layer penalty value.

Specifically, for each track to be selected, according to preset parameter information of each running node in track information to be selected, sequentially detecting whether the average longitudinal speed of each running node is zero or whether the time interval is infinity along the sequence from the starting point to the ending point; if yes, determining the layer sequence number of the running node as a stop layer sequence number N _stop (1≤N _stop ≤N _layer ). From the number of stop layers and the preset number of layers, it can be determined that the target vehicle fails to reach N _stop Layer complete movement to the nth _layer And determining a third punishment parameter value of the trace to be selected which does not reach the last layer according to the interval of the layers and a preset single-layer punishment value. For example, the third penalty parameter value J for the selected track that does not reach the last layer may be determined by the following formula ₃ ：

J ₃ ＝(N _layer -N _stop )×C _stop

Wherein C is _stop Is a single layer penalty value greater than zero that is preset.

And S260, determining the track cost value corresponding to each track to be selected according to the first penalty parameter value, the second penalty parameter value and the third penalty parameter value.

Specifically, weighted summation can be performed on each penalty parameter value corresponding to each track to be selected, and the obtained calculation result is used as the track cost value corresponding to the track to be selected.

The track cost value corresponding to each candidate track can be determined by the following formula:

J＝w ₁ ·J ₁ +w ₂ ·J ₂ +w ₃ ·J ₃

wherein J refers to the track cost value of the track to be selected; j (J) ₁ The first punishment parameter value of the collision of the track to be selected is indicated; j (J) ₂ A second punishment parameter value for discomfort of the track to be selected is indicated; j (J) ₃ The third punishment parameter value that the track to be selected does not reach the last layer is indicated; w (w) ₁ A first weight value that is a first penalty parameter value; w (w) ₂ A second weight value that is a second penalty parameter value; w (w) ₃ A third weight value being a third penalty parameter value.

It should be noted that, in the determination of the track cost value corresponding to each candidate track, each weight value, such as the curvature weight value w _curvature Offset weight value w _lateral Speed weight value w _longitudinal First weight value w ₁ Second weight value w ₂ And a third weight value w ₃ And penalty constant values for each non-weight, such as collision penalty value C _collision And monolayer penalty value C _stop The method can be automatically determined in advance based on service requirements and scene manual setting or based on Monte Carlo mode, so that the setting of each weight value and each non-weight punishment constant value is more accurate and reasonable, the determined track cost value is more accurate, the reference value is provided, and the accuracy of track decision is further improved.

S270, determining a target track of the target vehicle according to the cost value of each track.

According to the technical scheme, the track cost value corresponding to each track to be selected is measured by utilizing the first punishment parameter value of collision of each track to be selected, the second punishment parameter value of discomfort of each track to be selected and the third punishment parameter value of each track to be selected which does not reach the last layer, so that the advantages and disadvantages of the track to be selected in three aspects of safety, comfort and integrity can be simultaneously judged, the determination of the target track is more reasonable and accurate, the optimal target track can be conveniently obtained, and the accuracy of track decision is further improved.

Example III

Fig. 4 is a flowchart of a track decision method according to a third embodiment of the present invention, where a detailed description is made of a determination process of determining, based on a monte carlo method, each weight value and each non-weight penalty constant value used in a determination process of determining a track cost value corresponding to a track to be selected on the basis of the above embodiments. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.

Referring to fig. 4, the track decision method provided in this embodiment specifically includes the following steps:

s310, randomly selecting and combining the value of each weight value and the value of each non-weight punishment constant value used in the determination process of the track cost value corresponding to the track to be selected in a positive real number space, and obtaining each combination result to be selected.

The positive real space may be a set formed by preset real numbers greater than 0 based on service requirements. The weight value used in the determination of the track cost value corresponding to the track to be selected may be, but is not limited to, the curvature weight value w in the second embodiment _curvature Offset weight value w _lateral Speed weight value w _longitudinal First weight value w ₁ Second weight value w ₂ And a third weight value w ₃ . The non-weighted penalty constant value used in the determination of the trajectory cost value corresponding to the trajectory to be selected may be, but is not limited to, the collision penalty value C in embodiment two _collision And monolayer penalty value C _stop . The result of the combination to be selected may be represented byThe value of each weight value and the value of each penalty constant value of the non-weight.

Specifically, based on preset selection conditions set in advance, the value of each weight value and the value of each penalty constant value of the non-weight are randomly selected in the positive real number space, and each selected value is combined into a to-be-selected combined result, so that all different to-be-selected combined results can be determined. The preset selection conditions may include: the sum of some weight values is 1, such as the first weight value w ₁ Second weight value w ₂ And a third weight value w ₃ The sum of (2) is 1.

It should be noted that, because there may be a potential conflict between some penalty parameter values, for example, the offset penalty parameter value corresponding to the candidate track with the smaller curvature penalty parameter value is larger, so that a reasonable weight value needs to be set to perform neutralization and comprehensive consideration on various conflicts existing in the penalty parameter value, so that the determination of the track cost value is more accurate.

S320, determining a sample target track corresponding to each candidate combination result from the sample candidate tracks according to sample candidate track information and sample obstacle distribution data of each sample candidate track of the target vehicle in the sample road traffic area.

The sample road traffic area may refer to a road traffic area of a sample structured road, which is preset and is used for determining each weight value and each penalty constant value of non-weight. The embodiment may determine, in advance, sample candidate trajectory information of each sample candidate trajectory in the sample road traffic area based on the preset hierarchical sampling manner provided in the foregoing embodiments.

Specifically, for each weight value and each non-weight penalty constant value in each candidate combination result, the sample target track may be determined from each sample candidate track according to sample candidate track information and sample obstacle distribution data of each sample candidate track of the target vehicle in the sample road traffic area in a similar manner of the target track determination provided in the above embodiments, so that an optimal sample candidate track obtained based on each candidate combination result, that is, a sample target track may be determined.

S330, determining a corresponding running error according to the standard running track in the sample road traffic area and each sample target track.

The standard driving track may be a real track of a high-level driver driving in a sample road traffic area.

Specifically, a sample area surrounded by each sample target track in the sample road traffic area and a standard area surrounded by the standard running track in the sample road traffic area can be determined, and a corresponding running error is obtained by comparing the difference value between each sample area and the standard area. When the running error is smaller, it is indicated that the sample target trajectory has higher similarity with the standard running trajectory, that is, the driving level of the target vehicle is closer to the driver of the higher level.

S340, determining a target combination result from the combination results to be selected according to the driving errors, and obtaining each weight value and each non-weight penalty constant value used in the determination process of the track cost value corresponding to the track to be selected according to the target combination result.

Specifically, the to-be-selected combination result corresponding to the sample target track with the minimum running error can be determined as a target combination result, and specific values of each weight value and each non-weight penalty constant value are obtained based on the target combination result, so that reasonable value can be automatically determined.

S350, acquiring a road passing area of a structured road to be driven by the target vehicle.

S360, determining the track information to be selected of each track to be selected in the road traffic area, wherein the track information to be selected comprises path information and preset parameter information, and the preset parameter comprises time information or speed information.

And S370, determining at least one punishment parameter value corresponding to each candidate track according to the obstacle distribution data in the road traffic area and the information of each candidate track.

Specifically, the operations of steps S310-S340 may be utilized to automatically obtain various weight values, such as a curvature weight value w, used in determining the penalty parameter value in step S370 _curvature Offset weight value w _lateral Speed weight value w _longitudinal And penalty constant values for each non-weight, such as collision penalty C _collision And monolayer penalty value C _stop And determining at least one penalty parameter value corresponding to each candidate track based on the weight values and the penalty constant values.

S380, determining the track cost value corresponding to each track to be selected according to each punishment parameter value.

Specifically, the operations of steps S310 to S340 may be utilized to determine each weight value used in determining the track cost value based on each penalty parameter value in step S380, such as: first weight value w ₁ Second weight value w ₂ And a third weight value w ₃ And determining the track cost value corresponding to each track to be selected based on the weight values.

It should be noted that, the values of the penalty constant values of each weight value and each non-weight value selected for different types of vehicles are different, so that each weight value and each non-weight penalty constant value corresponding to each vehicle can be determined in advance, and a corresponding relation between the type identifier of each vehicle and each weight value and each non-weight penalty constant value is established, so that the specific values of each weight value and each non-weight penalty constant value corresponding to the target vehicle can be obtained more quickly based on the type identifier of the target vehicle and the corresponding relation.

S390, determining the target track of the target vehicle according to the cost value of each track.

According to the technical scheme, all the conditions of the to-be-selected combined results are determined in the positive real number space, and an optimal target combined result is selected from all the to-be-selected combined results based on the standard driving track in the sample road traffic area, so that all weight values and all non-weight punishment constant values can be set reasonably and accurately automatically, and the accuracy of track decision is improved.

Based on the above technical solution, S320 may include: according to each combination result to be selected, determining a sample cost value corresponding to each sample track to be selected according to sample track information and sample obstacle distribution data of each sample track to be selected of the target vehicle in a sample road passing area; screening the to-be-selected combined result meeting the preset punishment condition from the to-be-selected combined results according to the cost value of each sample to be used as a candidate combined result; and determining a sample target track corresponding to each candidate combination result according to the sample cost value corresponding to each sample candidate track determined for each candidate combination result.

The preset punishment condition may refer to punishment logic that needs to be met by a preset candidate track based on a service scene, so that setting of each weight value and each non-weight punishment constant value is more reasonable. Illustratively, the preset penalty conditions may include, but are not limited to: the sample cost value corresponding to any one sample to-be-selected track which does not collide and reaches the last layer is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides or does not reach the last layer; and the sample cost value corresponding to any one sample to-be-selected track which does not collide is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides; and the sample cost value corresponding to any one of the sample candidate trajectories reaching the last layer is smaller than the sample cost value corresponding to any one of the sample candidate trajectories not reaching the last layer.

Specifically, a penalty constant value, such as a collision penalty value C, for each non-weight is set _collision And monolayer penalty value C _stop Collision penalty value C _collision And monolayer penalty value C _stop All require values as large as possible, but due to the collision penalty value C _collision And monolayer penalty value C _stop The two parameters are not related at all and have different action modes, so that the sizes of the two parameters cannot be directly reviewed, whether the specific values of the two parameters meet reasonable punishment logic or not can be detected based on preset punishment conditions, and the two parameters are subjected to the following stepsAnd the candidate combination results meeting the preset punishment conditions are used as candidate combination results, so that candidate combination results meeting the preset punishment conditions are screened out from the candidate combination results, and then corresponding sample target tracks are determined for each candidate combination result, so that the setting of punishment constant values is more reasonable.

Accordingly, the "determining the target combination result from the respective combination results to be selected" in S340 may include: and determining a target combination result from the candidate combination results according to each driving error. According to the candidate combination results meeting the preset punishment conditions, corresponding running errors are determined according to the standard running track in the sample road passing area and the sample target track corresponding to each candidate combination result, and the candidate combination result corresponding to the sample target track with the smallest running error can be determined as the target combination result, so that the optimal target combination result can be determined from all the candidate combination results meeting the preset punishment conditions, the rationality and the accuracy of the target combination result are further improved, and the accuracy of track decision is further improved.

The following is an embodiment of a track decision device provided by the embodiment of the present invention, which belongs to the same inventive concept as the track decision method of the above embodiments, and details of the track decision device embodiment that are not described in detail may refer to the above embodiment of the track decision method.

Example IV

Fig. 5 is a schematic structural diagram of a track decision device according to a fourth embodiment of the present invention, where the embodiment is applicable to a situation of performing track decision on an autopilot vehicle on a structured road, the device specifically includes: the road traffic area acquisition module 410, the candidate trajectory information determination module 420, and the target trajectory determination module 430.

The road traffic area obtaining module 410 is configured to obtain a road traffic area of a structured road to be driven by the target vehicle; the track information to be selected determining module 420 is configured to determine track information to be selected of each track to be selected in the road traffic area, where the track information to be selected includes path information and preset parameter information, and the preset parameter includes time information or speed information; the target track determining module 430 is configured to determine a target track for the target vehicle to travel from the candidate tracks according to the obstacle distribution data and the candidate track information in the road traffic area.

Optionally, the candidate trajectory information determining module 420 is specifically configured to: layering the guide lines in the road passing area according to the preset layer number, and taking the normal line at the intersection point position of each layer and the guide lines as a boundary line of the corresponding layer; dividing the dividing line of each layer according to the number of preset nodes, and taking each divided node as a driving node of the target vehicle on the dividing line; determining each parameter value to be selected when the target vehicle runs to the running node according to the preset parameter value quantity; and selecting a driving node on the boundary line of each layer, selecting a parameter value to be selected for each driving node, and taking each driving node and each parameter value to be selected as track information to be selected of a track to be selected.

Optionally, the target trajectory determination module 430 includes:

the punishment parameter value determining unit is used for determining at least one punishment parameter value corresponding to each candidate track according to the obstacle distribution data in the road traffic area and the information of each candidate track;

the track cost value determining unit is used for determining the track cost value corresponding to each track to be selected according to each punishment parameter value;

And the target track determining unit is used for determining the target track of the target vehicle according to the cost value of each track.

Optionally, the penalty parameter value determining unit includes:

the first penalty parameter value determining subunit is used for determining a first penalty parameter value of each candidate track collision according to the obstacle distribution data in the road traffic area and the path information in the candidate track information;

the second punishment parameter value determining subunit is used for determining a second punishment parameter value uncomfortable for each track to be selected according to the node coordinates of each running node in the track information to be selected, the transverse offset of the running node on each layer relative to the intersection point position and preset parameter information;

and the third punishment parameter value determining subunit is used for determining a third punishment parameter value of each track to be selected which does not reach the last layer according to preset parameter information in the track to be selected information.

Optionally, the track cost value determining unit is specifically configured to: the track cost value corresponding to each track to be selected is determined by the following formula:

J＝w ₁ ·J ₁ +w ₂ ·J ₂ +w ₃ ·J ₃

Optionally, the first penalty parameter value determining subunit is specifically configured to: determining a punishment value corresponding to each pre-divided space-time grid in the road passing area according to the obstacle distribution data in the road passing area, wherein the collision punishment value of the collision space-time grid where the obstacle in the road passing area is located is the largest; determining each target space-time grid covered by each track to be selected according to the path information in the track to be selected information; determining a target penalty value corresponding to each target space-time grid according to the penalty value corresponding to each space-time grid; and determining a first punishment parameter value of each candidate track collision according to each target punishment value.

Optionally, the second penalty parameter value determining subunit is specifically configured to: determining the curvature of the running nodes on each layer except the last layer in the track to be selected according to the node coordinates of every adjacent three running nodes in the track to be selected, and determining curvature penalty parameter values according to the curvatures; determining an offset penalty parameter value according to the transverse offset of the driving node on each layer in the track information to be selected relative to the intersection point position; determining a speed penalty parameter value according to preset parameter information of each driving node in the track information to be selected; and determining a second punishment parameter value of discomfort of each candidate track according to the curvature punishment parameter value, the offset punishment parameter value and the speed punishment parameter value.

Optionally, the third penalty parameter value determining subunit is specifically configured to: according to preset parameter information in the track information to be selected, determining a stop layer ordinal number with zero average longitudinal speed or infinite time interval appearing in each track to be selected; and determining a third penalty parameter value that each track to be selected does not reach the last layer according to the stop layer number, the preset layer number and the single-layer penalty value.

Optionally, the apparatus further comprises:

the numerical value determining module is used for determining each weight value and each non-weight penalty constant value used in the determination process of the track cost value corresponding to the track to be selected based on the Monte Carlo mode before determining the target track of the target vehicle from the tracks to be selected according to the obstacle distribution data and the track to be selected information in the road passing area.

Optionally, the numerical value determining module includes:

the to-be-selected combination result determining unit is used for randomly selecting and combining the value of each weight value and the value of each non-weight punishment constant value used in the determination process of the track cost value corresponding to the to-be-selected track in the positive real number space to obtain each to-be-selected combination result;

The sample target track determining unit is used for determining a sample target track corresponding to each combination result from each sample target track according to sample target track information and sample obstacle distribution data of each sample target track of the target vehicle in the sample road passing area;

the running error determining unit is used for determining corresponding running errors according to the standard running track in the sample road passing area and each sample target track;

and the numerical value determining unit is used for determining a target combination result from the combination results to be selected according to the running errors, and obtaining each weight value and each non-weight penalty constant value used in the determination process of the track cost value corresponding to the track to be selected according to the target combination result.

Optionally, the sample target track determining unit is specifically configured to: according to each combination result to be selected, determining a sample cost value corresponding to each sample track to be selected according to sample track information and sample obstacle distribution data of each sample track to be selected of the target vehicle in a sample road passing area; screening the to-be-selected combined result meeting the preset punishment condition from the to-be-selected combined results according to the cost value of each sample to be used as a candidate combined result; according to the sample cost value corresponding to each sample to-be-selected track determined for each candidate combination result, determining a sample target track corresponding to each candidate combination result; accordingly, the numerical value determining unit is specifically configured to: and determining a target combination result from the candidate combination results according to each driving error.

Optionally, presetting the penalty condition includes:

the sample cost value corresponding to any one sample to-be-selected track which does not collide and reaches the last layer is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides or does not reach the last layer; and the sample cost value corresponding to any one sample to-be-selected track which does not collide is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides; and the sample cost value corresponding to any one of the sample candidate trajectories reaching the last layer is smaller than the sample cost value corresponding to any one of the sample candidate trajectories not reaching the last layer.

The track decision device provided by the embodiment of the invention can execute the track decision method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the track decision method.

Example five

Fig. 6 is a schematic structural diagram of a device according to a fifth embodiment of the present invention. Fig. 6 shows a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 6 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.

As shown in fig. 6, device 12 is in the form of a general purpose computing device. Components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in fig. 6, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.

Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with device 12, and/or any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, via network adapter 20. As shown, network adapter 20 communicates with other modules of device 12 over bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing a track decision method step provided by the present embodiment, the method comprising:

and determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the information of the candidate tracks.

Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the trajectory decision method provided by any embodiment of the present invention.

Example six

A sixth embodiment provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the track decision method steps as provided by any embodiment of the present invention, the method comprising:

The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: 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 this document, 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.

The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. 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: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present invention 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).

It will be appreciated by those of ordinary skill in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed over a network of computing devices, or they may alternatively be implemented in program code executable by a computer device, such that they are stored in a memory device and executed by the computing device, or they may be separately fabricated as individual integrated circuit modules, or multiple modules or steps within them may be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims

1. A trajectory decision method, comprising:

determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the candidate track information;

the determining the track information to be selected of each track to be selected in the road traffic area comprises the following steps:

layering the guide lines in the road passing area according to the preset layer number, and taking the normal line at the intersection point position of each layer and the guide lines as a boundary line of the corresponding layer;

dividing the dividing line of each layer according to the number of preset nodes, and taking each divided node as a driving node of the target vehicle on the dividing line;

determining each parameter value to be selected when the target vehicle runs to the running node according to the preset parameter value quantity;

And selecting a driving node on the boundary line of each layer, selecting a parameter value to be selected for each driving node, and taking each driving node and each parameter value to be selected as track information to be selected of a track to be selected.

2. The method according to claim 1, wherein determining a target track for the target vehicle to travel from among the candidate tracks based on the obstacle distribution data in the road traffic area and the respective candidate track information, comprises:

determining at least one penalty parameter value corresponding to each track to be selected according to the obstacle distribution data in the road traffic area and the track to be selected;

determining the track cost value corresponding to each track to be selected according to each punishment parameter value;

and determining the target track of the target vehicle according to the track cost value.

3. The method of claim 2, wherein determining at least one penalty parameter value for each of the candidate trajectories based on the obstacle distribution data in the road traffic zone and the respective candidate trajectory information comprises:

determining a first punishment parameter value of each candidate track collision according to the obstacle distribution data in the road traffic area and the path information in the candidate track information;

Determining a second punishment parameter value of discomfort of each track to be selected according to the node coordinates of each running node in the track to be selected, the transverse offset of the running node on each layer relative to the intersection point position and preset parameter information;

and determining a third punishment parameter value of each track to be selected which does not reach the last layer according to preset parameter information in the track to be selected information.

4. A method according to claim 3, wherein the track cost value corresponding to each of the candidate tracks is determined by the following formula:

J＝w ₁ ·J ₁ +w ₂ ·J ₂ +w ₃ ·J ₃

wherein J refers to the track cost value of the track to be selected; j (J) ₁ The first punishment parameter value of the collision of the track to be selected is indicated; j (J) ₂ A second penalty parameter value for discomfort of the candidate trajectory; j (J) ₃ Means that the trajectory to be selected does not reach the third penalty parameter value of the last layer; w (w) ₁ A first weight value that is the first penalty parameter value; w (w) ₂ A second weight value that is the second penalty parameter value; w (w) ₃ Is a third weight value of the third penalty parameter value.

5. A method according to claim 3, wherein determining a first penalty parameter value for each of the candidate trajectories to collide based on the obstacle distribution data in the road traffic zone and the path information in the candidate trajectory information, comprises:

Determining a punishment value corresponding to each pre-divided space-time grid in the road passing area according to the obstacle distribution data in the road passing area, wherein the collision punishment value of the collision space-time grid where the obstacle in the road passing area is located is the largest;

determining each target space-time grid covered by each track to be selected according to the path information in the track to be selected;

determining a target penalty value corresponding to each target space-time grid according to the penalty value corresponding to each space-time grid;

and determining a first punishment parameter value of each candidate track collision according to each target punishment value.

6. A method according to claim 3, wherein determining a second penalty parameter value for discomfort of each of the trajectories to be selected based on the node coordinates of each of the travel nodes in the trajectory to be selected, the lateral offset of the travel nodes on each layer relative to the intersection point position, and preset parameter information, comprises:

determining the curvature of the running nodes on each layer except the last layer in the track to be selected according to the node coordinates of every adjacent three running nodes in the track to be selected, and determining curvature penalty parameter values according to the curvatures;

Determining an offset penalty parameter value according to the transverse offset of the driving node on each layer in the track information to be selected relative to the intersection point position;

determining a speed penalty parameter value according to preset parameter information of each driving node in the track information to be selected;

and determining a second punishment parameter value of discomfort of each candidate track according to the curvature punishment parameter value, the offset punishment parameter value and the speed punishment parameter value.

7. A method according to claim 3, wherein determining a third penalty parameter value for each of the candidate tracks that does not reach the last layer according to preset parameter information in the candidate track information comprises:

according to preset parameter information in the track information to be selected, determining a stop layer ordinal number with zero average longitudinal speed or infinite time interval appearing in each track to be selected for the first time;

and determining a third punishment parameter value of each track to be selected which does not reach the last layer according to the stop layer ordinal number, the preset layer number and the single-layer punishment value.

8. The method according to claim 2, characterized by further comprising, before determining a target track on which the target vehicle travels from among the candidate tracks based on the obstacle distribution data in the road traffic area and the respective candidate track information:

And determining each weight value and each non-weight penalty constant value used in the determination process of the track cost value corresponding to the track to be selected based on a Monte Carlo mode.

9. The method of claim 8, wherein determining each weight value and each non-weight penalty constant value used in determining the track cost value corresponding to the candidate track based on a monte carlo approach comprises:

randomly selecting and combining the value of each weight value and the value of each non-weight punishment constant value used in the determination process of the track cost value corresponding to the track to be selected in a positive real number space to obtain each combination result to be selected;

for each candidate combination result, determining a sample target track corresponding to each candidate combination result from each sample candidate track according to sample candidate track information and sample obstacle distribution data of each sample candidate track of the target vehicle in a sample road passing area;

determining corresponding running errors according to the standard running track in the sample road passing area and each sample target track;

And determining a target combination result from the combination results to be selected according to the driving errors, and obtaining each weight value and each non-weight penalty constant value used in the determination process of the track cost value corresponding to the track to be selected according to the target combination result.

10. The method according to claim 9, wherein for each of the candidate combination results, determining, from among the candidate trajectories, a sample target trajectory corresponding to each of the candidate combination results according to sample candidate trajectory information and sample obstacle distribution data of respective sample candidate trajectories of the target vehicle in a sample road traffic area, includes:

for each candidate combination result, determining a sample cost value corresponding to each sample candidate track according to sample candidate track information and sample obstacle distribution data of each sample candidate track of the target vehicle in a sample road passing area;

screening the to-be-selected combined result meeting the preset punishment condition from the to-be-selected combined results according to the cost value of each sample to be used as a candidate combined result;

according to the sample cost value corresponding to each sample candidate track determined for each candidate combination result, determining a sample target track corresponding to each candidate combination result;

Accordingly, determining a target combination result from the candidate combination results according to the driving errors, including:

and determining a target combination result from the candidate combination results according to the running errors.

11. The method of claim 10, wherein the preset penalty condition comprises:

the sample cost value corresponding to any one sample to-be-selected track which does not collide and reaches the last layer is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides or does not reach the last layer;

and the sample cost value corresponding to any one sample to-be-selected track which does not collide is smaller than the sample cost value corresponding to any one sample to-be-selected track which collides;

and the sample cost value corresponding to any one of the sample candidate trajectories reaching the last layer is smaller than the sample cost value corresponding to any one of the sample candidate trajectories not reaching the last layer.

12. A trajectory decision device, comprising:

The target track determining module is used for determining a target track of the target vehicle from the candidate tracks according to the obstacle distribution data in the road traffic area and the candidate track information;

the to-be-selected track information determining module is specifically configured to: layering the guide lines in the road passing area according to the preset layer number, and taking the normal line at the intersection point position of each layer and the guide lines as a boundary line of the corresponding layer; dividing the dividing line of each layer according to the number of preset nodes, and taking each divided node as a driving node of the target vehicle on the dividing line; determining each parameter value to be selected when the target vehicle runs to the running node according to the preset parameter value quantity; and selecting a driving node on the boundary line of each layer, selecting a parameter value to be selected for each driving node, and taking each driving node and each parameter value to be selected as track information to be selected of a track to be selected.

13. A trajectory decision device, characterized in that it comprises:

one or more processors;

a memory for storing one or more programs;

The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the trajectory decision method of any one of claims 1-11.

14. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the trajectory decision method as claimed in any one of claims 1 to 11.