CN115447607A

CN115447607A - Method and device for planning a vehicle driving trajectory

Info

Publication number: CN115447607A
Application number: CN202211077626.3A
Authority: CN
Inventors: 蔡雄风; 陈炯
Original assignee: Anhui Weilai Zhijia Technology Co Ltd
Current assignee: Anhui Weilai Zhijia Technology Co Ltd
Priority date: 2022-09-05
Filing date: 2022-09-05
Publication date: 2022-12-09

Abstract

The present application relates to an automatic driving technology, and more particularly, to a method and apparatus for planning a vehicle driving trajectory in an application scenario where a user on a vulnerable road is present. A method for planning a vehicle travel path according to one aspect of the present application comprises the steps of: determining the type of the vulnerable road user in the moving direction of the ego-vehicle and a predicted moving track of the vulnerable road user in a next time period; determining a potential activity area of the vulnerable road user in the next time period based on the type of the vulnerable road user and the predicted motion trail; generating an avoidance transition region surrounding the potential activity region; and selecting the candidate planning track with the minimum cost from the candidate planning tracks which can bypass the potential activity area and are related to the self vehicle in the next time period as the optimized planning track, wherein the candidate planning track which passes through the avoidance transition area has extra avoidance cost compared with the candidate planning track which does not pass through the avoidance transition area.

Description

Method and device for planning a vehicle driving trajectory

Technical Field

The present application relates to an automatic driving technology, and more particularly, to a method and apparatus for planning a vehicle driving trajectory in an application scenario where a user on a vulnerable road is present.

Background

Vulnerable Road Users (VRU) refer to participants in road traffic who are vulnerable to injury due to lack of safety protection, including mainly pedestrians and two-wheel vehicle users. According to relevant statistics, the number of VRU deaths accounts for more than half of the number of global road traffic accident deaths, so that the improvement of the safety protection of the VRU is a topic of major attention in the field of active collision avoidance of automobiles.

In the field of automatic driving, active collision avoidance research aiming at weak road users at present mainly focuses on aspects of VRU identification, motion prediction and the like. However, due to the complexity of the application scenario, the diversified application requirements cannot be met only by means of improving the accuracy of VRU identification and motion prediction.

Disclosure of Invention

It is an object of the present application to provide a method and apparatus for planning a vehicle travel track that can improve both automated driving safety and ride comfort.

According to one aspect of the present application, there is provided a method for planning a driving trajectory of a vehicle, comprising the steps of:

determining the type of the vulnerable road user in the moving direction of the ego-vehicle and a predicted movement track of the vulnerable road user in a next time period;

determining a potential activity area of the vulnerable road user in a next time period based on the type of the vulnerable road user and the predicted movement track;

generating an avoidance transition region surrounding the potential active region;

selecting a candidate planning trajectory with the minimum cost from a plurality of candidate planning trajectories which can bypass the potential activity area and are related to the ego-vehicle in the next time period as an optimized planning trajectory, wherein the candidate planning trajectory which passes through the avoidance transition area has an additional avoidance cost compared with the candidate planning trajectory which does not pass through the avoidance transition area.

Optionally, in the above method, the step of determining the type and predicted movement locus of the vulnerable road user comprises:

receiving environmental status data of the ego-vehicle;

determining the type and the motion state of the vulnerable road user from the environment state data;

determining the predicted movement trajectory based on at least the type and movement state of the vulnerable road user.

Optionally, in the above method, the vulnerable road user is one or more of: pedestrians, non-motorized vehicles and motorcycles, the state of motion of said vulnerable road user comprising one or more of the following: speed, acceleration, direction of motion, turn signal status, and historical motion profiles.

Optionally, in the above method, the potential active region and the avoidance transition region are represented by regions in an ST diagram or an SL diagram.

Further, the step of generating an avoidance transition region comprises:

determining a boundary of the avoidance transition region based on at least one of a type of the vulnerable road user, a user driving history, and a user setting;

determining an attribute value of each position in the avoidance transition region based on at least one of the type of the vulnerable road user, the user driving history and the user settings, the attribute value representing a contribution component of the corresponding position to an additional avoidance cost.

Further, the attribute value of each location decreases as the minimum distance between the location and the boundary of the potential activity area increases.

In addition to one or more of the features described above, in the above method, the step of selecting an optimized planned trajectory comprises:

generating a plurality of candidate planning trajectories capable of bypassing the potential activity area;

calculating the basic cost of the candidate planning track by using a cost function;

determining the sum of the corresponding basic cost and the extra avoidance cost as the corresponding cost for the candidate planning track passing through the avoidance transition region;

and determining the candidate planning track with the minimum cost as the optimized planning track.

Further, the additional avoidance cost is a sum of contribution components of locations traversed by the candidate planned trajectory within the avoidance transition region.

Further, the parameter of the cost function is determined based on at least one of a type, a motion state, a user setting, and a user driving history of the vulnerable road user.

Further, the planned trajectory is configured to decrease a longitudinal speed of the ego-vehicle and increase a lateral distance from the vulnerable road user when approaching the vulnerable road user, and increase a longitudinal speed of the ego-vehicle and decrease a lateral distance from the vulnerable road user when away from the vulnerable road user.

According to another aspect of the present application, there is provided an apparatus for planning a driving trajectory of a vehicle, comprising:

a memory;

a processor coupled with the memory; and

a computer program stored on the memory and executable on the processor, the method as described above being implemented by executing the computer program.

According to yet another aspect of the present application, there is provided an apparatus for planning a driving trajectory of a vehicle, comprising:

a perception and prediction module configured to determine a type of a vulnerable road user in a moving direction of the ego-vehicle and a predicted movement track of the vulnerable road user in a next time period;

a planning decision module configured to perform the following operations:

determining a potential activity area of the vulnerable road user in a next time period based on the type of the vulnerable road user and the predicted motion trail;

selecting a candidate planning trajectory with the minimum cost as an optimized planning trajectory from a plurality of candidate planning trajectories for the ego-vehicle in the next time period that can bypass the potential activity area, wherein the candidate planning trajectory that passes through the avoidance transition area has an additional avoidance cost compared to the candidate planning trajectory that does not pass through the avoidance transition area.

In some embodiments of the present application, more safety redundancy is introduced by employing an avoidance transition region. In addition, due to the fact that extra avoidance cost is added, the tracks where longitudinal deceleration and transverse avoidance occur are more likely to be selected in the planning process, and therefore the driving habits of human users are better matched. Furthermore, since the basic framework of the existing path planning technology can be used, the existing mature algorithm can be fully utilized (for example, the existing cost function can be directly used for calculating the basic cost of the candidate planned path without modifying the existing cost function), which is beneficial to reducing the development cost and the development period.

Drawings

The above and/or other aspects and advantages of the present application will become more apparent and more readily appreciated from the following description of the various aspects, taken in conjunction with the accompanying drawings, in which like or similar elements are represented by like reference numerals. The drawings comprise:

FIG. 1 is a flow chart of a method for planning a vehicle travel path according to some embodiments of the present application.

FIG. 2 is a flow chart of a method for determining a type and predicted movement trajectory of a vulnerable road user according to further embodiments of the present application.

Fig. 3 is a schematic view of a potential activation region and an avoidance transition region.

Fig. 4 shows exemplary potential active regions and avoidance transition regions represented in the ST diagram.

FIG. 5 is a flow diagram of a method for generating an avoided transition region in accordance with further embodiments of the present application.

FIG. 6 is a flow diagram of a method for generating an optimized planned trajectory according to further embodiments of the present application.

Fig. 7 shows an example of an optimized planning trajectory resulting from using the above-described embodiment and using an existing planning strategy.

FIG. 8 is a schematic block diagram of a typical computer system.

Fig. 9 is a schematic block diagram of an apparatus for planning a travel path of a vehicle.

Detailed Description

The present application is described more fully hereinafter with reference to the accompanying drawings, in which illustrative embodiments of the application are shown. This application may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. The embodiments described above are intended to be a complete and complete disclosure of the present disclosure, so as to more fully convey the scope of the present application to those skilled in the art.

In the present specification, words such as "comprise" and "comprising" mean that in addition to elements and steps directly and unequivocally stated in the specification and claims, the technical solutions of the present application do not exclude other elements and steps not directly or unequivocally stated.

Unless otherwise specified, terms such as "first" and "second" do not denote an order of the elements in time, space, size, etc., but rather are used to distinguish one element from another.

In this application, "vulnerable road users" are to be understood broadly as dangerous objects susceptible to injury by road traffic, typically pedestrians, non-motor vehicles, motorcycles and the like.

FIG. 1 is a flow chart of a method for planning a vehicle travel trajectory according to some embodiments of the present application. Illustratively, the steps of the method are performed by an autonomous driving domain controller. In a typical entire vehicle architecture based on a domain controller, the automatic driving domain controller is responsible for data processing, calculating and judging capabilities required by automatic driving, for example, the data processing capabilities include data processing capabilities acquired by sensors such as a millimeter wave radar, a camera, a laser radar, a GPS, inertial navigation and the like.

The method shown in fig. 1 comprises the following steps:

step 101: determining the type and predicted movement trajectory of a vulnerable road user

In this step, the type of the vulnerable road user and the predicted movement locus can be determined by means of the subroutine shown in fig. 2.

Specifically, in step 201, an Ego vhile or an autonomous driving area controller of the own vehicle receives environmental state data of the own vehicle. The environment typically includes static elements such as road layout and lane structure, as well as dynamic elements such as vehicles, pedestrians, and other types of road users. Static elements can be obtained through a high-definition map containing lane level information, and dynamic elements can be obtained through sensors such as a camera, a millimeter wave radar and a laser radar.

The method flow shown in fig. 2 then proceeds to step 202. In this step, the automatic driving area controller determines the type and motion state of the vulnerable road user in the direction of the movement of the ego vehicle from environmental state data (e.g., an image captured by a camera, point cloud data acquired by a radar, and lane data extracted from a high-precision map, etc.). Examples of motion states described herein include, but are not limited to, speed, acceleration, direction of motion, turn signal status, historical motion profiles, etc. of a vulnerable road user.

Then, in step 203, the automatic driving area controller predicts the motion track of the vulnerable road user in the next time period. The length of the time period may depend on the application scenario and may be in the order of several hundred milliseconds or seconds, for example. The prediction of the movement trajectory is based on at least the type and movement state of the vulnerable road user. In addition, other factors such as road layout, lane structure, traffic light status, etc. may also be introduced in the prediction of the movement trajectory. For example, when the vulnerable road user is a pedestrian and is far from the intersection, the predicted motion trajectory is generally limited to the range of the sidewalk.

Step 102: determination of potential activity areas

Fig. 3 shows an example of a potential activity area. As shown in fig. 3, the vehicle EV is traveling on a road, and the area VRU marked with dark color in the front right thereof is an area associated with the vulnerable road users or potential activity areas thereof in the next time period.

In some embodiments, the potential active areas may be represented as areas in an ST map or an SL map. The ST diagram is a two-dimensional coordinate plane having time (T) as the horizontal axis and the vertical distance (S) of the planned path as the vertical axis. The SL graph is a two-dimensional coordinate plane with the horizontal axis as the vertical distance (S) of the planned route and the vertical axis as the horizontal distance (L) of the planned route, and is combined with the ST graph to generate a three-dimensional planned trajectory (vertical dimension, horizontal dimension, and time dimension) of the host vehicle. By constructing the ST map, the velocity plan can be projected onto a two-dimensional plane to be solved in an optimized manner, and the predicted trajectory of the obstacle can be projected onto the two-dimensional plane to make a rational decision. In addition, in the ST diagram, the slope of the curve represents the derivative of the S value to time (i.e., velocity), so that the relationship between the velocity and the path can be constructed by the S value, so that the two can be better merged into one track.

Fig. 4 shows an example of potential active areas represented in the ST diagram. In the example shown in fig. 4, the potential active areas VRU are identified by dark regions.

In step 102, the autopilot domain controller will determine the potential activity area based on the type of vulnerable road user determined in step 101 and the predicted motion profile. For example, since the vulnerable road user is an object occupying a certain space, the size of the space occupied by the vulnerable road user can be estimated from the type of the vulnerable road user, and a possible activity range (i.e., a potential activity area) of the vulnerable road user in the next time period can be obtained by combining the predicted motion trajectory.

Step 103: generation of an avoidance transition region

The existing VRU active collision avoidance strategy mainly considers safety, namely, collision with users on weak roads does not occur, and the collision is used as an optimization target of trajectory planning and motion control. However, in actual driving, it is not sufficient to consider only safety. For example, according to the currently common planning strategy, it is only necessary to ensure that the planned trajectory of the own vehicle does not cross the potential activity area of the VRU, and that the speed is not further planned (for example, decelerated or accelerated). However, this approach differs from human driving habits (when the host vehicle approaches a vulnerable road user, the human driver typically subconsciously reduces the vehicle speed and/or performs a slight lateral avoidance maneuver), thereby providing a poor user experience. Furthermore, existing collision avoidance planning methods require relatively aggressive braking and steering control in response to sudden behavior (e.g., sudden changes in direction or speed of movement) by the road users, which adversely affects driving safety and comfort.

In some embodiments of the present application, safety and ride comfort are improved by introducing an avoidance transition region in the trajectory plan. The avoidance transition region is a region that surrounds or encloses the potential active region, and when the planned trajectory passes through the avoidance transition region, additional avoidance costs are added as compared to regions outside the avoidance transition region. This additional avoidance cost will have an effect on the optimization result of the planned trajectory, i.e. the planned trajectory passing through the avoidance transition region is less likely to be selected as the optimized planned trajectory.

Fig. 3 shows an example of an avoidance transition region. Referring to fig. 3, the region VRU indicated in a dark color is surrounded by a region a (avoidance transition region). Fig. 4 shows an example of an avoidance transition region shown in the ST diagram. In the example shown in fig. 4, the potential active region VRU is likewise surrounded by a region a (avoidance transition region).

In step 103, the autopilot domain controller generates an avoidance transition region that encompasses the potential activity region. The avoidance transition region may be generated by means of a subroutine shown in fig. 5.

Specifically, in step 501, the autopilot domain controller obtains the boundary of the avoidance transition region, for example, by expanding the boundary of the potential active region. The extent of the expansion of the boundary may be determined according to various factors. In some embodiments, the factors considered include at least one of a type of vulnerable road user, a user setting, and a user profile. For example, for more mobile or random road users with weak roads (e.g., children, non-motor vehicles, motorcycles, etc.), the boundary expansion factor of the potential active region (e.g., expressed as the ratio of the area of the avoidance transition region to the potential active region or the ratio of the perimeter of the avoidance transition region to the potential active region) may be set to be larger. For another example, the driving history of a user may be analyzed to obtain the driving habit of the user, so as to obtain the customized boundary expansion coefficient for the user. As another example, the boundary expansion coefficient may be set by the user.

It is noted that while in the embodiment shown in fig. 5, the expansion of the potential active area is isotropic, this is not required. In some application scenarios, the expansion may be anisotropic, i.e. the degree of expansion differs in different directions.

As discussed above, additional avoidance costs are added when the planned trajectory passes through the avoidance transition region. The contribution component of the respective position to the additional avoidance cost is represented by assigning an attribute value to each position in the avoidance transition region. Fig. 4 shows an example of attribute values. Referring to fig. 4, the attribute value of each location decreases as the minimum distance between the location and the boundary of the potential activity area increases. It should be noted that the linear variation relationship between the attribute value and the minimum distance and the value of the attribute value given in fig. 4 are exemplary. For example, the attribute value may be in a non-linear variation relationship with the minimum distance according to the requirements of the application scenario.

After performing step 501, the method of FIG. 5 proceeds to step 502 where the autonomous driving range controller determines attribute values for various locations in the avoidance transition region. In some embodiments, the attribute value may be determined based on at least one of a type of the vulnerable road user, a user driving history, and a user setting.

Step 104: generation of planned trajectories

In this step, an optimized planned trajectory may be generated for the ego-vehicle by means of the subroutine shown in fig. 6.

Specifically, in step 601, the autonomous driving domain controller generates a plurality of candidate planned trajectories that can bypass the potential activity region. Various planning trajectory strategies are available for generating these candidate planning trajectories, and are not described in detail herein. In some embodiments, the candidate planned trajectory is set to decrease a longitudinal speed of the host vehicle and increase a lateral distance from the vulnerable road user when approaching the vulnerable road user, and to increase the longitudinal speed of the host vehicle and decrease the lateral distance from the vulnerable road user when away from the vulnerable road user.

Then, in step 602, the automatic driving domain controller calculates the basic cost of the candidate planned trajectories generated in step 601 by using the cost function. As discussed above, additional avoidance costs are added when the planned trajectory passes through the avoidance transition region. The base cost is referred to herein as the cost of a candidate planned trajectory without accounting for additional back-off costs. In calculating the basic cost, a cost function commonly used in the trajectory planning technology at present can be selected. The cost function may take into account a variety of factors including, for example and without limitation, reaching a target, smoothing, avoiding a collision, centripetal acceleration, lateral offset, comfort, and the like. Further, in some embodiments, parameters of the cost function (e.g., cost coefficients within a specified distance, etc.) may be determined or adjusted based on at least one of the type of the vulnerable road user, the state of motion, the user settings, and the user's driving history.

Then, in step 603, for the candidate planning trajectory passing through the avoidance transition region, the sum of the corresponding basic cost and the additional avoidance cost is determined as the corresponding cost.

In some embodiments, for each candidate planned trajectory passing through the avoidance transition region, the additional avoidance cost may be determined as follows:

wherein, extra _ Cost _i For the extra avoidance cost of the candidate planning track passing through the avoidance transition region, the candidate planning track passing through the avoidance transition region is assumed to pass through n positions, mu, in the avoidance transition region _ij Is the attribute value of the j-th position of the n positions, i.e. the contribution component of the j-th position to the extra back-off cost.

After step 603 is performed, the cost of each candidate planned trajectory, which has been added with an additional avoidance cost, is obtained. Thus, the method flow shown in FIG. 6 proceeds to step 604. In this step, the autopilot domain controller determines the candidate planned trajectory with the smallest cost as the optimized planned trajectory.

In the embodiments shown above, the use of an avoidance transition region instead of a potential active region amounts to the introduction of more safety redundancy. Meanwhile, as extra avoidance cost is added to the candidate planning path passing through the avoidance transition region, the tracks with longitudinal deceleration and transverse avoidance are more likely to be selected in the planning process, and the driving habits of human users are better matched. In addition, the above embodiments can use the basic framework of the existing path planning technology, so that the existing mature algorithm can be fully utilized (for example, the existing cost function can be directly used for calculating the basic cost of the candidate planned path without modifying), which is beneficial to reducing the development cost and the development period.

Fig. 7A and 7B respectively show examples of optimized planning trajectories obtained by using the above-described embodiment and the existing planning strategy, wherein the left half of fig. 7A and 7B is a top view, and the right half is a front view. As can be seen by comparing fig. 7A and 7B, when the own vehicle EV approaches the vulnerable road user VRU during the traveling of the own vehicle EV from right to left, there is a small magnitude of lateral avoidance operation in the optimized planned trajectory provided according to the above embodiment.

Fig. 8 is a schematic block diagram of a typical computer system that may be used to implement the above-mentioned apparatus for planning a vehicle travel track or an autonomous driving range controller. As shown in fig. 8, the computer system 80 includes a memory 810 (e.g., non-volatile memory such as flash memory, ROM, hard drives, magnetic disks, optical disks), a processor 820, and a computer program 830.

The memory 810 stores a computer program 830 that is executable by the processor 820. The processor 820 is configured to execute a computer program 830 stored on the memory 820. One or more steps involved in the methods described above with respect to fig. 1-6 may be implemented by running the computer program 830.

Fig. 9 is a schematic block diagram of an apparatus for planning a driving trajectory of a vehicle, which can be used to implement the above-mentioned automatic driving range controller. As shown in fig. 9, the apparatus 90 for planning a driving trajectory of a vehicle includes a sensing and predicting module 910 and a planning decision module 920.

The perception and prediction module 910 is configured to determine the type of the vulnerable road user in the direction of the ego-vehicle movement and the predicted movement trajectory of the vulnerable road user over the next time period.

Planning decision module 920 is configured to perform the following operations:

determining a potential activity area of the vulnerable road user in the next time period based on the type of the vulnerable road user and the predicted motion trail;

generating an avoidance transition region surrounding the potential activity region;

and selecting the candidate planning track with the minimum cost from a plurality of candidate planning tracks which can bypass the potential activity area and are related to the self vehicle in the next time period as the optimized planning track, wherein the candidate planning track which passes through the avoidance transition area has extra avoidance cost compared with the candidate planning track which does not pass through the avoidance transition area.

In addition to the features described above, the perception and prediction module 910 and the planning decision module 920 may be configured to have some or all of the features of the embodiments described above with respect to fig. 1-6.

According to another aspect of the present application, there is also provided a computer-readable storage medium, on which a computer program is stored which, when executed by a processor, may implement one or more of the steps comprised in the method described above with reference to fig. 1-6.

Computer-readable storage media, as referred to in this application, includes all types of computer storage media, which can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, computer-readable storage media may include RAM, ROM, EPROM, E2PROM, registers, hard disk, a removable disk, a CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other transitory or non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Combinations of the above should also be included within the scope of computer-readable storage media. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.

Those of skill in the art would understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.

To demonstrate interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Such functionality, whether implemented in hardware or software, depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

Although only a few specific embodiments of the present application have been described, those skilled in the art will appreciate that the present application may be embodied in many other forms without departing from the spirit or scope thereof. Accordingly, the present examples and embodiments are to be considered as illustrative and not restrictive, and various modifications and substitutions may be made therein without departing from the spirit and scope of the present application as defined by the appended claims.

The embodiments and examples set forth herein are presented to best explain the embodiments in accordance with the present technology and its particular application and to thereby enable those skilled in the art to make and utilize the application. However, those skilled in the art will recognize that the foregoing description and examples have been presented for the purpose of illustration and example only. The description as set forth is not intended to cover all aspects of the application or to limit the application to the precise form disclosed.

Claims

1. A method for planning a vehicle travel path, comprising the steps of:

determining the type of the vulnerable road user in the moving direction of the ego-vehicle and a predicted moving track of the vulnerable road user in a next time period;

2. The method of claim 1, wherein the step of determining the type of the vulnerable road user and the predicted movement trace comprises:

receiving environmental status data of the ego-vehicle;

determining the type and motion state of the vulnerable road user from the environmental state data;

3. The method of claim 2, wherein the vulnerable road user is one or more of: pedestrians, non-motorized vehicles and motorcycles, the state of motion of said vulnerable road user comprising one or more of the following: speed, acceleration, direction of motion, turn signal status, and historical motion profiles.

4. The method of claim 1, wherein the potential active and avoidance transition regions are represented by regions in an ST or SL graph.

5. The method of claim 4, wherein the step of generating an avoidance transition region comprises:

6. The method of claim 5, wherein the attribute value for each location decreases as the minimum distance between the location and the boundary of the potential activity area increases.

7. The method of any one of claims 1-6, wherein the step of selecting an optimized planned trajectory comprises:

8. The method of claim 7, wherein the additional back-off cost is a sum of contribution components of locations traversed by the candidate planned trajectory within the back-off transition region.

9. The method of claim 7, wherein the parameter of the cost function is determined based on at least one of a type, a motion state, a user setting, and a user driving history of the vulnerable road user.

10. The method of claim 7, wherein the planned trajectory is set to decrease a longitudinal speed of the ego-vehicle and increase a lateral distance from the vulnerable road user when approaching the vulnerable road user, and to increase the longitudinal speed of the ego-vehicle and decrease the lateral distance from the vulnerable road user when away from the vulnerable road user.

11. An apparatus for planning a vehicle travel trajectory, comprising:

a memory;

a processor coupled with the memory; and

a computer program stored on the memory and executable on the processor, the method of any one of claims 1-10 being implemented by executing the computer program.

12. An apparatus for planning a vehicle travel trajectory, comprising:

a planning decision module configured to perform the following operations:

13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-10.