A trajectory generation method, device, computer equipment and storage medium

By obtaining and combining bicycle status information and motion status information, an autonomous driving trajectory that conforms to the kinematic characteristics of the vehicle is generated, which solves the problems of long trajectory planning time and not conforming to the characteristics of the vehicle under complex road conditions, and improves the stability and comfort of the driving trajectory sex.

CN118025226BActive Publication Date: 2024-11-26BEIJING JIDU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410197812.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-22
Publication Date
2024-11-26
Estimated Expiration
2044-02-22

AI Technical Summary

Technical Problem

Under complex road conditions, the autonomous driving trajectory planning algorithm predicts that the driving trajectory is long and does not conform to the vehicle's kinematic characteristics, resulting in poor driving stability and comfort.

Method used

By obtaining the bicycle status information and motion status information of the target vehicle, multiple candidate path curves and speed curves are determined, and the target path curves and speed curves that conform to the kinematic characteristics of the vehicle are selected, and combined to generate the target driving trajectory.

Benefits of technology

The quality of trajectory generation is improved, the stability and comfort of the driving trajectory is ensured, the calculation volume is reduced, and the somatosensory of autonomous driving cars is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118025226B_ABST
    Figure CN118025226B_ABST
Patent Text Reader

Abstract

This disclosure provides a trajectory generation method, apparatus, computer device, and storage medium. The method includes: acquiring vehicle state information of a target vehicle, and determining multiple candidate path curves for the target vehicle based on the vehicle state information; acquiring motion state information of the target vehicle, and determining multiple candidate speed curves for the target vehicle based on the motion state information; selecting a target path curve from the multiple candidate path curves, and selecting a target speed curve from the multiple candidate speed curves; merging the target path curve and the target speed curve to generate a target driving trajectory of the target vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a trajectory generation method, device, computer equipment, and storage medium. Background Art

[0002] With the application of various advanced computer technologies in the automotive field, cars are becoming more and more intelligent. For example, autonomous driving technology can predict the vehicle's driving trajectory by sensing the road conditions, assisting the driver to better control the car. However, in some scenarios with more complex road conditions, such as scenarios with many obstacles around the vehicle, the autonomous driving trajectory planning algorithm takes a long time to predict the driving trajectory, and the predicted driving trajectory may not conform to the vehicle's kinematic characteristics, resulting in poor stability and comfort when the vehicle drives according to the predicted driving trajectory. Summary of the invention

[0003] In view of this, the present disclosure at least provides a trajectory generation method, apparatus, computer device and storage medium.

[0004] In a first aspect, the present disclosure provides a trajectory generation method, comprising:

[0005] Acquiring vehicle state information of a target vehicle, and determining a plurality of candidate path curves for the target vehicle based on the vehicle state information;

[0006] and, obtaining motion state information of the target vehicle, and determining a plurality of candidate speed profiles for the target vehicle based on the motion state information;

[0007] Selecting a target path curve from the plurality of candidate path curves, and selecting a target speed curve from the plurality of candidate speed curves;

[0008] The target path curve and the target speed curve are combined to generate a target driving trajectory of the target vehicle.

[0009] In a possible implementation manner, determining a plurality of candidate path curves for the target vehicle based on the vehicle state information includes:

[0010] Based on the driving strategy of the target vehicle, determining a candidate driving area of ​​the target vehicle in the current driving section;

[0011] Selecting a plurality of candidate path points from the candidate driving area, and determining path point information respectively corresponding to the plurality of candidate path points;

[0012] Based on the vehicle state information and the path point information respectively corresponding to the plurality of candidate path points, a plurality of candidate path curves are generated.

[0013] In a possible implementation manner, generating the candidate path curve based on the vehicle state information and path point information respectively corresponding to the plurality of candidate path points includes:

[0014] Constructing a first relational expression for the candidate path curve; wherein the first relational expression is used to describe the relationship between the lateral coordinate value and the longitudinal coordinate value of each position point in the candidate path curve in the vehicle coordinate system;

[0015] Taking the current position of the target vehicle as the starting position of the candidate path curve, and using the first relational expression to construct a first relational expression for describing the state of the vehicle at the starting position; and

[0016] For each candidate path point among the plurality of candidate path points, taking each candidate path point as the end point position of each candidate path curve, and using the first relational expression to construct a second relational expression for describing the state of the target vehicle when the target vehicle is located at the end point position;

[0017] Based on the first relational expression and the second relational expression, unknown parameters in the first relational expression are solved to obtain the candidate path curve.

[0018] In a possible implementation manner, the vehicle state information includes a first coordinate position, a first heading angle, and a first curvature of the target vehicle, wherein the first coordinate position includes: a first horizontal coordinate and a first vertical coordinate of the target vehicle in the vehicle coordinate system; the path point information includes a second coordinate position, a second heading angle, and a second curvature of the candidate path point; the second coordinate position includes: a second horizontal coordinate and a second vertical coordinate of the candidate path point in the vehicle coordinate system;

[0019] The first relational expression includes: a relational expression for describing the relationship between the first ordinate and the first abscissa, a relational expression for describing the relationship between the first heading angle and the first abscissa, and a relational expression for describing the relationship between the first curvature, the first heading angle and the first abscissa;

[0020] The second relationship includes: a relationship for describing the relationship between the second longitudinal coordinate and the second horizontal coordinate, a relationship for describing the relationship between the second heading angle and the second horizontal coordinate, and a relationship for describing the relationship between the second curvature, the second heading angle and the second horizontal coordinate.

[0021] In a possible implementation manner, the motion state information includes: motion state information of the own vehicle and motion state information of other vehicles;

[0022] The step of determining a plurality of candidate speed curves for the target vehicle based on the motion state information includes:

[0023] Based on the motion state information of the vehicle and the motion state information of the other vehicle, candidate speed points are determined for multiple sampling time points respectively, and a candidate speed and a candidate acceleration corresponding to each of the candidate speed points are determined; wherein two adjacent sampling time points are separated by a preset time length, and each of the sampling time points corresponds to at least one candidate speed point;

[0024] The candidate speed curve is generated based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points.

[0025] In a possible implementation, determining candidate speed points for a plurality of sampling time points based on the motion state information of the own vehicle and the motion state information of the other vehicle, and determining a candidate speed and a candidate acceleration corresponding to each of the candidate speed points, includes:

[0026] For a first sampling time point, based on the motion state information of the own vehicle and the motion state information of the other vehicle, determine a corresponding candidate speed point for the first sampling time point, and determine a candidate speed and a candidate acceleration corresponding to each candidate speed point;

[0027] For each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point, and the motion state information of the other vehicle, the corresponding candidate speed point is determined for each other sampling time point, and the candidate speed and candidate acceleration corresponding to each of the candidate speed points are determined.

[0028] In a possible implementation manner, the self-vehicle motion state information includes a first vehicle speed and a first vehicle acceleration of the target vehicle; the other vehicle motion state information includes a second vehicle speed and a second vehicle acceleration of the other vehicle;

[0029] The step of determining a corresponding candidate speed point for the first sampling time point based on the vehicle motion state information and the other vehicle motion state information, and determining a candidate speed and a candidate acceleration corresponding to each candidate speed point includes:

[0030] Determine the first self-vehicle maximum speed of each candidate speed point corresponding to the first sampling time point based on the interval time between the first sampling time point and the current time, the preset self-vehicle maximum acceleration, and the first vehicle speed; and determine the first self-vehicle minimum speed corresponding to each candidate speed point corresponding to the first sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the first vehicle speed;

[0031] An acceleration interval is formed based on the maximum acceleration of the own vehicle, the minimum acceleration of the own vehicle, and the second vehicle acceleration, and a candidate acceleration of each candidate speed point corresponding to the first sampling time point is determined within the acceleration interval based on the first vehicle acceleration, the target vehicle jerk, the interval time, and the number of candidate speed points corresponding to the first sampling time point;

[0032] A first speed interval is formed based on the first self-vehicle maximum speed, the first self-vehicle minimum speed, and the second vehicle speed, and a candidate speed of each candidate speed point corresponding to the first sampling time point is determined within the first speed interval based on the first vehicle speed, the candidate acceleration of each candidate speed point corresponding to the first sampling time point, and the interval duration.

[0033] In a possible implementation manner, for each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point and the motion state information of the other vehicle, determining the corresponding candidate speed point for each other sampling time point, and determining the candidate speed and candidate acceleration corresponding to each of the candidate speed points include:

[0034] Determine the second self-vehicle maximum speed of each candidate speed point corresponding to each other sampling time point based on the interval time between each other sampling time point and the corresponding previous sampling time point, the preset self-vehicle maximum acceleration, and the candidate speed corresponding to the previous sampling time point; and determine the second self-vehicle minimum speed of each candidate speed point corresponding to each other sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the candidate acceleration corresponding to the previous sampling time point;

[0035] Based on the candidate acceleration corresponding to the previous sampling time point, the target vehicle jerk, the interval duration, and the number of candidate speed points corresponding to each of the other sampling time points, determine the candidate acceleration of each candidate speed point corresponding to each of the other sampling time points within the acceleration interval;

[0036] A second speed interval is formed based on the second self-vehicle maximum speed corresponding to the candidate speed point, the second self-vehicle minimum speed corresponding to the candidate speed point, and the second vehicle speed, and a candidate speed corresponding to each candidate speed point at each other sampling time point is determined within the second speed interval based on the candidate speed corresponding to the previous sampling time point, the candidate acceleration of each candidate speed point corresponding to each other sampling time point, and the interval duration.

[0037] In a possible implementation manner, generating the candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points includes:

[0038] Constructing a second relational expression of the displacement curve; wherein the second relational expression is used to describe the relationship between each displacement and time in the displacement curve;

[0039] Taking the current position of the target vehicle as the starting position of the displacement curve, and using the second relational expression, constructing a third relational expression for describing the ego-vehicle motion state of the target vehicle;

[0040] For each of the plurality of candidate speed points, using the second relational expression, construct a fourth relational expression for describing the motion state of the target vehicle at the candidate speed point;

[0041] Based on the third relational expression and the fourth relational expression, the unknown parameters in the second relational expression are solved, and based on the second relational expression in which the unknown parameters are determined, the candidate speed curve is obtained.

[0042] In a possible implementation manner, the third relationship includes: a relationship for describing the relationship between the vehicle displacement and the current time point, a relationship for describing the relationship between the vehicle speed and the current time point, and a relationship for describing the relationship between the vehicle acceleration and the current time point;

[0043] The fourth relational expression includes: a relational expression for describing the relationship between the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point, and a relational expression for describing the relationship between the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point.

[0044] In a possible implementation manner, selecting a target path curve from the multiple candidate path curves includes:

[0045] Generate first scoring data corresponding to the plurality of candidate path curves respectively; the first scoring data is used to describe the smoothness and comfort of the target vehicle when traveling along the candidate path curve;

[0046] The target path curve is determined from the plurality of candidate path curves based on the first scoring data.

[0047] In a possible implementation manner, selecting a target speed curve from the plurality of candidate speed curves includes:

[0048] Generating second scoring data corresponding to the plurality of candidate speed curves respectively; the second scoring data is used to describe the safety and comfort of the target vehicle when traveling according to the candidate speed curve;

[0049] The target speed profile is determined from the plurality of candidate speed profiles based on the second scoring data.

[0050] In a possible implementation manner, merging the target path curve with the target speed curve to generate a target driving trajectory includes:

[0051] Determine the driving displacements corresponding to the plurality of sampling time points in the target speed curve when the target vehicle drives to each of the plurality of sampling time points;

[0052] Determine the vehicle coordinate position of the target vehicle at the multiple sampling time points based on the current position of the target vehicle and the driving displacements corresponding to the multiple sampling time points in the target speed curve;

[0053] Based on the second coordinate position of each target path point in the target path curve and the vehicle coordinate position corresponding to each sampling time point in the target speed curve, the target path curve and the target speed curve are merged to generate a target driving trajectory.

[0054] In a second aspect, the present disclosure provides a trajectory generation device, comprising:

[0055] A first determination module is used to obtain vehicle state information of a target vehicle and determine a plurality of candidate path curves for the target vehicle based on the vehicle state information;

[0056] a second determination module, configured to obtain motion state information of the target vehicle, and determine a plurality of candidate speed curves for the target vehicle based on the motion state information;

[0057] A selection module, configured to select a target path curve from the plurality of candidate path curves, and to select a target speed curve from the plurality of candidate speed curves;

[0058] A generation module is used to merge the target path curve with the target speed curve to generate a target driving trajectory of the target vehicle.

[0059] In a third aspect, the present disclosure provides a computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the trajectory generation method described in the first aspect or any one of the embodiments are performed.

[0060] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the trajectory generation method as described in the first aspect or any one of the embodiments are executed.

[0061] For a description of the effects of the above-mentioned trajectory generating apparatus, computer device, and computer-readable storage medium, please refer to the description of the above-mentioned trajectory generating method, which will not be repeated here.

[0062] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.

[0063] The disclosed embodiments provide a trajectory generation method, device, computer equipment and storage medium. The method obtains the self-vehicle state information of the target vehicle, and determines a plurality of candidate path curves for the target vehicle based on the self-vehicle state information; and obtains the motion state information of the target vehicle, and determines a plurality of candidate speed curves for the target vehicle based on the motion state information. A target path curve is selected from the plurality of candidate path curves, and a target speed curve is selected from the plurality of candidate speed curves; the target path curve is merged with the target speed curve to generate a target driving trajectory for the target vehicle. The method takes into account the physical constraints and comfort constraints of the vehicle, so the candidate path curve is determined based on the self-vehicle state information, and the candidate speed curve is determined based on the motion state information, so that the selected target path curve and target speed curve are more consistent with the kinematic characteristics of the vehicle. At the same time, the stability and comfort of the target driving trajectory generated according to the target path curve and the target speed curve are better, thereby improving the quality of trajectory generation.

[0064] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0066] Figure 1 A schematic diagram of a process flow of a trajectory generation method provided by an embodiment of the present disclosure is shown;

[0067] Figure 2 A schematic diagram of multiple candidate path curves in a trajectory generation method provided by an embodiment of the present disclosure is shown;

[0068] Figure 3 A schematic diagram of multiple candidate speed curves in a trajectory generation method provided by an embodiment of the present disclosure is shown;

[0069] Figure 4 A schematic diagram of the architecture of a trajectory generating device provided by an embodiment of the present disclosure is shown;

[0070] Figure 5 A schematic diagram of the structure of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0072] With the application of various advanced computer technologies in the automotive field, cars are becoming more and more intelligent. For example, autonomous driving technology can predict the vehicle's driving trajectory through perceived road conditions and assist the driver in better controlling the car.

[0073] In the related technologies, there are many algorithms for autonomous driving trajectory planning, such as the Rapidly-exploring random trees (RRT) algorithm based on sampling, the Probabilistic Roadmap (PRM) algorithm based on sampling and graph search, the Dijkstra algorithm based on graph search, the optimization algorithm based on reference line planning, etc. However, these algorithms take a long time to predict the driving trajectory in some scenes with more complex road conditions, such as scenes with many obstacles around the vehicle, and the predicted driving trajectory does not conform to the kinematic characteristics of the vehicle.

[0074] In order to alleviate the above problems, the embodiments of the present disclosure provide a trajectory generation method, apparatus, computer equipment and storage medium, which implement segmented control of the speed sampling interval based on the physical constraints and comfort constraints of the vehicle, thereby reducing the range of the speed sampling interval and reducing the amount of calculation. At the same time, it improves the smoothness and comfort of the target driving trajectory, so that the autonomous driving car has a better physical sense.

[0075] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0076] To facilitate understanding of the embodiments of the present disclosure, a trajectory generation method disclosed in the embodiments of the present disclosure is first introduced in detail. The execution subject of the trajectory generation method provided in the embodiments of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example, a vehicle-mounted device, etc. In some possible implementations, the trajectory generation method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0077] See also Figure 1 FIG. 1 is a flow chart of a trajectory generation method provided by an embodiment of the present disclosure, the method comprising steps S101 to S104, wherein:

[0078] S101: Acquire vehicle state information of a target vehicle, and determine a plurality of candidate path curves for the target vehicle based on the vehicle state information.

[0079] S102: Acquire motion state information of the target vehicle, and determine a plurality of candidate speed curves for the target vehicle based on the motion state information.

[0080] S103: Selecting a target path curve from a plurality of candidate path curves, and selecting a target speed curve from a plurality of candidate speed curves.

[0081] S104: Merge the target path curve and the target speed curve to generate a target driving trajectory of the target vehicle.

[0082] The following is a relatively detailed description of S101 to S104.

[0083] For S101:

[0084] Here, the self-vehicle state information can be obtained through sensors on the target vehicle; wherein the self-vehicle state information may include the current position of the target vehicle, the heading angle of the target vehicle, the curvature of the target vehicle, etc.; for example, the current position of the target vehicle can be obtained through the positioning sensor on the target vehicle, the heading angle of the target vehicle can be calculated based on the current position and driving direction of the target vehicle, and the curvature of the target vehicle can be calculated based on the driving speed and angular velocity of the target vehicle. In actual operation, multiple candidate path curves that the target vehicle can travel can be determined based on the self-vehicle state information of the target vehicle.

[0085] In a possible implementation, when determining a plurality of candidate path curves for a target vehicle based on the vehicle state information, the following steps may be included:

[0086] Step A1, based on the driving strategy of the target vehicle, determining a candidate driving area of ​​the target vehicle in the current driving section;

[0087] Step A2, selecting a plurality of candidate path points from the candidate driving area, and determining path point information corresponding to the plurality of candidate path points respectively;

[0088] Step A3, generating a plurality of candidate path curves based on the vehicle state information and the path point information corresponding to the plurality of candidate path points.

[0089] During implementation, the driving strategy of the target vehicle can be obtained first, where the driving strategy can be generated by the driving decision planning module on the target vehicle according to the scene in which the target vehicle is located. For example, the driving strategy can be to instruct the vehicle to drive in the current lane, or to instruct the vehicle to change to the left lane, or to instruct the vehicle to change to the right lane, and so on.

[0090] Then, according to the driving strategy, the candidate driving area of ​​the target vehicle can be determined in the current driving section. For example, if the driving strategy instructs the vehicle to drive in the current lane, the candidate driving area can be determined in front of the target vehicle and in the current lane. The size of the candidate driving area can be set according to the actual situation, or can be pre-set, such as 3 meters × 30 meters.

[0091] Multiple candidate path points can be selected from the candidate driving area, wherein the lateral spacing and longitudinal spacing between adjacent candidate path points can be determined according to the area size of the candidate driving area; for example, when the area size of the candidate driving area is 10 meters × 30 meters, the lateral spacing between adjacent candidate path points can be 1 meter, and the longitudinal spacing can be 10 meters. Figure 2 The schematic diagram of the candidate path points shown in FIG. The path point information corresponding to the multiple candidate path points can be determined. Here, the path point information may include the coordinate position of the candidate path point in the vehicle coordinate system, the heading angle of the candidate path point, and the curvature of the candidate path point. The heading angle and curvature of the candidate path point can be estimated based on the current position of the target vehicle and the coordinate position of the candidate path point.

[0092] Furthermore, multiple candidate path curves can be generated based on the vehicle state information and the path point information corresponding to the multiple candidate path points. Specifically, the current position of the target vehicle can be used as the starting position, each candidate path point can be used as the middle and end position, and the starting position and the end position can be constructed into a curve to obtain multiple candidate path curves. Figure 2 Schematic diagram of multiple candidate path curves shown in .

[0093] Here, based on the driving strategy of the target vehicle, the candidate driving area of ​​the target vehicle is determined in the current driving section, which can effectively control the area size of the candidate driving area, that is, the selection of candidate path points can be effectively reduced. Furthermore, based on the vehicle state information and the path point information corresponding to multiple candidate path points, multiple candidate path curves can be generated more quickly and efficiently.

[0094] In specific implementation, in step A3, based on the vehicle state information and the path point information corresponding to the plurality of candidate path points, generating the candidate path curve may include:

[0095] Step A31, constructing a first relational expression of the candidate path curve; wherein the first relational expression is used to describe the relationship between the lateral coordinate value and the longitudinal coordinate value of each position point in the candidate path curve in the vehicle coordinate system;

[0096] Step A32, taking the current position of the target vehicle as the starting position of the candidate path curve, and using the first relational expression to construct a first relational expression for describing the state of the ego vehicle at the starting position; and, for each candidate path point among the plurality of candidate path points, taking each candidate path point as the end position of each candidate path curve, and using the first relational expression to construct a second relational expression for describing the state of the ego vehicle when the target vehicle is at the end position;

[0097] Step A33: Based on the first relational expression and the second relational expression, the unknown parameters in the first relational expression are solved to obtain a candidate path curve.

[0098] During implementation, a first relational expression of the candidate path curve can be constructed, wherein the first relational expression can be used to describe the relationship between the lateral coordinate value and the longitudinal coordinate value of each position point in the candidate path curve in the vehicle coordinate system; during actual operation, the first relational expression can be expressed as y=c0+c1*x+c2*x 2 +c3*x 3 +c4*x 4 +c5*x 5 , where c0~c5 represent unknown parameters in the first relational expression, x represents the horizontal coordinate of the position point in the candidate path curve, and y represents the vertical coordinate of the position point in the candidate path curve.

[0099] Furthermore, the current position of the target vehicle can be used as the starting position of the candidate path curve, and the first relational expression can be used to construct a first relational formula, where the first relational formula can be used to describe the state of the vehicle at the starting position.

[0100] Specifically, the vehicle status information may include the first coordinate position, the first heading angle, and the first curvature of the target vehicle. The first coordinate position may include the first horizontal coordinate and the first vertical coordinate of the target vehicle in the vehicle coordinate system. The first relationship may include: a relationship for describing the relationship between the first vertical coordinate and the first horizontal coordinate, a relationship for describing the relationship between the first heading angle and the first horizontal coordinate, and a relationship for describing the relationship between the first curvature, the first heading angle and the first horizontal coordinate.

[0101] In actual operation, the first horizontal coordinate and the first vertical coordinate of the target vehicle can be substituted into the first relational expression to obtain a relational expression for describing the relationship between the first vertical coordinate and the first horizontal coordinate, as shown in the following relational expression (1-1); and, the first relational expression can be used to construct a relational expression for describing the relationship between the first heading angle and the first horizontal coordinate based on the first heading angle and the first horizontal coordinate, as shown in the following relational expression (1-2); and, the first relational expression can be used to construct a relational expression for describing the relationship between the first curvature, the first heading angle and the first horizontal coordinate based on the first heading angle, the first curvature and the first horizontal coordinate, as shown in the following relational expression (1-3).

[0102] y0=c0+c1*x0+c2*x0 2 +c3*x0 3 +c4*x0 4 +c5*x0 5 (1-1)

[0103] tan(heading0)=c1+2c2*x0+3c3*x0 2 +4c4*x0 3 +5c5*x0 4 (1-2)

[0104]

[0105] Among them, c0~c5 represent unknown parameters; x0 represents the first horizontal coordinate; y0 represents the first vertical coordinate; heading0 represents the first heading angle, which can be calculated based on the first coordinate position and the driving direction of the target vehicle; curvature0 represents the first curvature, which can be calculated based on the driving speed and angular velocity of the target vehicle.

[0106] For each candidate path point among multiple candidate path points, each candidate path point can be used as the end point position of each candidate path curve, and the first relational expression can be used to construct a second relational expression, where the second relational expression can be used to describe the state of the target vehicle when the target vehicle is at the end point position.

[0107] Specifically, the waypoint information may include the second coordinate position, the second heading angle, and the second curvature of the candidate waypoint; the second coordinate position may include: the second horizontal coordinate and the second vertical coordinate of the candidate waypoint in the vehicle coordinate system; the second relationship may include: a relationship for describing the relationship between the second vertical coordinate and the second horizontal coordinate, a relationship for describing the relationship between the second heading angle and the second horizontal coordinate, and a relationship for describing the relationship between the second curvature, the second heading angle and the second horizontal coordinate.

[0108] In actual operation, the second horizontal coordinate and the second vertical coordinate of the candidate path point can be substituted into the first relational expression to obtain a relational expression for describing the relationship between the second vertical coordinate and the second horizontal coordinate, as shown in the following relational expression (1-4); and, the first relational expression can be used to construct a relational expression for describing the relationship between the second heading angle and the second horizontal coordinate based on the second heading angle and the second horizontal coordinate, as shown in the following relational expression (1-5); and, the first relational expression can be used to construct a relational expression for describing the relationship between the second curvature, the second heading angle and the second horizontal coordinate based on the second heading angle, the second curvature and the second horizontal coordinate, as shown in the following relational expression (1-6).

[0109] y1=c0+c1*x1+c2*x1 2 +c3*x1 3 +c4*x1 4 +c5*x1 5 (1-4)

[0110] tan(heading1)=c1+2c2*x1+3c3*x1 2 +4c4*x1 3 +5c5*x1 4 (1-5)

[0111]

[0112] Among them, c0~c5 represent unknown parameters; x1 represents the first horizontal coordinate; y1 represents the first vertical coordinate; heading1 represents the second heading angle, which can be estimated based on the first coordinate position and the second coordinate position; curvature1 represents the second curvature, which can be estimated based on the first coordinate position and the second coordinate position.

[0113] Finally, multiple relational expressions containing unknown parameters can be obtained, and the unknown parameters in the first relational expression can be solved based on the first relational expression and the second relational expression to obtain a candidate path curve; in actual operation, the values ​​of c0 to c5 can be solved based on relational expressions (1-1), (1-2), (1-3), (1-4), (1-5), and (1-6); furthermore, the values ​​of c0 to c5 can be substituted into the first relational expression to obtain a candidate path curve: y = c0 + c1*x + c2*x 2 +c3*x 3 +c4*x 4 +c5*x 5 , where c0~c5 represent the known coefficients in the candidate path curve, x represents the horizontal coordinate of the position point, and y represents the vertical coordinate of the position point.

[0114] For S102:

[0115] Here, the motion state information may include the motion state information of the vehicle and the motion state information of other vehicles. The motion state information of the vehicle may include the vehicle speed and vehicle acceleration of the target vehicle, which may be obtained through sensors on the target vehicle; the motion state information of other vehicles may include the vehicle speed and vehicle acceleration of other vehicles. Here, the vehicle speed and vehicle acceleration of other vehicles may be determined by obtaining the vehicle speed and vehicle acceleration of other vehicles near the target vehicle, or, when no other vehicles are detected near the target vehicle, may be determined based on the road sign information of the current driving section of the target vehicle. Furthermore, multiple candidate speed curves may be determined for the target vehicle based on the motion state information.

[0116] In a possible implementation manner, the motion state information may include: the motion state information of the vehicle itself and the motion state information of other vehicles; when determining multiple candidate speed curves for the target vehicle based on the motion state information, the following may be included:

[0117] Step B1, based on the motion state information of the vehicle and the motion state information of the other vehicle, respectively determine candidate speed points for multiple sampling time points, and determine the candidate speed and candidate acceleration corresponding to each candidate speed point; wherein two adjacent sampling time points are separated by a preset time length, and each sampling time point corresponds to at least one candidate speed point;

[0118] Step B2, generating a candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at each sampling time point.

[0119] Considering the safety and comfort of vehicle driving, candidate speed points can be determined for multiple sampling time points based on the motion state information and the motion state information of other vehicles, and the candidate speed and candidate acceleration corresponding to each candidate speed point can be determined, that is, the candidate speed and candidate acceleration of the target vehicle at each sampling time point can be determined. Among them, there is a preset time interval between two adjacent sampling time points, and the preset time interval can be determined according to actual conditions, such as 1 second; each sampling time point corresponds to at least one candidate speed point, for example, the vehicle speed of the target vehicle at sampling time point 1 can be 80 kilometers per hour, or can be 82 kilometers per hour, at this time, sampling time point 1 corresponds to two candidate speed points.

[0120] Furthermore, a candidate speed curve can be generated based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at each sampling time point. Specifically, the candidate speed curve can be constructed based on the current speed point of the target vehicle and any candidate speed point corresponding to each sampling time point in the order of each sampling time point. Figure 3 Schematic diagram of multiple candidate speed profiles shown in .

[0121] In specific implementation, in step B1, based on the motion state information of the vehicle and the motion state information of other vehicles, candidate speed points are determined for multiple sampling time points respectively, and the candidate speed and candidate acceleration corresponding to each candidate speed point are determined, which may include:

[0122] Step B11, for the first sampling time point, based on the motion state information of the vehicle and the motion state information of other vehicles, determine the corresponding candidate speed point for the first sampling time point, and determine the candidate speed and candidate acceleration corresponding to each candidate speed point;

[0123] Step B12, for each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point, and the motion state information of other vehicles, determine the corresponding candidate speed point for each other sampling time point, and determine the candidate speed and candidate acceleration corresponding to each candidate speed point.

[0124] During implementation, the candidate speed point corresponding to the first sampling time point can be determined first, as well as the candidate speed and candidate acceleration corresponding to each candidate speed point; in actual operation, based on the motion state information of the vehicle itself and the motion state information of other vehicles, the candidate speed and candidate acceleration are determined for the first sampling time point, wherein each candidate speed corresponds to a candidate speed point, and each candidate speed corresponds to a candidate acceleration.

[0125] For each sampling time point other than the first sampling time point, the corresponding candidate speed and candidate acceleration can be determined for each other sampling time point based on the candidate speed and candidate acceleration corresponding to each candidate speed point at the previous sampling time point corresponding to each other sampling time point, and the motion state information of other vehicles. That is, the candidate speed and candidate acceleration corresponding to the candidate speed point at the next sampling time point can be determined based on the candidate speed and candidate acceleration corresponding to the candidate speed point at the previous sampling time point, and the motion state information of other vehicles.

[0126] Exemplarily, if the sampling time points include t1, t2, and t3, in actual operation, the candidate speed and candidate acceleration of the candidate speed point corresponding to the sampling time point t1 can be determined based on the motion state information of the own vehicle and the motion state information of the other vehicle; then, the candidate speed and candidate acceleration of the candidate speed point corresponding to the sampling time point t2 can be determined based on the candidate speed and candidate acceleration of the candidate speed point corresponding to the sampling time point t1, and the motion state information of the other vehicle; then, the candidate speed and candidate acceleration of the candidate speed point corresponding to the sampling time point t3 can be determined based on the candidate speed and candidate acceleration of the candidate speed point corresponding to the sampling time point t2, and the motion state information of the other vehicle.

[0127] Here, based on the candidate speed and candidate acceleration corresponding to the candidate speed point at the previous sampling time point and the motion state information of other vehicles, the candidate speed and candidate acceleration corresponding to the candidate speed point at the next sampling time point are determined, so that the candidate speed curve subsequently constructed based on the candidate speed and candidate acceleration corresponding to the candidate speed point at each sampling time point has better smoothness; and considering the motion state information of other vehicles, the safety of the constructed candidate speed curve is higher.

[0128] In actual operation, considering the kinematic characteristics of the vehicle, the maximum acceleration of the vehicle and the minimum acceleration of the vehicle can be preset. Here, the maximum acceleration of the vehicle and the minimum acceleration of the vehicle can be determined according to the motion state information of the vehicle and the motion state information of the other vehicle. For example, the maximum acceleration of the vehicle can be 2m / s 2 , Minimum acceleration of the vehicle - 4m / s 2 ; and the acceleration of the target vehicle can be determined according to the vehicle condition of the target vehicle, such as 3m / s 3 The candidate speed point at each sampling time point can be determined based on the maximum acceleration of the vehicle, the minimum acceleration of the vehicle, and the jerk of the target vehicle.

[0129] In a possible implementation, the self-vehicle motion state information may include a first vehicle speed and a first vehicle acceleration of the target vehicle; the other vehicle motion state information may include a second vehicle speed and a second vehicle acceleration of the other vehicle.

[0130] In step B11, for the first sampling time point, based on the motion state information of the vehicle and the motion state information of the other vehicle, determining the corresponding candidate speed point for the first sampling time point, and determining the candidate speed and candidate acceleration corresponding to each candidate speed point may include:

[0131] Determine the first self-vehicle maximum speed of each candidate speed point corresponding to the first sampling time point based on the interval time between the first sampling time point and the current time, the preset self-vehicle maximum acceleration, and the first vehicle speed; and determine the first self-vehicle minimum speed corresponding to each candidate speed point corresponding to the first sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the first vehicle speed;

[0132] An acceleration interval is formed based on the maximum acceleration of the own vehicle, the minimum acceleration of the own vehicle, and the acceleration of the second vehicle, and a candidate acceleration corresponding to each candidate speed point at the first sampling time point is determined within the acceleration interval based on the acceleration of the first vehicle, the jerk of the target vehicle, the interval time, and the number of candidate speed points corresponding to the first sampling time point;

[0133] A first speed interval is formed based on the maximum speed of the first ego vehicle, the minimum speed of the first ego vehicle, and the speed of the second vehicle, and a candidate speed corresponding to each candidate speed point at a first sampling time point is determined within the first speed interval based on the first vehicle speed, the candidate acceleration of each candidate speed point at a first sampling time point, and the interval duration.

[0134] During implementation, formula (2-1) can be used to determine the number of candidate speed points corresponding to the first sampling time point according to the preset maximum acceleration of the vehicle, the preset minimum acceleration of the vehicle, and the jerk of the target vehicle.

[0135] Then, the interval length between the first sampling time point and the current moment can be determined, and then the following formula (2-2) can be used to calculate the first self-vehicle maximum speed of each candidate speed point corresponding to the first sampling time point according to the first vehicle speed, the interval length and the preset self-vehicle maximum acceleration; and the following formula (2-3) can be used to calculate the first self-vehicle minimum speed corresponding to each candidate speed point corresponding to the first sampling time point according to the first vehicle speed, the interval length and the preset self-vehicle minimum acceleration.

[0136] i=(max_accel-min_accel) / comfort_lon_jerk (2-1)

[0137]

[0138]

[0139] Where i represents the number of candidate speed points corresponding to the first sampling time point, max_accel represents the preset maximum acceleration of the vehicle, min_accel represents the preset minimum acceleration of the vehicle, comfort_lon_jerk represents the jerk of the target vehicle; v0 represents the first vehicle speed, which can be obtained by the speed sensor on the target vehicle; delta_t represents the interval between the first sampling time point and the current moment; Indicates the maximum speed of the first ego vehicle at each candidate speed point corresponding to the first sampling time point; Indicates the minimum speed of the first ego vehicle at each candidate speed point corresponding to the first sampling time point.

[0140] During implementation, it is considered that the candidate speeds of the candidate speed points determined by random sampling have a large deviation from the actual driving speed of the target vehicle, and the speed sampling interval in the random sampling method has a large interval range, resulting in a large amount of calculation; therefore, in the present disclosure, the speed sampling interval of the candidate speed points corresponding to the first sampling time point can be determined according to the maximum speed of the first ego vehicle and the minimum speed of the first ego vehicle, so as to reduce the amount of calculation.

[0141] In specific implementation, the candidate acceleration of each candidate speed point can be determined first, and then the candidate speed of each candidate speed point can be determined according to the candidate acceleration of each candidate speed point. In actual operation, the acceleration interval can be formed based on the maximum acceleration of the vehicle, the minimum acceleration of the vehicle, and the acceleration of the second vehicle. For example, the acceleration interval can be expressed as [min_accel, min(max_accel, final_a)], where min_accel represents the minimum acceleration of the vehicle, final_a represents the second vehicle acceleration of the other vehicle, and min() represents the minimum value of the parameters, that is, the minimum value of the maximum acceleration of the vehicle max_accel and the second vehicle acceleration final_a is selected as the maximum acceleration of the acceleration interval.

[0142] Then, based on the first vehicle acceleration, the target vehicle acceleration, the interval duration, and the number of candidate speed points corresponding to the first sampling time point, the candidate acceleration of each candidate speed point corresponding to the first sampling time point can be determined within the acceleration interval; specifically, the initial candidate acceleration of each candidate speed point corresponding to the first sampling time point can be determined using formula (2-4), and then the initial candidate acceleration within the acceleration interval can be determined as the candidate acceleration of each candidate speed point corresponding to the first sampling time point.

[0143]

[0144] in, It represents the candidate acceleration of the j-th candidate speed point corresponding to the first sampling time point t1; a0 represents the first vehicle acceleration, which can be obtained by the acceleration sensor on the target vehicle; j represents the j-th candidate speed point corresponding to the first sampling time point, and j represents any value from 1 to i; comfort_lon_jerk represents the acceleration of the target vehicle; delta_t represents the interval between the first sampling time point and the current moment.

[0145] Finally, a first speed interval can be formed based on the first vehicle maximum speed, the first vehicle minimum speed, and the second vehicle speed; illustratively, the first speed interval can be expressed as in, represents the minimum speed of the first self-vehicle, which can be calculated according to the above formula (2-3); final_v represents the second vehicle speed of the other vehicle, Indicates the selection of the maximum speed of the first vehicle and the minimum value of the second vehicle speed final_v as the maximum speed of the first speed interval, It can be calculated according to the above formula (2-2).

[0146] And based on the first vehicle speed, the candidate acceleration of each candidate speed point corresponding to the first sampling time point, and the interval duration, the candidate speed of each candidate speed point corresponding to the first sampling time point can be determined in the first speed interval. Specifically, the initial candidate speed of each candidate speed point corresponding to the first sampling time point can be determined by using formula (2-5), and then the initial candidate speed in the first speed interval can be determined as the candidate speed of each candidate speed point corresponding to the first sampling time point.

[0147]

[0148] in, represents the candidate speed of the j-th candidate speed point corresponding to the first sampling time point t1; v0 represents the first vehicle speed; j represents the j-th candidate speed point corresponding to the first sampling time point, and j represents any value from 1 to i; The candidate acceleration of the jth candidate velocity point corresponding to the first sampling time point t1 can be calculated using formula (2-4); delta_t represents the interval between the first sampling time point and the current moment.

[0149] In a possible implementation manner, in step B12, for each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point, and the motion state information of the other vehicle, a corresponding candidate speed point is determined for each other sampling time point. When determining the candidate speed and candidate acceleration corresponding to each candidate speed point, the following steps may be included:

[0150] Determine the second self-vehicle maximum speed of each candidate speed point corresponding to each other sampling time point based on the interval time between each other sampling time point and the corresponding previous sampling time point, the preset self-vehicle maximum acceleration, and the candidate speed corresponding to the previous sampling time point; and determine the second self-vehicle minimum speed of each candidate speed point corresponding to each other sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the candidate acceleration corresponding to the previous sampling time point;

[0151] Based on the candidate acceleration corresponding to the previous sampling time point, the target vehicle jerk, the interval duration, and the number of candidate speed points corresponding to each other sampling time point, determine the candidate acceleration corresponding to each candidate speed point at each other sampling time point within the acceleration interval;

[0152] A second speed interval is formed based on the second vehicle maximum speed corresponding to the candidate speed point, the second vehicle minimum speed corresponding to the candidate speed point, and the second vehicle speed, and based on the candidate speed corresponding to the previous sampling time point, the candidate acceleration of each candidate speed point corresponding to each other sampling time point, and the interval duration, within the second speed interval, the candidate speed of each candidate speed point corresponding to each other sampling time point is determined.

[0153] During implementation, formula (2-1) can be used to determine the number of candidate speed points corresponding to each sampling time point except the first sampling time point based on the preset maximum acceleration of the vehicle, the preset minimum acceleration of the vehicle, and the acceleration of the target vehicle.

[0154] Then, the interval length between each other sampling time point and the corresponding previous sampling time point can be determined. For example, for sampling time point t2, the interval length between sampling time point t2 and sampling time point t1 can be calculated; then the following formula (2-6) can be used to calculate the second self-vehicle maximum speed of each candidate speed point corresponding to each other sampling time point based on the candidate speed corresponding to the previous sampling time point, the interval length, and the preset self-vehicle maximum acceleration; and the following formula (2-7) can be used to calculate the second self-vehicle minimum speed of each candidate speed point corresponding to each other sampling time point based on the candidate speed corresponding to the previous sampling time point, the interval length, and the preset self-vehicle minimum acceleration.

[0155]

[0156]

[0157] in, represents the sampling time point t k-1 The corresponding candidate speed of the jth candidate speed point; delta_t represents the sampling time point t k With sampling time t k-1 The interval length; represents the sampling time point t k The maximum speed of the second ego vehicle at each corresponding candidate speed point; represents the sampling time point t k The minimum speed of the second vehicle at each corresponding candidate speed point; k is a positive integer greater than or equal to 2.

[0158] Then, based on the candidate acceleration corresponding to the previous sampling time point, the target vehicle acceleration, the interval duration, and the number of candidate speed points corresponding to each other sampling time point, the candidate acceleration corresponding to each candidate speed point at each other sampling time point can be determined within the acceleration interval; specifically, the initial candidate acceleration corresponding to each candidate speed point at each other sampling time point can be determined using formula (2-8), and then the initial candidate acceleration within the acceleration interval can be determined as the candidate acceleration corresponding to each candidate speed point at each other sampling time point. Wherein, the acceleration interval is [min_accel, min(max_accel, final_a)].

[0159]

[0160] in, Indicates other sampling time points t k The corresponding candidate acceleration of the jth candidate velocity point; Indicates other sampling time points t k-1 The candidate acceleration corresponding to the j-th candidate speed point; j represents the j-th candidate speed point corresponding to the first sampling time point, and j represents any value from 1 to i; comfort_lon_jerk represents the jerk of the target vehicle; delta_t represents other sampling time points t k With other sampling time points t k-1 The interval duration.

[0161] Finally, a second speed interval can be formed based on the second vehicle maximum speed corresponding to the candidate speed point, the second vehicle minimum speed corresponding to the candidate speed point, and the second vehicle speed; illustratively, the second speed interval can be expressed as in, Indicates other sampling time points t k The corresponding second minimum speed of the self-vehicle can be calculated according to the above formula (2-7); final_v represents the second vehicle speed of the other vehicle, Indicates the selection of other sampling time points t k The corresponding maximum speed of the second vehicle and the minimum value of the second vehicle speed final_v as the maximum speed of the second speed interval, It can be calculated according to the above formula (2-6).

[0162] The candidate speed corresponding to the previous sampling time point, the candidate acceleration corresponding to each candidate speed point at each other sampling time point, and the interval duration can be used to determine the candidate speed of each candidate speed point corresponding to each other sampling time point in the second speed interval. Specifically, the initial candidate speed of each candidate speed point corresponding to each other sampling time point can be determined by using formula (2-9), and then the initial candidate speed in the second speed interval can be determined as the candidate speed of each candidate speed point corresponding to each other sampling time point.

[0163]

[0164] in, Indicates other sampling time points t k The corresponding candidate speed of the jth candidate speed point; Indicates other sampling time points t k-1 The candidate speed of the corresponding j-th candidate speed point; j represents the j-th candidate speed point corresponding to the first sampling time point, and j represents any value from 1 to i; Indicates other sampling time points t k The candidate acceleration corresponding to the jth candidate velocity point can be calculated using formula (2-8); delta_t represents the other sampling time point t k With other sampling time points t k-1 The interval duration.

[0165] Here, by constructing a speed interval to control the sampling range of the speed sampling points, the amount of calculation can be effectively reduced. At the same time, based on the target vehicle jerk, the candidate acceleration and candidate speed of each candidate speed are determined, so that the comfort of the candidate speed curve obtained subsequently can be better.

[0166] In a possible implementation manner, in step B2, based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at each sampling time point, generating the candidate speed curve may include:

[0167] Step B21, constructing a second relational expression of the displacement curve; wherein the second relational expression is used to describe the relationship between each displacement and time in the displacement curve;

[0168] Step B22, taking the current position of the target vehicle as the starting position of the displacement curve, and using the second relational expression to construct a third relational expression for describing the ego-vehicle motion state of the target vehicle;

[0169] Step B23, for each of the plurality of candidate speed points, using the second relational expression, constructing a fourth relational expression for describing the motion state of the target vehicle at the candidate speed point;

[0170] Step B24, based on the third relational expression and the fourth relational expression, the unknown parameters in the second relational expression are solved, and based on the second relational expression in which the unknown parameters are determined, a candidate speed curve is obtained.

[0171] During implementation, a second relational expression of the displacement curve can be constructed, wherein the second relational expression can be used to describe the relationship between each displacement and time in the displacement curve; during actual operation, the second relational expression can be expressed as s=b0+b1*t+b2*t 2 +b3*t 3 +b4*t 4 , where b0~b4 represent unknown parameters in the second relational expression, s represents the displacement distance in the displacement curve, and t represents the time distance between the sampling time point and the current time point.

[0172] Furthermore, the current position of the target vehicle can be used as the starting position of the displacement curve, and the third relational expression can be constructed using the second relational expression, where the first relational expression can be used to describe the self-vehicle motion state of the target vehicle. Specifically, the third relational expression can include: a relational expression for describing the relationship between the vehicle displacement and the current time point, a relational expression for describing the relationship between the vehicle speed and the current time point, and a relational expression for describing the relationship between the vehicle acceleration and the current time point.

[0173] In actual operation, the vehicle displacement and the current time point of the target vehicle can be substituted into the second relational expression to obtain a relational expression for describing the relationship between the vehicle displacement and the current time point, as shown in the following relational expression (3-1); and, based on the first-order derivative of the second relational expression, the first vehicle speed and the current time point of the target vehicle can be substituted to obtain a relational expression for describing the relationship between the vehicle speed and the current time point, as shown in the following relational expression (3-2); and, based on the second-order derivative of the second relational expression, the first vehicle acceleration and the current time point of the target vehicle can be substituted to obtain a relational expression for describing the relationship between the vehicle acceleration and the current time point, as shown in the following relational expression (3-3).

[0174] s0=b0+b1*t0+b2*t0 2 +b3*t0 3 +b4*t0 4 (3-1)

[0175] v0=b1+2b2*t0+3b3*t0 2 +4b4*t0 3 (3-2)

[0176] a0=2b2+6b3*t0+12b4*t0 2 (3-3)

[0177] Among them, b0~b4 represent unknown parameters; t0 represents the current time point, that is, 0; s0 represents the vehicle displacement of the target vehicle at the current time point, that is, 0; v0 represents the first vehicle speed; a0 represents the first vehicle acceleration.

[0178] For each of the multiple candidate speed points, the second relational expression can be used to construct a fourth relational expression, where the fourth relational expression can be used to describe the motion state of the target vehicle at the candidate speed point; specifically, the fourth relational expression may include: a relational expression for describing the relationship between the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point, and a relational expression for describing the relationship between the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point.

[0179] The relational expression used to describe the relationship between the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point can be obtained based on the first-order derivative of the second relational expression, by substituting the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point, as shown in the following relational expression (3-4); and the relational expression used to describe the relationship between the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point can be obtained based on the second-order derivative of the second relational expression, by substituting the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point, as shown in the following relational expression (3-5).

[0180]

[0181]

[0182] Among them, b1~b4 represent unknown parameters; t k represents the sampling time point t k The time interval from the current time point; represents the sampling time point t k The corresponding candidate speed of the jth candidate speed point; represents the sampling time point t k The candidate acceleration corresponding to the j-th candidate velocity point; k is a positive integer greater than or equal to 1.

[0183] Finally, multiple relational expressions containing unknown parameters can be obtained, and the unknown parameters in the second relational expression can be solved based on the third and fourth relational expressions to obtain the values ​​of the unknown parameters, and the candidate velocity curve can be obtained based on the second relational expression in which the unknown parameters are determined. In actual operation, the values ​​of b0~b4 can be solved based on relational expressions (3-1), (3-2), (3-3), (3-4), and (3-5). Furthermore, the values ​​of b0~b4 can be substituted into the second relational expression to obtain the displacement curve: s=b0+b1*t+b2*t 2 +b3*t 3 +b4*t 4 , and then the first-order derivative of the displacement curve can be taken to obtain the candidate velocity curve: v = b1 + 2b2*t + 3b3*t 2 +4b4*t 3 ; Among them, b1~b4 represent the known coefficients in the candidate speed curve, t represents the interval between the sampling time point t and the current time point, and v represents the speed corresponding to the sampling time point.

[0184] During implementation, step S101 and step S102 in the present disclosure are executed in no particular order, and step S101 may be executed first, and then step S102; or, step S102 may be executed first, and then step S101; or, step S101 and step S102 may be executed simultaneously; this is not limited here.

[0185] For S103 and S104:

[0186] The candidate path curve can be used to describe the target vehicle's driving trajectory in the lateral direction, and the candidate speed curve can be used to describe the target vehicle's driving speed in the longitudinal direction. Therefore, the path curve and the speed curve can be combined to obtain the target vehicle's driving trajectory, which can be used to indicate the target vehicle's driving direction and driving speed. In specific implementation, a target path curve can be selected from multiple candidate path curves, and a target speed curve can be selected from multiple candidate speed curves. Then, the target path curve and the target speed curve can be combined to generate a target driving trajectory.

[0187] In actual operation, the one with the highest smoothness and safety among multiple candidate path curves can be selected as the target path curve, and the one with the highest comfort and safety among multiple candidate speed curves can be selected as the target speed curve; furthermore, the target path curve and the target speed curve can be merged according to the coordinate position of the position point in the target path curve and the displacement corresponding to the speed point in the target speed curve to generate the target driving trajectory.

[0188] In one possible implementation, when selecting a target path curve from a plurality of candidate path curves, it may include: generating first scoring data corresponding to each of the plurality of candidate path curves; the first scoring data is used to describe the smoothness and comfort of the target vehicle when traveling along the candidate path curves; and determining the target path curve from the plurality of candidate path curves based on the first scoring data.

[0189] In a specific implementation, when generating first scoring data corresponding to multiple candidate path curves respectively, it can include: for each candidate path curve, determining the target coordinate position corresponding to each position point in the candidate path curve, and generating first intermediate data based on the second coordinate position and the target coordinate position corresponding to each position point; the first intermediate data is used to describe the smoothness of the target vehicle when traveling along the candidate path curve; and, for each candidate path curve, determining the first acceleration corresponding to each position point in the candidate path curve, and generating second intermediate data based on the first acceleration corresponding to each position point and the target vehicle acceleration; the second intermediate data is used to describe the comfort of the target vehicle when traveling along the candidate path curve; based on the first intermediate data and the second intermediate data, generate the first scoring data corresponding to the candidate path curve.

[0190] In actual operation, for each candidate path curve, the horizontal coordinate value of each position point can be brought into the candidate path curve, the first-order derivative of the candidate path curve can be calculated, and the first-order derivative result can be determined as the target lateral distance corresponding to each position point; then, based on the second coordinate position corresponding to each position point, the second lateral distance corresponding to each position point can be determined, the second coordinate position is the coordinate position in the vehicle coordinate system obtained after determining the candidate path point, and the second lateral distance can be the second horizontal coordinate in the second coordinate position. Furthermore, the following formula (4-1) can be used to generate the first intermediate data according to the second lateral distance and the target lateral distance corresponding to each position point; wherein the first intermediate data can be used to describe the smoothness of the target vehicle when driving along the candidate path curve.

[0191]

[0192] Among them, target_l i represents the target lateral distance of the i-th position point; l iIt represents the second lateral distance of the i-th position point; i represents the number of position points, which can be any positive integer between 0 and m; m represents the number of position points in the candidate path curve, which can be determined according to actual conditions; lat_target_cost represents the sum of the differences between the second lateral distances of each position point on the candidate path curve and the target lateral distance. The smaller the value of lat_target_cost is, the smaller the difference between the second lateral distances of each position point on the candidate path curve and the target lateral distance is, that is, the higher the corresponding smoothness of the candidate path curve is.

[0193] Furthermore, the horizontal coordinate value of each position point can be brought into the candidate path curve, the third-order derivative of the candidate path curve can be calculated, and the third-order derivative result can be determined as the first acceleration corresponding to each position point; then, the target lateral acceleration corresponding to each position point can be determined based on the target vehicle jerk and the second heading angle of each position point, and the second heading angle is obtained after the candidate path point is determined. Furthermore, the following formula (4-2) can be used to generate second intermediate data according to the first acceleration and target lateral acceleration corresponding to each position point; wherein the second intermediate data can be used to describe the comfort of the target vehicle when driving along the candidate path curve.

[0194]

[0195] Where comfort_lat_jerk represents the target lateral jerk; l i ″′ represents the first acceleration of the i-th position point; i represents the number of position points, which can be any positive integer between 0 and m; m represents the number of position points in the candidate path curve, which can be determined according to actual conditions; lat_comfort_cost represents the comfort of the candidate path curve in the lateral direction. The smaller the value of lat_comfort_cost, the higher the comfort corresponding to the candidate path curve.

[0196] Furthermore, the first scoring data corresponding to the candidate path curve can be generated based on the first intermediate data and the second intermediate data. Specifically, the sum of the first intermediate data and the second intermediate data can be used as the first scoring data; or the weighted sum of the first intermediate data and the second intermediate data can be used as the first scoring data. The target path curve can be determined from multiple candidate path curves based on the first scoring data. In actual operation, after obtaining the first scoring data based on the above method, the candidate path curve with the smallest first scoring data can be determined as the target path curve.

[0197] Here, the target path curve is selected based on the smoothness and comfort of the candidate path curves, so that the target vehicle can have better smoothness and comfort when driving along the target path curve.

[0198] In a possible implementation, selecting a target speed curve from a plurality of candidate speed curves includes: generating second scoring data corresponding to the plurality of candidate speed curves respectively; the second scoring data is used to describe the safety and comfort of the target vehicle when traveling along the candidate speed curves; and determining the target speed curve from the plurality of candidate speed curves based on the second scoring data.

[0199] In a specific implementation, when generating second scoring data corresponding to multiple candidate speed curves respectively, it can include: for each candidate speed curve, determining the target speeds corresponding to each sampling time point in the candidate speed curve, and generating third intermediate data based on the target speeds corresponding to each sampling time point and the candidate speeds; the third intermediate data is used to characterize the safety of the target vehicle when traveling according to the candidate speed curve; and, for each candidate speed curve, determining the second acceleration corresponding to each sampling time point in the candidate speed curve, and generating fourth intermediate data based on the second acceleration corresponding to each sampling time point and the target vehicle acceleration; the fourth intermediate data is used to characterize the comfort of the target vehicle when traveling according to the candidate speed curve; based on the third intermediate data and the fourth intermediate data, generate the second scoring data corresponding to the candidate speed curve.

[0200] In actual operation, for each candidate speed curve, each sampling time point can be substituted into the candidate speed curve to calculate the target speed corresponding to each sampling time point; or each sampling time point can be substituted into the displacement curve to calculate the first-order derivative of the displacement curve, and the first-order derivative result can be determined as the target speed corresponding to each sampling time point. Then, the following formula (5-1) can be used to generate the third intermediate data according to the target speed corresponding to each sampling time point and the candidate speed; wherein the third intermediate data can be used to characterize the safety of the target vehicle when driving according to the candidate speed curve.

[0201]

[0202] Among them, target_v t Indicates the target speed corresponding to the acquisition time point t; s t′ represents the candidate speed corresponding to the acquisition time point t; t represents the number of acquisition time points, which can represent any positive integer between 0 and n; n represents the number of acquisition time points in the candidate speed curve, which is consistent with the number of sampling time points when constructing the candidate speed curve; lon_target_cost represents the balance of the difference between the candidate speed and the target speed at each sampling time point on the candidate speed curve. The smaller the value of lon_target_cost is, the smaller the difference between the candidate speed and the target speed at each sampling time point on the candidate speed curve is, that is, the higher the stability and safety of the candidate speed curve is.

[0203] In actual operation, considering that the coordinate position of the target vehicle at each collection time point and the position distance between the coordinate position of other vehicles are close, which has a greater impact on the safety of vehicle driving, the coordinate position of the target vehicle at each collection time point and the position distance between the coordinate position of other vehicles can be determined, and the safety of the candidate speed curve can be determined based on the position distance corresponding to each collection time point. Specifically, the safety of the candidate speed curve can be determined according to the segmented value method shown in the following formula (5-2).

[0204]

[0205] Among them, x t Indicates the coordinate position of the target vehicle at the acquisition time point t; Indicates the coordinate position of the other vehicle at the acquisition time point t; when the distance between the coordinate position of the target vehicle and the coordinate position of the other vehicle is less than half the length of the vehicle body, such as 2.5 meters, the safety of the candidate speed curve is determined to be low; otherwise, when the distance is greater than or equal to half the length of the vehicle body, such as 2.5 meters, the safety of the candidate speed curve is determined to be high. lon_safe_cost indicates the safety of the candidate speed curve. The smaller the value of lon_safe_cost, the higher the safety of the candidate speed curve.

[0206] In actual implementation, after obtaining lon_target_cost, the sum of lon_target_cost and lon_safe_cost can be used as third intermediate data to characterize the safety of the target vehicle when traveling according to the candidate speed curve.

[0207] For each candidate speed curve, each sampling time point can be substituted into the candidate speed curve, the second-order derivative of the candidate speed curve can be calculated, and the second-order derivative result can be determined as the second jerk corresponding to each sampling time point; or each sampling time point can be substituted into the displacement curve, the third-order derivative of the displacement curve can be calculated, and the third-order derivative result can be determined as the second jerk corresponding to each sampling time point. Then, the following formula (5-3) can be used to generate fourth intermediate data according to the second jerk corresponding to each sampling time point and the jerk of the target vehicle; wherein the fourth intermediate data can be used to characterize the comfort of the target vehicle when driving according to the candidate speed curve.

[0208]

[0209] Among them, comfort_lon_jerk represents the target vehicle acceleration; s t ″′ represents the second jerk corresponding to the acquisition time point t; t represents the number of acquisition time points, which can represent any positive integer between 0 and n; n represents the number of acquisition time points in the candidate speed curve, which is consistent with the number of sampling time points when constructing the candidate speed curve; lon_comfort_cost represents the average of the difference between the second jerk at each sampling time point on the candidate speed curve and the target vehicle jerk. The smaller the value of lon_comfort_cost, the higher the comfort level corresponding to the candidate speed curve.

[0210] Furthermore, the second scoring data corresponding to the candidate speed curve can be generated based on the third intermediate data and the fourth intermediate data. Specifically, the sum of the third intermediate data and the fourth intermediate data can be used as the second scoring data; or the weighted sum of the third intermediate data and the fourth intermediate data can be used as the second scoring data. Based on the second scoring data, the target speed curve can be determined from multiple candidate speed curves. In actual operation, after the second scoring data is obtained based on the above method, the candidate speed curve with the smallest second scoring data can be determined as the target speed curve.

[0211] Here, the target speed curve is selected based on the safety and comfort of the candidate speed curves, so that the target vehicle has better safety and comfort when driving according to the target speed curve. At the same time, the target vehicle is more in line with the vehicle kinematic characteristics when driving according to the target speed curve.

[0212] In a possible implementation, in S104, when the target path curve and the target speed curve are combined to generate the target driving trajectory, the following steps may be included:

[0213] Step C1, determining the driving displacements corresponding to the target vehicle when it travels to a plurality of sampling time points in the target speed curve;

[0214] Step C2, determining the vehicle coordinate position of the target vehicle at multiple sampling time points based on the current position of the target vehicle and the driving displacements corresponding to the multiple sampling time points in the target speed curve;

[0215] Step C3, based on the second coordinate position of each target path point in the target path curve and the vehicle coordinate position corresponding to each sampling time point in the target speed curve, the target path curve and the target speed curve are merged to generate a target driving trajectory.

[0216] During implementation, each sampling time point can be first brought into the displacement curve to calculate the driving displacement corresponding to each sampling time point in the target speed curve when the target vehicle travels. Then, based on the current position of the target vehicle and the driving displacement corresponding to each sampling time point in the target speed curve, the vehicle coordinate position of the target vehicle at multiple sampling time points can be determined; specifically, the sum of the first ordinate in the first coordinate position of the target vehicle and the driving displacement can be determined as the ordinate value of the target vehicle at the sampling time point, and the first abscissa in the first coordinate position of the target vehicle can be determined as the abscissa value of the target vehicle at the sampling time point; that is, the vehicle coordinate position of the target vehicle at the sampling time point can be obtained.

[0217] Furthermore, based on the second coordinate position of each target path point in the target path curve and the vehicle coordinate position corresponding to each sampling time point in the target speed curve, the target path points and target speed points with matching positions can be determined, and based on the target path points and target speed points with matching positions, the target path curve and the target speed curve can be merged to generate a target driving trajectory.

[0218] Here, by merging the target path curve with the highest smoothness and comfort and the target speed curve with the highest safety and comfort, the quality of the target driving trajectory is better, which improves the smoothness and comfort of the target driving trajectory.

[0219] The disclosed embodiments provide a trajectory generation method, device, computer equipment and storage medium. The method obtains the self-vehicle state information of the target vehicle, and determines a plurality of candidate path curves for the target vehicle based on the self-vehicle state information; and obtains the motion state information of the target vehicle, and determines a plurality of candidate speed curves for the target vehicle based on the motion state information. A target path curve is selected from the plurality of candidate path curves, and a target speed curve is selected from the plurality of candidate speed curves; the target path curve is merged with the target speed curve to generate a target driving trajectory for the target vehicle. The method takes into account the physical constraints and comfort constraints of the vehicle, so the candidate path curve is determined based on the self-vehicle state information, and the candidate speed curve is determined based on the motion state information, so that the selected target path curve and target speed curve are more consistent with the kinematic characteristics of the vehicle. At the same time, the stability and comfort of the target driving trajectory generated according to the target path curve and the target speed curve are better, thereby improving the quality of trajectory generation.

[0220] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0221] Based on the same concept, the present disclosure also provides a trajectory generation device, see Figure 4 As shown, it is a schematic diagram of the architecture of the trajectory generation device provided by the embodiment of the present disclosure, including a first determination module 401, a second determination module 402, a selection module 403, and a generation module 404. Specifically:

[0222] A first determination module 401 is used to obtain vehicle state information of a target vehicle and determine a plurality of candidate path curves for the target vehicle based on the vehicle state information;

[0223] A second determination module 402 is used to obtain the motion state information of the target vehicle and determine a plurality of candidate speed profiles for the target vehicle based on the motion state information;

[0224] A selection module 403 is used to select a target path curve from the plurality of candidate path curves, and to select a target speed curve from the plurality of candidate speed curves;

[0225] The generating module 404 is used to merge the target path curve with the target speed curve to generate a target driving trajectory of the target vehicle.

[0226] In a possible implementation manner, when determining a plurality of candidate path curves for the target vehicle based on the vehicle state information, the first determination module 401 is configured to:

[0227] Based on the driving strategy of the target vehicle, determining a candidate driving area of ​​the target vehicle in the current driving section;

[0228] Selecting a plurality of candidate path points from the candidate driving area, and determining path point information respectively corresponding to the plurality of candidate path points;

[0229] Based on the vehicle state information and the path point information respectively corresponding to the plurality of candidate path points, a plurality of candidate path curves are generated.

[0230] In a possible implementation manner, when generating the candidate path curve based on the vehicle state information and the path point information respectively corresponding to the plurality of candidate path points, the first determination module 401 is configured to:

[0231] Constructing a first relational expression for the candidate path curve; wherein the first relational expression is used to describe the relationship between the lateral coordinate value and the longitudinal coordinate value of each position point in the candidate path curve in the vehicle coordinate system;

[0232] Taking the current position of the target vehicle as the starting position of the candidate path curve, and using the first relational expression to construct a first relational expression for describing the state of the vehicle at the starting position; and

[0233] For each candidate path point among the plurality of candidate path points, taking each candidate path point as the end point position of each candidate path curve, and using the first relational expression to construct a second relational expression for describing the state of the target vehicle when the target vehicle is located at the end point position;

[0234] Based on the first relational expression and the second relational expression, unknown parameters in the first relational expression are solved to obtain the candidate path curve.

[0235] In a possible implementation manner, the vehicle state information includes a first coordinate position, a first heading angle, and a first curvature of the target vehicle, wherein the first coordinate position includes: a first horizontal coordinate and a first vertical coordinate of the target vehicle in the vehicle coordinate system; the path point information includes a second coordinate position, a second heading angle, and a second curvature of the candidate path point; the second coordinate position includes: a second horizontal coordinate and a second vertical coordinate of the candidate path point in the vehicle coordinate system;

[0236] The first relational expression includes: a relational expression for describing the relationship between the first ordinate and the first abscissa, a relational expression for describing the relationship between the first heading angle and the first abscissa, and a relational expression for describing the relationship between the first curvature, the first heading angle and the first abscissa;

[0237] The second relationship includes: a relationship for describing the relationship between the second longitudinal coordinate and the second horizontal coordinate, a relationship for describing the relationship between the second heading angle and the second horizontal coordinate, and a relationship for describing the relationship between the second curvature, the second heading angle and the second horizontal coordinate.

[0238] In a possible implementation manner, the motion state information includes: motion state information of the own vehicle and motion state information of other vehicles;

[0239] The second determination module 402, when determining a plurality of candidate speed curves for the target vehicle based on the motion state information, is configured to:

[0240] Based on the motion state information of the vehicle and the motion state information of the other vehicle, candidate speed points are determined for multiple sampling time points respectively, and a candidate speed and a candidate acceleration corresponding to each of the candidate speed points are determined; wherein two adjacent sampling time points are separated by a preset time length, and each of the sampling time points corresponds to at least one candidate speed point;

[0241] The candidate speed curve is generated based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points.

[0242] In a possible implementation manner, the second determination module 402, when determining candidate speed points for a plurality of sampling time points respectively based on the own vehicle motion state information and the other vehicle motion state information, and determining a candidate speed and a candidate acceleration corresponding to each of the candidate speed points, is configured to:

[0243] For a first sampling time point, based on the motion state information of the own vehicle and the motion state information of the other vehicle, determine a corresponding candidate speed point for the first sampling time point, and determine a candidate speed and a candidate acceleration corresponding to each candidate speed point;

[0244] For each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point, and the motion state information of the other vehicle, the corresponding candidate speed point is determined for each other sampling time point, and the candidate speed and candidate acceleration corresponding to each of the candidate speed points are determined.

[0245] In a possible implementation manner, the self-vehicle motion state information includes a first vehicle speed and a first vehicle acceleration of the target vehicle; the other vehicle motion state information includes a second vehicle speed and a second vehicle acceleration of the other vehicle;

[0246] The second determination module 402, when determining the corresponding candidate speed point for the first sampling time point based on the own vehicle motion state information and the other vehicle motion state information, and determining the candidate speed and candidate acceleration corresponding to each of the candidate speed points, is used to:

[0247] Determine the first self-vehicle maximum speed of each candidate speed point corresponding to the first sampling time point based on the interval time between the first sampling time point and the current time, the preset self-vehicle maximum acceleration, and the first vehicle speed; and determine the first self-vehicle minimum speed corresponding to each candidate speed point corresponding to the first sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the first vehicle speed;

[0248] An acceleration interval is formed based on the maximum acceleration of the own vehicle, the minimum acceleration of the own vehicle, and the second vehicle acceleration, and a candidate acceleration of each candidate speed point corresponding to the first sampling time point is determined within the acceleration interval based on the first vehicle acceleration, the target vehicle jerk, the interval time, and the number of candidate speed points corresponding to the first sampling time point;

[0249] A first speed interval is formed based on the first self-vehicle maximum speed, the first self-vehicle minimum speed, and the second vehicle speed, and a candidate speed of each candidate speed point corresponding to the first sampling time point is determined within the first speed interval based on the first vehicle speed, the candidate acceleration of each candidate speed point corresponding to the first sampling time point, and the interval duration.

[0250] In a possible implementation manner, the second determination module 402, for each sampling time point other than the first sampling time point, determines the corresponding candidate speed point for each other sampling time point based on the candidate speeds and candidate accelerations corresponding to the respective candidate speed points at the previous sampling time point corresponding to each other sampling time point, and the motion state information of the other vehicle, and determines the candidate speed and candidate acceleration corresponding to each of the candidate speed points, for:

[0251] Determine the second self-vehicle maximum speed of each candidate speed point corresponding to each other sampling time point based on the interval time between each other sampling time point and the corresponding previous sampling time point, the preset self-vehicle maximum acceleration, and the candidate speed corresponding to the previous sampling time point; and determine the second self-vehicle minimum speed of each candidate speed point corresponding to each other sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the candidate acceleration corresponding to the previous sampling time point;

[0252] Based on the candidate acceleration corresponding to the previous sampling time point, the target vehicle jerk, the interval duration, and the number of candidate speed points corresponding to each of the other sampling time points, determine the candidate acceleration of each candidate speed point corresponding to each of the other sampling time points within the acceleration interval;

[0253] A second speed interval is formed based on the second self-vehicle maximum speed corresponding to the candidate speed point, the second self-vehicle minimum speed corresponding to the candidate speed point, and the second vehicle speed, and a candidate speed corresponding to each candidate speed point at each other sampling time point is determined within the second speed interval based on the candidate speed corresponding to the previous sampling time point, the candidate acceleration of each candidate speed point corresponding to each other sampling time point, and the interval duration.

[0254] In a possible implementation manner, the second determination module 402, when generating the candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points, is configured to:

[0255] Constructing a second relational expression of the displacement curve; wherein the second relational expression is used to describe the relationship between each displacement and time in the displacement curve;

[0256] Taking the current position of the target vehicle as the starting position of the displacement curve, and using the second relational expression, constructing a third relational expression for describing the ego-vehicle motion state of the target vehicle;

[0257] For each of the plurality of candidate speed points, using the second relational expression, construct a fourth relational expression for describing the motion state of the target vehicle at the candidate speed point;

[0258] Based on the third relational expression and the fourth relational expression, the unknown parameters in the second relational expression are solved, and based on the second relational expression in which the unknown parameters are determined, the candidate speed curve is obtained.

[0259] In a possible implementation manner, the third relationship includes: a relationship for describing the relationship between the vehicle displacement and the current time point, a relationship for describing the relationship between the vehicle speed and the current time point, and a relationship for describing the relationship between the vehicle acceleration and the current time point;

[0260] The fourth relational expression includes: a relational expression for describing the relationship between the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point, and a relational expression for describing the relationship between the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point.

[0261] In a possible implementation manner, the selection module 403, when selecting a target path curve from the plurality of candidate path curves, is configured to:

[0262] Generate first scoring data corresponding to the plurality of candidate path curves respectively; the first scoring data is used to describe the smoothness and comfort of the target vehicle when traveling along the candidate path curve;

[0263] The target path curve is determined from the plurality of candidate path curves based on the first scoring data.

[0264] In a possible implementation manner, the selection module 403, when selecting a target speed curve from the plurality of candidate speed curves, is configured to:

[0265] Generating second scoring data corresponding to the plurality of candidate speed curves respectively; the second scoring data is used to describe the safety and comfort of the target vehicle when traveling according to the candidate speed curve;

[0266] The target speed profile is determined from the plurality of candidate speed profiles based on the second scoring data.

[0267] In a possible implementation manner, the generating module 404, when merging the target path curve with the target speed curve to generate the target driving trajectory, is configured to:

[0268] Determine the driving displacements corresponding to the plurality of sampling time points in the target speed curve when the target vehicle drives to each of the plurality of sampling time points;

[0269] Determine the vehicle coordinate position of the target vehicle at the multiple sampling time points based on the current position of the target vehicle and the driving displacements corresponding to the multiple sampling time points in the target speed curve;

[0270] Based on the second coordinate position of each target path point in the target path curve and the vehicle coordinate position corresponding to each sampling time point in the target speed curve, the target path curve and the target speed curve are merged to generate a target driving trajectory.

[0271] In some embodiments, the functions or templates contained in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0272] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Figure 5 As shown, it is a schematic diagram of the structure of a computer device provided by an embodiment of the present disclosure, including a processor 501, a memory 502, and a bus 503. Among them, the memory 502 is used to store execution instructions, including a memory 5021 and an external memory 5022; the memory 5021 here is also called an internal memory, which is used to temporarily store the operation data in the processor 501, and the data exchanged with the external memory 5022 such as a hard disk. The processor 501 exchanges data with the external memory 5022 through the memory 5021. When the computer device is running, the processor 501 communicates with the memory 502 through the bus 503, so that the processor 501 executes the following instructions:

[0273] Acquiring vehicle state information of a target vehicle, and determining a plurality of candidate path curves for the target vehicle based on the vehicle state information;

[0274] and, obtaining motion state information of the target vehicle, and determining a plurality of candidate speed profiles for the target vehicle based on the motion state information;

[0275] Selecting a target path curve from the plurality of candidate path curves, and selecting a target speed curve from the plurality of candidate speed curves;

[0276] The target path curve and the target speed curve are combined to generate a target driving trajectory of the target vehicle.

[0277] The specific processing flow of the processor 501 may refer to the description of the above method embodiment, which will not be repeated here.

[0278] In addition, the embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the trajectory generation method described in the above method embodiment are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0279] The present disclosure also provides a computer program product, which carries a program code. The program code includes instructions that can be used to execute the steps of the trajectory generation method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0280] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0281] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0282] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0283] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0284] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0285] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A trajectory generation method, characterized in that: include: Acquiring vehicle state information of a target vehicle, and determining a plurality of candidate path curves for the target vehicle based on the vehicle state information; and, obtaining motion state information of the target vehicle, and determining a plurality of candidate speed profiles for the target vehicle based on the motion state information; Selecting a target path curve from the plurality of candidate path curves, and selecting a target speed curve from the plurality of candidate speed curves; Merging the target path curve with the target speed curve to generate a target driving trajectory of the target vehicle; The motion state information includes: the motion state information of the own vehicle and the motion state information of other vehicles; The step of determining a plurality of candidate speed curves for the target vehicle based on the motion state information includes: For a first sampling time point, based on the motion state information of the own vehicle and the motion state information of the other vehicle, determine a corresponding candidate speed point for the first sampling time point, and determine a candidate speed and a candidate acceleration corresponding to each candidate speed point; For each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point and the motion state information of the other vehicle, determine the corresponding candidate speed point for each other sampling time point, and determine the candidate speed and candidate acceleration corresponding to each of the candidate speed points; Generate the candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points; There is a preset time interval between two adjacent sampling time points, and each of the sampling time points corresponds to at least one candidate speed point.

2. The method according to claim 1, characterized in that The step of determining a plurality of candidate path curves for the target vehicle based on the vehicle state information includes: Based on the driving strategy of the target vehicle, determining a candidate driving area of ​​the target vehicle in the current driving section; Selecting a plurality of candidate path points from the candidate driving area, and determining path point information respectively corresponding to the plurality of candidate path points; Based on the vehicle state information and the path point information respectively corresponding to the plurality of candidate path points, a plurality of candidate path curves are generated.

3. The method according to claim 2, characterized in that The generating the candidate path curve based on the vehicle state information and the path point information respectively corresponding to the plurality of candidate path points comprises: Constructing a first relational expression for the candidate path curve; wherein the first relational expression is used to describe the relationship between the lateral coordinate value and the longitudinal coordinate value of each position point in the candidate path curve in the vehicle coordinate system; Taking the current position of the target vehicle as the starting position of the candidate path curve, and using the first relational expression to construct a first relational expression for describing the state of the vehicle at the starting position; and For each candidate path point among the plurality of candidate path points, taking each candidate path point as the end point position of each candidate path curve, and using the first relational expression to construct a second relational expression for describing the state of the target vehicle when the target vehicle is located at the end point position; Based on the first relational expression and the second relational expression, unknown parameters in the first relational expression are solved to obtain the candidate path curve.

4. The method according to claim 3, characterized in that The vehicle state information includes a first coordinate position, a first heading angle, and a first curvature of the target vehicle, wherein the first coordinate position includes: a first horizontal coordinate and a first vertical coordinate of the target vehicle in the vehicle coordinate system; the path point information includes a second coordinate position, a second heading angle, and a second curvature of the candidate path point; the second coordinate position includes: a second horizontal coordinate and a second vertical coordinate of the candidate path point in the vehicle coordinate system; The first relational expression includes: a relational expression for describing the relationship between the first ordinate and the first abscissa, a relational expression for describing the relationship between the first heading angle and the first abscissa, and a relational expression for describing the relationship between the first curvature, the first heading angle and the first abscissa; The second relationship includes: a relationship for describing the relationship between the second longitudinal coordinate and the second horizontal coordinate, a relationship for describing the relationship between the second heading angle and the second horizontal coordinate, and a relationship for describing the relationship between the second curvature, the second heading angle and the second horizontal coordinate.

5. The method according to claim 1, characterized in that The self-vehicle motion state information includes a first vehicle speed and a first vehicle acceleration of the target vehicle; the other vehicle motion state information includes a second vehicle speed and a second vehicle acceleration of the other vehicle; The step of determining a corresponding candidate speed point for the first sampling time point based on the vehicle motion state information and the other vehicle motion state information, and determining a candidate speed and a candidate acceleration corresponding to each candidate speed point includes: Determine the first self-vehicle maximum speed of each candidate speed point corresponding to the first sampling time point based on the interval time between the first sampling time point and the current time, the preset self-vehicle maximum acceleration, and the first vehicle speed; and determine the first self-vehicle minimum speed corresponding to each candidate speed point corresponding to the first sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the first vehicle speed; An acceleration interval is formed based on the maximum acceleration of the own vehicle, the minimum acceleration of the own vehicle, and the acceleration of the second vehicle, and a candidate acceleration of each candidate speed point corresponding to the first sampling time point is determined within the acceleration interval based on the first vehicle acceleration, the target vehicle jerk, the interval time, and the number of candidate speed points corresponding to the first sampling time point; A first speed interval is formed based on the first self-vehicle maximum speed, the first self-vehicle minimum speed, and the second vehicle speed, and a candidate speed of each candidate speed point corresponding to the first sampling time point is determined within the first speed interval based on the first vehicle speed, the candidate acceleration of each candidate speed point corresponding to the first sampling time point, and the interval duration.

6. The method according to claim 5, characterized in that The step of determining the corresponding candidate speed point for each other sampling time point except the first sampling time point based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point and the motion state information of the other vehicle, and determining the candidate speed and candidate acceleration corresponding to each of the candidate speed points includes: Determine the second self-vehicle maximum speed of each candidate speed point corresponding to each other sampling time point based on the interval time between each other sampling time point and the corresponding previous sampling time point, the preset self-vehicle maximum acceleration, and the candidate speed corresponding to the previous sampling time point; and determine the second self-vehicle minimum speed of each candidate speed point corresponding to each other sampling time point based on the interval time, the preset self-vehicle minimum acceleration, and the candidate acceleration corresponding to the previous sampling time point; Based on the candidate acceleration corresponding to the previous sampling time point, the target vehicle jerk, the interval duration, and the number of candidate speed points corresponding to each of the other sampling time points, determine the candidate acceleration of each candidate speed point corresponding to each of the other sampling time points within the acceleration interval; A second speed interval is formed based on the second self-vehicle maximum speed corresponding to the candidate speed point, the second self-vehicle minimum speed corresponding to the candidate speed point, and the second vehicle speed, and a candidate speed corresponding to each candidate speed point at each other sampling time point is determined within the second speed interval based on the candidate speed corresponding to the previous sampling time point, the candidate acceleration of each candidate speed point corresponding to each other sampling time point, and the interval duration.

7. The method according to any one of claims 1 to 6, characterized in that: The generating the candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points comprises: Constructing a second relational expression of the displacement curve; wherein the second relational expression is used to describe the relationship between each displacement and time in the displacement curve; Taking the current position of the target vehicle as the starting position of the displacement curve, and using the second relational expression, constructing a third relational expression for describing the ego-vehicle motion state of the target vehicle; For each candidate speed point among the plurality of candidate speed points, constructing a fourth relational expression for describing the motion state of the target vehicle at the candidate speed point by using the second relational expression; Based on the third relational expression and the fourth relational expression, the unknown parameters in the second relational expression are solved, and based on the second relational expression in which the unknown parameters are determined, the candidate speed curve is obtained.

8. The method according to claim 7, characterized in that The third relational expression includes: a relational expression for describing the relationship between the vehicle displacement of the target vehicle and the current time point, a relational expression for describing the relationship between the vehicle speed of the target vehicle and the current time point, and a relational expression for describing the relationship between the vehicle acceleration of the target vehicle and the current time point; The fourth relational expression includes: a relational expression for describing the relationship between the candidate speed corresponding to the candidate speed point and the sampling time point matching the candidate speed point, and a relational expression for describing the relationship between the candidate acceleration corresponding to the candidate speed point and the sampling time point matching the candidate speed point.

9. The method according to claim 1, characterized in that: The step of selecting a target path curve from a plurality of candidate path curves comprises: Generate first scoring data corresponding to the plurality of candidate path curves respectively; the first scoring data is used to describe the smoothness and comfort of the target vehicle when traveling along the candidate path curve; The target path curve is determined from the plurality of candidate path curves based on the first scoring data.

10. The method according to claim 1, characterized in that The step of selecting a target speed curve from a plurality of candidate speed curves comprises: Generating second scoring data corresponding to the plurality of candidate speed curves respectively; the second scoring data is used to describe the safety and comfort of the target vehicle when traveling according to the candidate speed curve; The target speed profile is determined from the plurality of candidate speed profiles based on the second scoring data.

11. The method according to claim 1, characterized in that: The step of merging the target path curve with the target speed curve to generate a target driving trajectory includes: Determine the driving displacements corresponding to the target vehicle when it travels to a plurality of sampling time points in the target speed curve; Determine the vehicle coordinate position of the target vehicle at the multiple sampling time points based on the current position of the target vehicle and the driving displacements corresponding to the multiple sampling time points in the target speed curve; Based on the second coordinate position of each target path point in the target path curve and the vehicle coordinate position corresponding to each sampling time point in the target speed curve, the target path curve and the target speed curve are merged to generate a target driving trajectory.

12. A trajectory generating device, characterized in that: include: A first determination module is used to obtain vehicle state information of a target vehicle and determine a plurality of candidate path curves for the target vehicle based on the vehicle state information; a second determination module, configured to obtain motion state information of the target vehicle, and determine a plurality of candidate speed curves for the target vehicle based on the motion state information; A selection module, configured to select a target path curve from the plurality of candidate path curves, and to select a target speed curve from the plurality of candidate speed curves; A generating module, used for combining the target path curve with the target speed curve to generate a target driving trajectory of the target vehicle; The motion state information includes: the motion state information of the own vehicle and the motion state information of other vehicles; The second determination module, when determining a plurality of candidate speed curves for the target vehicle based on the motion state information, is used to: For a first sampling time point, based on the motion state information of the own vehicle and the motion state information of the other vehicle, determine a corresponding candidate speed point for the first sampling time point, and determine a candidate speed and a candidate acceleration corresponding to each candidate speed point; For each sampling time point other than the first sampling time point, based on the candidate speeds and candidate accelerations corresponding to the candidate speed points at the previous sampling time point corresponding to each other sampling time point and the motion state information of the other vehicle, determine the corresponding candidate speed point for each other sampling time point, and determine the candidate speed and candidate acceleration corresponding to each of the candidate speed points; Generate the candidate speed curve based on the motion state information of the target vehicle and the candidate speeds and candidate accelerations of the candidate speed points at the respective sampling time points; There is a preset time interval between two adjacent sampling time points, and each of the sampling time points corresponds to at least one candidate speed point.

13. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the trajectory generation method according to any one of claims 1 to 11 are performed.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the trajectory generation method according to any one of claims 1 to 11 are executed.