CN112987760A

CN112987760A - Trajectory planning method and device, storage medium and electronic equipment

Info

Publication number: CN112987760A
Application number: CN202110502855.4A
Authority: CN
Inventors: 夏华夏; 陈国胜; 任冬淳; �田润; 邢学韬; 王志超; 陈鸿帅; 张杨宇; 颜诗涛; 樊明宇
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-05-10
Filing date: 2021-05-10
Publication date: 2021-06-18
Anticipated expiration: 2041-05-10
Also published as: CN112987760B

Abstract

The specification discloses a trajectory planning method, a trajectory planning device, a storage medium and electronic equipment. The probability of collision between the unmanned equipment and each obstacle is determined through the predicted track of the obstacle and the track planned for the unmanned equipment, the obstacle is expanded according to the collision probability, the expanded volume of the obstacle with higher probability of collision with the unmanned equipment is larger, a sufficient avoidance space can be reserved for the unmanned equipment when the track is planned, the expanded volume of the obstacle with lower probability of collision with the unmanned equipment is smaller, and therefore a larger solution space is provided for the unmanned equipment when the track is planned.

Description

Trajectory planning method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a trajectory planning method and apparatus, a storage medium, and an electronic device.

Background

Currently, when controlling an unmanned device, a reference trajectory for a period of time in the future is usually planned for the unmanned device to guide the unmanned device to move according to the planned reference trajectory.

Since there are other obstacles in the movement space of the drone in addition to the drone itself, for example, there are obstacles on the road when the drone is traveling, and the drone is also confronted with flying birds or other drones in the air when the drone is traveling, when planning the reference trajectory for the drone, it is necessary to avoid each obstacle according to the movement state of each obstacle in addition to the movement target of the drone itself.

In the prior art, a motion track of an obstacle in a future period of time is usually predicted, a reference track of the unmanned device is planned with a goal that the unmanned device does not collide with the obstacle, and on the basis, in order to ensure driving safety, the unmanned device is often required not only to not collide with the volume of the obstacle, but also to uniformly expand the obstacle, and the reference track is planned with a goal that the unmanned device does not collide with the expanded volume of the obstacle.

The unified inflation process usually inflates all the obstacles at the same ratio or uniformly inflates all the obstacles outward for the same distance, but in practical applications, for an unmanned device, the probability of collision with each obstacle is different, so for an obstacle with a higher probability of collision with the unmanned device, the unified inflation cannot guarantee that the unmanned device and the obstacle have a sufficient avoidance distance, while the inflation space of an obstacle with a small probability of collision with the unmanned device can limit the range of motion of the unmanned device in the space, and the solution set in planning the trajectory for the unmanned device is too small.

Disclosure of Invention

The present specification provides a trajectory planning method, an apparatus, a storage medium, and an electronic device, to partially solve the above problems in the prior art.

The technical scheme adopted by the specification is as follows:

the present specification provides a trajectory planning method, including:

determining a pre-reference track of target equipment and a target prediction track of each obstacle;

for each obstacle, determining an expansion coefficient of the obstacle according to a target predicted track of the obstacle and a pre-reference track of target equipment, wherein the higher the probability that the obstacle and the target equipment are located at the same position at the same time, the higher the determined expansion coefficient of the obstacle is;

determining the expansion volume of the obstacle after expansion according to the expansion coefficient of the obstacle and the original volume of the obstacle;

and adjusting the pre-reference track of the target equipment according to the target reference track and the expansion volume of each obstacle, and taking the adjusted pre-reference track as the reference track of the target equipment.

Optionally, determining an expansion coefficient of the obstacle according to the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device, specifically including:

aiming at each future moment, determining a pre-reference track point of the target equipment at the future moment according to the pre-reference track of the target equipment, and determining a target prediction track point of the obstacle at the future moment according to the target prediction track of the obstacle;

and determining the expansion coefficient of the obstacle at the future time according to the target predicted track point of the obstacle at the future time and the pre-reference track point of the target device at the future time.

Optionally, determining a target predicted trajectory of each obstacle specifically includes:

for each obstacle, determining a base predicted trajectory of the obstacle, and an uncertainty of the obstacle;

and adjusting the basic predicted track of the obstacle according to the uncertainty of the obstacle, and taking the adjusted basic predicted track as the target predicted track of the obstacle.

Optionally, determining the uncertainty of the obstacle specifically includes:

determining the type of the obstacle according to the collected driving data of the obstacle; according to the preset corresponding relation between the type of the obstacle and the uncertainty of the obstacle, taking the uncertainty corresponding to the type of the obstacle as the uncertainty of the obstacle; and/or the presence of a gas in the gas,

obtaining a historical movement track of the obstacle and a historical prediction track for predicting the movement of the obstacle historically; and determining the uncertainty of the obstacle according to the difference between the historical predicted track and the historical motion track.

Optionally, determining the pre-reference trajectory of the target device specifically includes:

aiming at each future moment, determining a pre-reference track point of the target equipment at the future moment according to the pre-reference track of the target equipment;

adjusting the basic predicted trajectory of the obstacle according to the uncertainty of the obstacle, specifically comprising:

aiming at each basic predicted track point in the basic predicted track, determining a target predicted track point in a neighborhood range of the basic predicted track point according to the uncertainty of the obstacle;

aiming at each future moment, determining the probability that the barrier is positioned at each target predicted track point at the future moment according to the uncertainty of the barrier and each target predicted track point;

determining an expansion coefficient of the obstacle according to the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device, specifically comprising:

and determining the expansion coefficient of the obstacle at the future time according to the pre-reference track point of the target device at the future time and the probability that the obstacle is located at each target predicted track point at the future time.

Optionally, for each basic predicted trajectory point in the basic predicted trajectory, determining a target predicted trajectory point in a neighborhood range of the basic predicted trajectory point according to the uncertainty of the obstacle, specifically including:

aiming at each basic predicted track point in the basic predicted track, determining an uncertain range of a neighborhood of the basic predicted track point according to the uncertainty of the obstacle, and taking points contained in the uncertain range as target predicted track points of the obstacle at the future moment, wherein the larger the uncertainty of the obstacle is, the larger the determined uncertain range is;

for each future moment, determining the probability that the obstacle is located at each target predicted track point at the future moment according to the uncertainty of the obstacle and each target predicted track point, and specifically comprising:

and for each future moment, determining the probability that the obstacle is located at the target predicted track point at the future moment according to the distance between each target predicted track point and the basic predicted track point at the future moment, wherein the determined probability that the obstacle is located at the target predicted track point at the future moment is higher as the distance between the target predicted track point and the basic predicted track point at the future moment is shorter.

Optionally, determining the basic predicted trajectory of the obstacle specifically includes:

determining each basic prediction track of the obstacle, and taking the probability of the obstacle moving according to each basic prediction track as the movement probability corresponding to the basic prediction track;

according to the uncertainty of the obstacle and the predicted track points of the targets, the probability that the obstacle is located at each predicted track point of the targets at the future moment is determined, and the method specifically comprises the following steps:

for each basic prediction track, determining the motion probability corresponding to the basic prediction track as the motion probability of the target prediction track obtained after the basic prediction track is adjusted;

aiming at each target predicted track point, determining the motion probability of a target predicted track where the target predicted track point is located;

and determining the probability that the obstacle is positioned at the target predicted track point at the future moment according to the motion probability of the target predicted track where the target predicted track point is positioned and the probability that the obstacle is positioned at the target predicted track point at the future moment under the condition of motion of the obstacle along the basic predicted track where the basic predicted track point is positioned.

Optionally, after determining the probability that the obstacle is located at each target predicted trajectory point at the future time according to the uncertainty of the obstacle and each target predicted trajectory point, before determining the expansion coefficient of the obstacle according to the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device, the method further includes:

for each future moment, determining the probability that the distance between the target device and the obstacle at the future moment is greater than a preset safe distance according to the pre-reference track point of the target device at the future moment and the target predicted track point of the obstacle at the future moment, wherein the pre-reference track point is used as the safe probability of the target device relative to the obstacle at the future moment;

selecting the obstacles with the safety probability smaller than a preset probability threshold value at the future moment from all the obstacles as the appointed obstacles to be expanded;

and aiming at each specified obstacle at the future moment, determining the expansion coefficient of the specified obstacle at the future moment according to the pre-reference track point of the target device at each future moment and the probability that the specified obstacle is positioned at each target predicted track point at the future moment.

Optionally, determining an expanded volume of the obstacle after expansion according to the expansion coefficient of the obstacle and the original volume of the obstacle, specifically including:

determining the expansion distance of the obstacle in each preset expansion direction through a preset expansion algorithm according to the expansion coefficient of the obstacle, wherein the determined expansion distance is positively correlated with the expansion coefficient of the obstacle in each expansion direction;

the original volume of the obstacle is expanded in the corresponding expansion direction by the determined expansion distance.

This specification provides a trajectory planning device, including:

the track determining module is used for determining a pre-reference track of the target equipment and a target prediction track of each obstacle;

the coefficient determining module is used for determining the expansion coefficient of each obstacle according to the target predicted track of the obstacle and the pre-reference track of the target device, wherein the larger the probability that the obstacle and the target device are located at the same position at the same time, the larger the determined expansion coefficient of the obstacle is;

the expansion module is used for determining the expanded volume of the barrier after expansion according to the expansion coefficient of the barrier and the original volume of the barrier;

and the track adjusting module is used for adjusting the pre-reference track of the target equipment according to the target reference track and the expansion volume of each obstacle, and taking the adjusted pre-reference track as the reference track of the target equipment.

The present specification provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the trajectory planning method described above.

The present specification provides an unmanned aerial device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the trajectory planning method when executing the program.

The technical scheme adopted by the specification can achieve the following beneficial effects:

in the trajectory planning method provided by the present specification, the probability of collision between the unmanned aerial vehicle and each obstacle is determined by the predicted trajectory for the obstacle and the planned trajectory for the unmanned aerial vehicle, and the obstacle is expanded according to the collision probability, so that the expanded volume of the obstacle having a higher probability of collision with the unmanned aerial vehicle is also larger, and it is ensured that a sufficient avoidance space can be reserved for the unmanned aerial vehicle when the trajectory is planned, and the expanded volume of the obstacle having a lower probability of collision with the unmanned aerial vehicle is also smaller, thereby providing a larger solution space for the unmanned aerial vehicle when the trajectory is planned.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

fig. 1 is a schematic flow chart of a trajectory planning method in this specification;

FIG. 2 is a schematic flow chart of a method for adjusting a base predicted trajectory provided herein;

FIG. 3 is a schematic illustration of the expansion of an obstacle provided herein;

FIG. 4 is a schematic diagram of a trajectory planning apparatus provided herein;

fig. 5 is a schematic structural diagram of the unmanned aerial vehicle corresponding to fig. 1 provided in the present specification.

Detailed Description

Based on the recognition of the above problems, the present specification provides a trajectory planning method for determining the probability of collision between the unmanned aerial vehicle and each obstacle through a predicted trajectory for the obstacle and a planned trajectory for the unmanned aerial vehicle, expanding the obstacle according to the collision probability, and planning a reference trajectory under a condition that the expanded obstacle is avoided.

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a trajectory planning method in this specification, which specifically includes the following steps:

s100: a pre-reference trajectory of the target device is determined, as well as a target predicted trajectory for each obstacle.

The target device in this specification is an unmanned device, and the reference trajectory planned by the trajectory planning method provided in this specification is used to control the target device so as to guide the target device to move along the reference trajectory. In this embodiment of the present specification, the trajectory planning method provided in this specification may be executed by the target device itself, for example, an unmanned device or an unmanned aerial vehicle, or may be executed by a server or other electronic devices that can perform information transmission with the target device and control the target device, which is not limited in this specification. For convenience of description, the trajectory prediction method provided by the present specification is exemplarily described with a target device as an execution subject.

In the embodiment of the present specification, the target device may include an unmanned device moving on a plane, and an unmanned device moving in a three-dimensional space, where the movement of the unmanned device on the plane does not mean that the movement space of the unmanned device is two-dimensional, but means that the unmanned device can only complete movement based on a certain plane when moving in a motion manner inherent to the unmanned device, for example, a car can only move on the plane where a road is located.

For simplicity, in the following part of the present specification, a target device is taken as an unmanned device (hereinafter referred to as an unmanned vehicle) that moves only on a plane where a road is located, a trajectory planning method provided in the present specification is described, and the trajectory planning method is explained when the unmanned device (hereinafter referred to as an unmanned vehicle) that moves in a three-dimensional space needs to perform corresponding steps in other ways.

It should be noted that, when the target device described in this specification is an unmanned vehicle, the unmanned vehicle may include an autonomous vehicle and a vehicle having a driving assistance function. The unmanned vehicle may be a delivery vehicle applied to the delivery field. And when the target device in this specification is unmanned aerial vehicle, unmanned aerial vehicle can be for the delivery unmanned aerial vehicle in delivery field, especially can be applied to takeaway delivery.

In planning the trajectory of the unmanned vehicle, the obstacles considered are generally obstacles around the position where the unmanned vehicle is located, for example, obstacles 20 meters away from the unmanned vehicle, although any distance range may be considered as the surroundings of the unmanned vehicle. However, since the driving tendency of the unmanned vehicle is known, only an obstacle in the driving tendency direction of the unmanned vehicle (for example, an obstacle in front of the unmanned vehicle) may be considered, and an obstacle in the environment where the unmanned vehicle is located may be regarded as an obstacle around the unmanned vehicle, for example, each obstacle on the same road as the unmanned vehicle. It can be seen that there are many existing methods for selecting the obstacle, and this specification does not limit this.

And similarly, when the target device is unmanned aerial vehicle, what considered also can be the barrier around the position that unmanned aerial vehicle is located, nevertheless because unmanned aerial vehicle usually with fixed high navigation, consequently when the target device is unmanned aerial vehicle, can also not consider the barrier that height and unmanned aerial vehicle place height are greater than preset height distance threshold value of locating.

The driving data of each obstacle around the unmanned vehicle may be collected by a sensor installed on the unmanned vehicle, wherein the driving data may include inherent properties of the obstacle itself (such as shape, volume, type of the obstacle, etc.), and information of coordinates, time, speed, etc. of movement over a historical period of time, which is not limited by the present specification. When the trajectory planning method described in this specification is executed, it is necessary to predict the movement of each obstacle according to the collected driving data of each obstacle, and obtain the predicted trajectory of each obstacle in the future, that is, the target predicted trajectory.

In addition, a pre-reference trajectory needs to be determined for the unmanned vehicle according to the driving purpose of the unmanned vehicle, and it should be noted that the pre-reference trajectory does not directly guide the unmanned vehicle to drive, but serves as an optimization basis of the reference trajectory, that is, the reference trajectory obtained after the pre-reference trajectory is adjusted is a trajectory for guiding the unmanned vehicle to drive.

Generally speaking, a pre-reference trajectory within a first preset time period in the future may be determined for the unmanned vehicle, and a target predicted trajectory within a second preset time period in the future may be predicted for each obstacle, where the pre-reference trajectory and the target predicted trajectory may include where the unmanned vehicle and the obstacle travel along the corresponding trajectories, respectively. It should be noted that the first preset time period and the second preset time period may be the same or different, and the following part of this specification takes the first preset time period and the second preset time period as an example for description, that is, the predicted target trajectory of the obstacle is also the predicted trajectory of the obstacle in the first preset time period in the future.

In another embodiment of the present disclosure, the two types of trajectories may not be smooth curves, but may be a connection line of a plurality of sequential track points, that is, in this embodiment of the present disclosure, the predicted target trajectory for the obstacle may include predicted target predicted track points of the obstacle and predicted time of the predicted target track points of the obstacle route, and the pre-reference trajectory determined for the unmanned vehicle may include pre-reference track points determined for the unmanned vehicle and time of the predicted target track points of the unmanned vehicle route. For example only, in the following portions of this specification, the pre-reference trajectory of the unmanned vehicle may be a pre-reference trajectory point for each future time instant of the unmanned vehicle within a first predetermined time instant in the future, and the target predicted trajectory of the obstacle may be a target predicted trajectory point for each future time instant of the obstacle within the first predetermined time instant in the future.

In addition to the predicted future trajectory of the obstacle directly serving as the target predicted trajectory of the obstacle, the present specification provides a second mode of determining the target predicted trajectory of the obstacle according to the uncertainty of the obstacle, using the predicted future trajectory of the obstacle as a base predicted trajectory, and the flowchart is as shown in fig. 2:

s200: a base predicted trajectory for each obstacle is determined, as well as an uncertainty for each obstacle.

Those skilled in the art will appreciate that the obstacle traveling data collected by the unmanned vehicle may be acquired by any conventional technique, such as a Long Short-Term Memory (LSTM), the future movement track of the obstacle is predicted, but the prediction is limited by the existing track prediction technology, the predicted future track point of the obstacle usually has deviation with the real future movement track point of the obstacle, uncertainty can be used to describe the deviation between such predicted and observed results, and as the predicted future trajectory points of the obstacle generally deviate more from the actual future trajectory points of the obstacle, the more uncertain is the basic predicted trajectory for the predicted obstacle to be considered accurate, the greater the uncertainty of the obstacle, the greater the uncertainty in this description, which is the uncertainty in the accuracy of the prediction of the obstacle position.

Generally, such deviations may be inherent in the nature of the obstacle itself and may have a relationship with the type of obstacle. Compared with the case that the obstacle is an automobile, when the type of the obstacle is an electric bicycle, the deviation between the predicted future track point for the obstacle and the actual future movement track point of the obstacle is larger because the automobile is restrained by the lane when driving, and of course, the future refers to the future of the time when the obstacle track point is predicted in this case. Therefore, the uncertainty can be determined for each type of obstacle in advance, the type of the obstacle can be determined according to the driving data of the obstacle collected by the unmanned vehicle, and the uncertainty corresponding to the type of the obstacle can be used as the uncertainty of the obstacle.

Of course, the estimation may be performed by analyzing historical travel data of the obstacle without paying attention to the inherent attribute of the obstacle, specifically, a historical movement track of the obstacle, which is historically predicted by the unmanned vehicle, in a historical time period may be determined, the predicted historical movement track may be compared with a real movement track of the acquired obstacle in the historical time period, and the uncertainty of the obstacle may be determined according to a historical deviation between the real movement track of the acquired obstacle in the historical time period and the predicted historical movement track, and specifically, the larger the historical deviation is, the larger the uncertainty of the obstacle is.

S202: and aiming at each obstacle, adjusting the basic predicted track corresponding to the obstacle according to the uncertainty of the obstacle, and obtaining the probability that the obstacle is positioned at each target predicted track point at each future moment.

According to the method, the device and the system, the inaccuracy of the predicted track point of the obstacle can be described according to the uncertainty of the obstacle, furthermore, the basic predicted track of the predicted obstacle can be adjusted according to the uncertainty of the obstacle, and the probability that the obstacle is located at each target predicted track point at each future moment can be obtained.

Specifically, for each future moment, according to a pre-reference track of the target device, a pre-reference track point of the target device at the future moment is determined, and according to uncertainty of the obstacle, a target predicted track point of the obstacle in a neighborhood range of a basic predicted track point at the future moment is determined; and determining the probability that the barrier is positioned at each target predicted track point at the future moment according to the uncertainty of the barrier and each target predicted track point.

In this embodiment of the present specification, a neighborhood range of the determined basic predicted trajectory point at the future time may be used as an uncertainty range of the basic predicted trajectory point, that is, an inaccuracy degree of the predicted obstacle located at the basic predicted trajectory point is described, and a point included in the uncertainty range is used as a target predicted trajectory point of the obstacle at the future time. Similarly, the probability that the obstacle is located at the predicted target trajectory point at the future time may be considered to be higher as the predicted target trajectory point is closer to the predicted base trajectory point, and therefore, the probability that the obstacle is located at the predicted target trajectory point at the future time may be determined according to the distance between each predicted target trajectory point and the predicted base trajectory point at the future time, where the determined probability that the obstacle is located at the predicted target trajectory point at the future time is higher as the distance between the predicted target trajectory point and the predicted base trajectory point at the future time is closer.

In an embodiment of the present specification, for each obstacle, the probability distribution of the obstacle at each target predicted trajectory point at each future time is subjected to normal distribution in which the predicted trajectory points based on the future time are taken as a mean value, and the variance is positively correlated with the uncertainty of the obstacle.

Since the normal distribution can only represent the distribution of the positions of the obstacles in one dimension, in this embodiment of the present specification, in any one of the above manners, at each future time, the uncertainty of each obstacle in the direction of at least two linearly independent vectors is determined for each obstacle, and the position of the target predicted trajectory point of the obstacle in the corresponding direction is determined according to the position of the basic predicted trajectory point of the obstacle in the corresponding direction. Specifically, since the unmanned vehicle can be regarded as traveling on the two-dimensional plane of the road, a cartesian rectangular coordinate system can be constructed for the obstacle, in this case, the uncertainty in the x-axis direction and the uncertainty in the y-axis direction can be determined for the obstacle by any of the above-described manners, and the normal distribution of the positions of the obstacle in the x-axis direction at the future time can be determined according to the uncertainty in the x-axis direction of the obstacle, and similarly, the normal distribution of the positions of the obstacle in the y-axis direction at the future time can be determined according to the uncertainty in the y-axis direction of the obstacle, so as to obtain the probability distribution of the positions of the obstacle in the two-dimensional coordinate system at the future time. Of course, when the target device is a drone, the established coordinate system may be a three-dimensional coordinate system.

The second method for determining the target predicted trajectory provided in the present specification is not limited to determining the target predicted trajectory of the obstacle by any other conventional method. In the following part of the present specification, the target predicted trajectory is determined by the second method.

In addition, in an embodiment of the present specification, a plurality of basic predicted trajectories may be determined for each obstacle, and each basic predicted trajectory further corresponds to a motion probability of the obstacle moving along the basic predicted trajectory.

The predicted target trajectory determined in the above-described manner according to the present specification indicates the probability of being located at each predicted target trajectory point when the obstacle moves along the predicted target trajectory, and therefore, when it is known that the obstacle moves along the i-th entry mark predicted trajectory, the probability of collision of the obstacle with the unmanned vehicle under the condition that the obstacle moves along the i-th entry mark predicted trajectory can be determined for each future time

。

However, when the obstacle is inflated, it is not the conditional probability that the obstacle collides with the unmanned vehicle under the condition that the obstacle moves in a target predicted trajectory, but it is widely considered that the unmanned vehicle has the predicted trajectory movement of each target in all casesThe possibility of collision with the unmanned vehicle. Specifically, for an obstacle, the motion probability of the i-th item mark predicted track of the obstacle can be recorded as

The probability of collision between the obstacle and the unmanned vehicle is recorded as

. In the embodiment of the present specification, when a plurality of basic predicted trajectories are determined for each obstacle, the predicted trajectories may be recorded according to the probability of collision between the obstacle and the unmanned vehicle

The expansion coefficient at each future time instant is determined for the obstacle.

The above part of the present specification describes the trajectory planning method provided in the present specification by taking the target device as an unmanned vehicle as an example, but when the target device is another unmanned device, such as an unmanned aerial vehicle, the planned reference trajectory may also be determined according to the trajectory planning method provided in the present specification, and only the steps explained in the present specification need to be replaced.

S102: and for each obstacle, determining the expansion coefficient of the obstacle according to the target predicted track of the obstacle and the pre-reference track of the target device, wherein the higher the probability that the obstacle and the target device are at the same position at the same time, the higher the determined expansion coefficient of the obstacle is.

S104: and determining the expanded volume of the obstacle after expansion according to the expansion coefficient of the obstacle and the original volume of the obstacle.

In practical application, the distance between each obstacle around the unmanned vehicle and the unmanned vehicle is far and near, and it can be understood that at each future moment, the obstacle near the unmanned vehicle has a higher possibility of collision with the unmanned vehicle. For an obstacle with a greater possibility of collision with the unmanned vehicle, in the embodiment of the present specification, a greater expansion coefficient may be used to expand a greater volume for the obstacle, so that when a trajectory is planned with avoidance of the obstacle as a target, a greater space is reserved between the unmanned vehicle and the obstacle with a greater volume after expansion, thereby avoiding collision to a greater extent.

On the other hand, for the obstacle with low possibility of collision with the unmanned vehicle, the obstacle can be expanded by a small expansion coefficient, and the obstacle with small volume after expansion is obtained.

Specifically, the probability that the unmanned vehicle and the obstacle are located at the same position at the same time can be directly determined according to the number of intersection points between the target predicted trajectory of the obstacle and the pre-reference trajectory of the unmanned vehicle, for each future time, for each obstacle at the future time, since the probability distribution of the obstacle position is described in the target predicted trajectory point of the obstacle, the probability that the obstacle collides with the unmanned vehicle at the future time can be determined according to the target predicted trajectory point of the obstacle at the future time and the pre-reference trajectory point of the unmanned vehicle at the future time, thereby determining the expansion coefficient of the obstacle at the future time, and it can be seen that, for each obstacle, the expansion coefficient of the obstacle at each future time is determined according to the probability that the obstacle collides with the unmanned vehicle at the future time, that is, the expansion coefficients of the obstacle at a plurality of future times may be different, and the larger the probability of collision between the obstacle and the target device, the larger the determined expansion coefficient of the obstacle at the future time, and the larger the expansion volume of the obstacle after expansion at the future time.

In addition, in the embodiment of the present specification, when it is considered that the unmanned vehicle does not collide with an obstacle at a future time, the obstacle may be used as a safety obstacle at the future time, and the safety obstacle is not considered when a reference trajectory point at the future time, which is the future time, is planned for the unmanned vehicle, and certainly, the safety obstacle does not need to be expanded.

As follows, the present specification illustratively provides a manner of determining a safety barrier:

and for each future moment, according to the pre-reference track point of the target device at the future moment and the target predicted track point of the obstacle at the future moment, determining the probability that the distance between the target device and the obstacle at the future moment is greater than a preset safe distance, taking the probability as the safe probability of the obstacle at the future moment, selecting the obstacle with the safe probability less than a preset probability threshold value at the future moment from the obstacles to serve as a specified obstacle to be expanded, and taking the obstacle with the safe probability greater than the preset probability threshold value at the future moment from the obstacles as the safe obstacle.

Of course, any existing method may be used to select the designated obstacle and the safety obstacle from the obstacles, which is not limited in this specification.

As described above, in the above part of the present specification, when determining the collision probability between the unmanned vehicle and the obstacle, it is determined based on the criterion that whether the unmanned vehicle and the obstacle are at the same position at the same time, that is, if it is determined that the unmanned vehicle and the obstacle are at the same position at a certain future time, the unmanned vehicle collides with the unmanned vehicle at the future time, but it is known to those skilled in the art that the trajectory point where the unmanned vehicle and the obstacle are located refers to the position coordinates where the center points of the unmanned vehicle and the obstacle are located, and in practical application, both the unmanned vehicle and the obstacle have an inherent volume, and therefore, in the embodiment of the present specification, the criterion that whether the unmanned vehicle and the obstacle are at the same position at the same time is not determined based on the criterion that the center points of the unmanned vehicle and the obstacle are at the same position at the same time, but based on the volume of the acquired obstacle and the volume of the unmanned vehicle itself acquired in advance, and judging whether any point on the inherent volume of the unmanned vehicle and any point on the inherent volume of the barrier are at the same position at the same time, and when any point on the inherent volume of the unmanned vehicle and any point on the inherent volume of the barrier are at the same position at the same time, considering that the unmanned vehicle and the barrier are at the same position at the same time as a standard, namely the unmanned vehicle collides with the barrier.

Generally speaking, when the target device is an unmanned vehicle, the unmanned vehicle can be considered to move on a two-dimensional plane of a road, and therefore, whether the unmanned vehicle and the obstacle are at the same position can be determined only according to the projection shapes of the unmanned vehicle and the obstacle on the two-dimensional plane.

Similarly, when the obstacle is expanded, only the shape of the obstacle may be expanded without expanding the obstacle in the height direction, and in this case, the shape of the obstacle before the expansion may be the original shape of the obstacle, and the shape of the obstacle after the expansion may be the expanded shape of the obstacle. For example, fig. 3 illustrates a method for expanding the shape of the obstacle by this expansion method, specifically, a cartesian coordinate system may be established for the obstacle, and the expansion distance x 'in the x-axis direction and the expansion distance y' in the y-axis direction of the obstacle are determined according to the expansion coefficient of the obstacle, and then, the obstacle is expanded in the x-direction of the original shape of the obstacle as illustrated by the solid line in the positive direction and the negative direction respectively toward the x-axis, and the obstacle is expanded in the y-direction in the positive direction and the negative direction respectively toward the y-axis, and the expanded shape of the obstacle as illustrated by the expanded dotted line is obtained.

As described above, according to the preset expansion direction for the obstacle, any existing algorithm may be used to determine the expansion distance of the obstacle in each expansion direction, and expand the original shape of the obstacle in the corresponding expansion direction by the determined expansion distance, where in each expansion direction, the expansion distance in the expansion direction determined according to the expansion coefficient is positively correlated with the expansion coefficient. It should be noted that, the above is only exemplarily described by only expanding the shape of the obstacle on the two-dimensional plane, and in this specification, the expansion direction may include any direction in the three-dimensional space in which the target device moves, and this specification does not limit this.

In addition, when predicted trajectories are determined for a plurality of bases for each obstacle, the determined trajectories are determined based on the inflation method as described above

The larger the expansion coefficient determined for the obstacle at the future time, the larger the expansion coefficient determined for the obstacle, and on the basis of this, the uncertainty of the obstacle may also be based on

The determination of the expansion coefficient is carried out, in particular, as

The larger the determined obstacle, the larger the coefficient of expansion at that future time. Further, it can be determined

In the same situation as in the case of the above,

the smaller the coefficient of expansion determined for the obstruction. At this time, can be respectively based on

And

to determine two kinds of expansion coefficients of the obstacle, and then determine the expansion coefficient of the obstacle at the future time by the preset expansion weight, of course, any other method can be adopted according to the above

And

the coefficient of expansion of the obstacle is determined and is not limited by the present specification.

S106: and adjusting the pre-reference track of the target equipment according to the target reference track and the expansion volume of each obstacle, and taking the adjusted pre-reference track as the reference track of the target equipment.

According to the expanded volume of each obstacle after expansion, the pre-reference trajectory of the target device can be optimized by taking avoidance of the obstacle as a target, in the embodiment of the specification, when the target device is an unmanned vehicle, the unmanned vehicle can be considered to move on a two-dimensional plane of a road, so that the pre-reference trajectory of the unmanned vehicle can be adjusted by taking the target that the adjusted reference trajectory curve does not coincide with the position of any obstacle as a target, and the specification provides two methods as follows:

the first method is that for each future moment, in a range with a preset optimization distance as a radius and with a pre-reference track point of target equipment at the future moment as a circle center, the reference track point of the target equipment at the future moment is determined by taking the minimum sum of probabilities of being at the same position with each obstacle at the future moment as a target.

Secondly, for each obstacle, according to the speed of the obstacle and the speed of the target device, a corresponding constraint boundary is determined for the obstacle, a space which is surrounded by the constraint boundaries and contains the unmanned vehicle is obtained and serves as a constraint set corresponding to the target time, and for each future time, a reference track point located in the constraint set is determined for the unmanned vehicle.

Thereafter, a reference track formed by the reference track points determined in any of the above manners can be determined. When the reference trajectory is determined according to the second method, the present specification exemplarily proposes a determination method of the constraint boundary, specifically, it may be determined whether a distance between the obstacle and the target device has a tendency of decreasing under the action of a relative speed between the unmanned vehicle and the obstacle, if so, a hyperplane taking a vector perpendicular to a speed direction of the obstacle as a normal vector is determined as a candidate hyperplane corresponding to the obstacle, if not, a hyperplane taking a vector perpendicular to a speed direction of the target device as a normal vector is determined as a candidate hyperplane corresponding to the obstacle, and the constraint boundary corresponding to the obstacle is selected from the candidate hyperplanes corresponding to the obstacle.

It should be noted that, in any of the above determining manners of the constraint boundaries, the whole of the target device and the obstacle that are divided into a certain two-dimensional space by the determined corresponding constraint boundary are all located in the two-dimensional space where the track point is located, and it does not happen that the certain target device or the obstacle is divided into two non-intersecting two-dimensional spaces.

Obviously, when the constraint boundaries are known as the slopes of straight lines, numerous straight lines satisfying the above conditions can be determined, and any one of the straight lines can be selected as the constraint boundary corresponding to the obstacle, which is not limited in this specification.

It should be noted that, in the embodiment of the present specification, a constraint boundary corresponding to an obstacle is determined according to any mode, the constraint boundary divides a space where a target device and the obstacle are located into two disjoint parts, and the obstacle is divided into a part different from the target device by the corresponding constraint boundary.

Therefore, when the constraint boundary is determined in the above manner, it may not be possible to determine the constraint boundary that satisfies the above condition, and taking the constraint boundary determined in the above third manner as an example, when the candidate hyperplane corresponding to the obstacle satisfies the above condition, the candidate hyperplane is taken as the target hyperplane of the obstacle, and the constraint boundary corresponding to the obstacle is selected from the target hyperplanes corresponding to the obstacle. When none of the candidate hyperplanes corresponding to the obstacle satisfies the above condition, the constraint boundary corresponding to the obstacle may not be selected from the candidate hyperplanes, but the constraint boundary corresponding to the obstacle may be determined according to the direction of the relative speed between the obstacle and the target device, specifically, a hyperplane whose vector perpendicular to the direction of the relative speed between the obstacle and the target device is a normal vector may be determined as the constraint boundary of the obstacle, and the constraint boundary corresponding to the obstacle may also be determined according to the boundary of the obstacle, for example, a hyperplane including a boundary point of the obstacle closest to the target device may be determined as the constraint boundary of the obstacle. It can be seen that the determination method of the constraint boundary is various, and any existing method may be used to determine the constraint boundary, which is not described in detail below in this specification. In addition, when the target device is unmanned aerial vehicle, for the hyperplane of the restraint boundary that the barrier around unmanned aerial vehicle confirmed, this hyperplane normal vector direction can point to the pre-reference track point at unmanned aerial vehicle place.

Obviously, when determining the constraint boundaries for each obstacle, if the slope of the constraint boundaries is known, numerous straight lines satisfying the above conditions may be determined as the constraint boundaries for the obstacle, but in an optimization problem, it is generally desirable to solve in a larger solution set space and reflect the solution in the two-dimensional plane, that is, determining the constraint boundaries for more targets based on the constraint set surrounded by the constraint boundaries when the slope is determined, and at this time, for each candidate hyperplane corresponding to the obstacle, according to the pre-reference trajectory point of the target device, determining the distance between the candidate hyperplane and the pre-reference trajectory point of the target device, and selecting the candidate hyperplane with the farthest distance from the pre-reference trajectory point of the target device from the candidate hyperplane corresponding to the obstacle as the constraint boundary corresponding to the obstacle.

Based on the trajectory planning method shown in fig. 1, the probability of collision between the unmanned aerial vehicle and each obstacle is determined through the predicted trajectory for the obstacle and the planned trajectory for the unmanned aerial vehicle, and the obstacle is expanded according to the collision probability, so that the expanded volume of the obstacle with higher probability of collision with the unmanned aerial vehicle is larger, a sufficient avoidance space can be reserved for the unmanned aerial vehicle when the trajectory is planned, and the expanded volume of the obstacle with lower probability of collision with the unmanned aerial vehicle is smaller, thereby providing a larger solution space for the unmanned aerial vehicle when the trajectory is planned.

In addition, in an embodiment of the present specification, a plurality of basic predicted trajectories may be determined for each obstacle, and each basic predicted trajectory further corresponds to a movement probability of the obstacle moving along the basic predicted trajectory, and of course, after the corresponding target predicted trajectory is determined, the movement probability of the basic predicted trajectory may be used as the movement probability of the target predicted trajectory corresponding to the basic predicted trajectory, where each target predicted trajectory represents a probability distribution of positions of the obstacle under a condition of moving along the target predicted trajectory.

Based on the same idea, the trajectory planning method provided in one or more embodiments of the present specification further provides a corresponding trajectory planning device, as shown in fig. 4.

Fig. 4 is a schematic diagram of a trajectory planning apparatus provided in this specification, the apparatus including: track determination module, coefficient determination module, inflation module and track adjustment module, wherein:

a trajectory determination module 400, configured to determine a pre-reference trajectory of the target device and a target predicted trajectory of each obstacle;

a coefficient determining module 402, configured to determine, for each obstacle, an expansion coefficient of the obstacle according to a target predicted trajectory of the obstacle and a pre-reference trajectory of a target device, where the determined expansion coefficient of the obstacle is larger when a probability that the obstacle and the target device are located at the same position at the same time is larger;

an expansion module 404, configured to determine an expanded volume of the obstacle after expansion according to the expansion coefficient of the obstacle and the original volume of the obstacle;

and a track adjusting module 406, configured to adjust a pre-reference track of the target device according to the target reference track and the expansion volume of each obstacle, and use the adjusted pre-reference track as a reference track of the target device.

Optionally, the coefficient determining module 402 is specifically configured to, for each future time, determine a pre-reference trajectory point of the target device at the future time according to the pre-reference trajectory of the target device, and determine a target predicted trajectory point of the obstacle at the future time according to the target predicted trajectory of the obstacle; and determining the expansion coefficient of the obstacle at the future time according to the target predicted track point of the obstacle at the future time and the pre-reference track point of the target device at the future time.

Optionally, the trajectory adjusting module 406 is specifically configured to, for each obstacle, determine a base predicted trajectory of the obstacle and an uncertainty of the obstacle; and adjusting the basic predicted track of the obstacle according to the uncertainty of the obstacle, and taking the adjusted basic predicted track as the target predicted track of the obstacle.

Optionally, the trajectory adjusting module 406 is specifically configured to determine the type of the obstacle according to the collected driving data of the obstacle; according to the preset corresponding relation between the type of the obstacle and the uncertainty of the obstacle, taking the uncertainty corresponding to the type of the obstacle as the uncertainty of the obstacle; and/or acquiring a historical movement track of the obstacle and a historical prediction track for predicting the movement of the obstacle historically; and determining the uncertainty of the obstacle according to the difference between the historical predicted track and the historical motion track.

Optionally, the track adjusting module 406 is specifically configured to, for each future time, determine a pre-reference track point of the target device at the future time according to the pre-reference track of the target device; aiming at each basic predicted track point in the basic predicted track, determining a target predicted track point in a neighborhood range of the basic predicted track point according to the uncertainty of the obstacle; aiming at each future moment, determining the probability that the barrier is positioned at each target predicted track point at the future moment according to the uncertainty of the barrier and each target predicted track point; and determining the expansion coefficient of the obstacle at the future time according to the pre-reference track point of the target device at the future time and the probability that the obstacle is located at each target predicted track point at the future time.

Optionally, the trajectory adjusting module 406 is specifically configured to, for each basic predicted trajectory point in the basic predicted trajectory, determine an uncertainty range of a neighborhood of the basic predicted trajectory point according to uncertainty of the obstacle, and use a point included in the uncertainty range as a target predicted trajectory point of the obstacle at the future time, where the greater the uncertainty of the obstacle, the greater the determined uncertainty range is; and for each future moment, determining the probability that the obstacle is located at the target predicted track point at the future moment according to the distance between each target predicted track point and the basic predicted track point at the future moment, wherein the determined probability that the obstacle is located at the target predicted track point at the future moment is higher as the distance between the target predicted track point and the basic predicted track point at the future moment is shorter.

Optionally, the trajectory determining module 400 is specifically configured to determine each basic predicted trajectory of the obstacle, and a probability of the obstacle moving according to each basic predicted trajectory, as a motion probability corresponding to the basic predicted trajectory; the trajectory adjustment module 406 is specifically configured to, for each basic predicted trajectory, determine a motion probability corresponding to the basic predicted trajectory as a motion probability of a target predicted trajectory obtained after the basic predicted trajectory is adjusted; aiming at each target predicted track point, determining the motion probability of a target predicted track where the target predicted track point is located; and determining the probability that the obstacle is positioned at the target predicted track point at the future moment according to the motion probability of the target predicted track where the target predicted track point is positioned and the probability that the obstacle is positioned at the target predicted track point at the future moment under the condition of motion of the obstacle along the basic predicted track where the basic predicted track point is positioned.

Optionally, after determining the probability that the obstacle is located at each target predicted trajectory point at the future time according to the uncertainty of the obstacle and each target predicted trajectory point, before determining the expansion coefficient of the obstacle according to the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device, the trajectory determination module 400 is specifically configured to determine, for each future time, the probability that the distance between the target device and the obstacle at the future time is greater than a preset safe distance according to the pre-reference trajectory point of the target device at the future time and the target predicted trajectory point of the obstacle at the future time, as the safe probability of the target device relative to the obstacle at the future time; selecting the obstacles with the safety probability smaller than a preset probability threshold value at the future moment from all the obstacles as the appointed obstacles to be expanded; the coefficient determining module 402 and the expansion module 404 are specifically configured to, for each specified obstacle at the future time, determine an expansion coefficient of the specified obstacle at the future time according to the pre-reference trajectory point of the target device at each future time and the probability that the specified obstacle is located at each target predicted trajectory point at the future time.

Optionally, the expansion module 404 is specifically configured to determine, according to the expansion coefficient of the obstacle, an expansion distance of the obstacle in each preset expansion direction through a preset expansion algorithm, where in each expansion direction, the determined expansion distance is positively correlated with the expansion coefficient of the obstacle; the original volume of the obstacle is expanded in the corresponding expansion direction by the determined expansion distance.

The present specification also provides a computer-readable storage medium having stored thereon a computer program operable to execute the trajectory planning method provided in fig. 1 above.

The present specification also provides a schematic structural diagram of the drone shown in fig. 5. As shown in fig. 5, at the hardware level, the drone includes a processor, an internal bus, a memory, and a non-volatile memory, although it may also include hardware needed for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the trajectory planning method provided in fig. 1.

Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A trajectory planning method, comprising:

2. The method of claim 1, wherein determining the expansion coefficient of the obstacle based on the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device comprises:

3. The method of claim 1, wherein determining a target predicted trajectory for each obstacle comprises:

4. The method of claim 3, wherein determining the uncertainty of the obstruction comprises:

5. The method of claim 3, wherein determining the pre-reference trajectory of the target device specifically comprises:

6. The method according to claim 5, wherein determining, for each base predicted trajectory point in the base predicted trajectory, a target predicted trajectory point within a neighborhood range of the base predicted trajectory point according to the uncertainty of the obstacle comprises:

7. The method of any one of claims 5-6, wherein determining the base predicted trajectory of the obstacle comprises:

8. The method of claim 5, wherein after determining a probability that the obstacle is located at each of the target predicted trajectory points at the future time based on the uncertainty of the obstacle and the target predicted trajectory points, and before determining the expansion coefficient of the obstacle based on the target predicted trajectory of the obstacle and the pre-reference trajectory of the target device, the method further comprises:

9. The method of claim 1, wherein determining an expanded volume of the obstacle after expansion based on the coefficient of expansion of the obstacle and the original volume of the obstacle comprises:

10. A trajectory planning device, characterized in that the device specifically comprises:

11. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 9.

12. An unmanned aerial device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of any of claims 1-9.