WO2021088681A1

WO2021088681A1 - Long-distance flight-tracking method and device for unmanned aerial vehicle, apparatus, and storage medium

Info

Publication number: WO2021088681A1
Application number: PCT/CN2020/124052
Authority: WO
Inventors: 吕浩
Original assignee: 深圳市道通智能航空技术股份有限公司
Priority date: 2019-11-08
Filing date: 2020-10-27
Publication date: 2021-05-14
Also published as: CN110687923B; CN110687923A

Abstract

A long-distance flight-tracking method and device for an unmanned aerial vehicle, an apparatus, and a storage medium. The method comprises: acquiring, with respect to an unmanned aerial vehicle, a previous target waypoint corresponding to a previous time point, a queue of waypoints, and a current flight position corresponding to a current time point (S101); determining, from the queue of waypoints, and on the basis of the current flight position, a current target waypoint corresponding to the current time point (S102); generating, on the basis of a flight position information set associated with the unmanned aerial vehicle within a historical period and the current flight position in combination with a preset local planning algorithm, a local path from the current flight position to the current target waypoint, along which the unmanned aerial vehicle will fly (S103); and adding the local path to a previous global path corresponding to the previous time point, and obtaining a current global path corresponding to the current time point, such that the unmanned aerial vehicle flies along the current global path (S104). The invention combines a local planning algorithm and a global path, such that an unmanned aerial vehicle substantially flies along a preset path.

Description

UAV long-distance tracking flight method, device, equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 201911087651.8, and the application name is "UAV long-distance tracking flight method, device, equipment and storage medium" on November 8, 2019. The entire content is incorporated into this application by reference.

Technical field

The embodiments of the present invention relate to the technical field of unmanned aerial vehicles, and in particular to an unmanned aerial vehicle long-distance tracking flight method, device, equipment and storage medium.

Background technique

A practical application of drones is to fly along a fixed trajectory. For example, agricultural plant protection drones fly along a fixed trajectory to perform spraying tasks, and environmental detection drones fly along a fixed trajectory to inspect urban rivers. The executed trajectory is usually given by the user, or generated by other trajectory generation methods, such as identifying the river in the city through satellite images.

For the UAV flight planning system, a target location needs to be given. Due to the constraints of onboard computing performance, the planning system is all local planning, and long-distance global flight planning cannot be carried out. How to combine the ultra-long-distance preset trajectory and local flight motion planning so that the aircraft can fly according to the preset trajectory as a whole is a problem that needs to be solved.

Summary of the invention

The embodiments of the present invention provide a long-distance tracking flight method, device, equipment, and storage medium of an unmanned aerial vehicle to combine the ultra-long-distance preset trajectory and local planning algorithm, so that the aircraft can fly according to the preset trajectory as a whole. Realize long-distance global flight planning.

In the first aspect, an embodiment of the present invention provides a long-distance tracking flight method for an unmanned aerial vehicle, the method including:

Get the last target waypoint and waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment;

Determining the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position;

Based on the flight position information set of the drone in the historical time and the current flight position, combined with a preset local planning algorithm, the drone is generated to fly from the current flight position to the current target path point Local path;

The local path is added to the last global path corresponding to the last moment, and the current global path corresponding to the current moment is obtained, so that the UAV can fly along the current global path.

In the second aspect, an embodiment of the present invention also provides a long-distance tracking flying device for a UAV, which includes:

The information acquisition module is used to acquire the last target waypoint and the waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment;

A target determination module, configured to determine the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position;

The path generation module is used to generate the UAV to fly from the current flight position based on the flight position information set of the UAV in the historical time and the current flight position in combination with a preset local planning algorithm The local path of the current target path point;

The path adding module is used to add the local path to the previous global path corresponding to the last moment to obtain the current global path corresponding to the current moment, so that the UAV can fly along the current global path .

In a third aspect, an embodiment of the present invention also provides an unmanned aerial vehicle, which includes:

One or more processors;

Storage device for storing one or more programs;

The one or more programs are executed by the one or more processors, so that the one or more processors implement the long-distance tracking flight method of an unmanned aerial vehicle as described in the first aspect of the embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the drone according to the first aspect of the embodiment of the present invention is implemented. Long-distance tracking flight method.

The embodiment of the present invention determines the current target path point corresponding to the current time based on the current flight position corresponding to the current time of the drone, and combines the preset local planning algorithm to generate the drone to fly from the current flight position to the The local path of the current target path point finally makes the UAV fly to the end along the preset trajectory as a whole, effectively solving the problem of combining the local planning algorithm with the global path, and allowing the UAV to pass through the preset necessary points .

Description of the drawings

FIG. 1 is a schematic flowchart of a long-distance tracking flying method for a UAV according to Embodiment 1 of the present invention;

2 is a schematic flowchart of a long-distance tracking flight method for a UAV according to the second embodiment of the present invention;

Fig. 3 is an example flow chart of a method for long-distance tracking flight of a UAV according to the second embodiment of the present invention;

4 is a schematic structural diagram of a long-distance tracking flying device for a UAV according to the third embodiment of the present invention;

Fig. 5 is a schematic structural diagram of an unmanned aerial vehicle according to the fourth embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. In addition, it should be noted that, for ease of description, the drawings only show a part of the structure related to the present invention instead of all of the structure.

Example one

Fig. 1 is a schematic flow chart of a long-distance tracking flight method for a UAV according to the first embodiment of the present invention. This embodiment may be suitable for combining a local planning algorithm with a global path to make the UAV follow a preset overall path. In the case of the trajectory flying to the end point, the method can be executed by the UAV long-distance tracking flying device, which can be implemented by software and/or hardware, and can be integrated in the UAV.

It is understandable that for long-distance flight trajectory planning, when the preset waypoints reach a certain scale, the existing flight planning algorithm will not be able to generate a complete flight trajectory by taking all preset waypoints as constraints. , To realize the long-distance tracking flight of the UAV. The local planning algorithm can plan the flight trajectory or flight path of the UAV from the current flight position to the target position according to the set target position, and the flight trajectory or flight path can be composed of multiple continuous partial trajectories or partial paths. That is, it is achieved through multiple consecutive local motion planning or local path planning. The purpose of the embodiments of the present invention is to determine the unmanned person from the global path points corresponding to the previous time based on the current flight position of the UAV. The current target path point corresponding to the current time of the aircraft is selected, and the corresponding local planning algorithm is selected to generate a local path for the UAV to fly from the current flight position to the current target path point, thereby combining the local planning algorithm with the global path, and Continuously iterating the above process, so that the UAV can fly to the destination along the preset flight trajectory.

As shown in Fig. 1, the long-distance tracking flight method for drones provided in this embodiment specifically includes the following steps:

S101. Obtain the last target waypoint and the waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment.

Wherein, the last target path point refers to the flight destination corresponding to the last time determined for the drone. The path point queue refers to a queue formed by the coordinates of each known path point in the global path from the global start point to the global end point corresponding to the UAV at the previous moment. The current flying position is the coordinates of the space position the drone is currently flying to.

S102. Determine a current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position.

Wherein, the current target path point refers to the flight destination corresponding to the current moment determined for the drone.

It is understandable that the current target waypoint corresponding to the current moment is selected from the waypoint queue corresponding to the previous moment, and the last target waypoint corresponding to the previous moment is selected from the waypoint queue corresponding to the previous moment , And the path point queue corresponds to the path point coordinates in the global path, so the target path point corresponding to each moment is determined by continuous iteration until the determined target path point is the global path as the end point. The target waypoint corresponding to each moment is used as the flight destination of the drone at that moment. It must be the waypoint that the drone has not yet arrived at that moment and is expected to arrive. That is, the drone is based on The pre-determined target waypoint corresponding to this moment performs local path planning, and flies to the target waypoint corresponding to this moment; because the method described in the embodiment of the present invention is from the current flight position of the drone to the current target waypoint Perform local path planning, which means that the UAV only planned the path before the last target waypoint at the last moment, so that the UAV can seamlessly connect the subsequent flight when it reaches the last target waypoint. For missions, the new target waypoint can be determined before the UAV flies to the last target waypoint. Optionally, the new target waypoint is determined when the drone flies to the last target waypoint at a preset distance, that is, when the drone does not reach the preset distance, there is no need to determine The new target waypoint. At this time, the UAV's target waypoint is still the last target waypoint. Optionally, to determine the current target waypoint corresponding to the current moment, the distance between the current flying position of the drone and the last target waypoint can be used, and a distance threshold can be set, when the distance is less than the distance threshold , That is, the new target waypoint located after the last target waypoint is determined from the waypoint queue corresponding to the last moment; otherwise, the last target waypoint is also used as the current target waypoint corresponding to the current moment.

S103. Based on the flight position information set of the drone in the historical time and the current flight position, combined with a preset local planning algorithm, generate the drone to fly from the current flight position to the current target The local path of the waypoint.

Wherein, the flight position information set within the historical time can be understood as an information set composed of a continuous preset number of historical flight positions corresponding to the UAV before the current flight position. The local planning algorithm can be understood as a path planning algorithm for generating a flight path between two determined points. Optionally, the local planning algorithm determines the flight path between two determined points by generating multiple continuous local paths.

It is understandable that after the current target waypoint corresponding to the current moment is determined, a preset local planning algorithm can be combined to perform at least one local path planning between the current flight position and the current target waypoint to generate the current The flight path from the flight position to the current target path point.

During the drone's tracking flight, if an obstacle is encountered, the drone's local motion planning program will generate a new obstacle avoidance trajectory, but some scenes are very complicated, and the generated obstacle avoidance trajectory cannot guide the drone Surrounded by obstacles, it is necessary to start an additional global planner, and generate a temporary local path based on global information (that is, a map of obstacles in a certain area around the drone), so as to guide the aircraft out of obstacles . The state when the drone is trapped in an obstacle is determined to be the stagnant state, but it should be noted that the stagnant state of the drone does not mean that the speed of the drone is 0, because the aircraft can be in a certain state at this time. Irregular movement within the space, that is, trying in all directions, but it has been unable to continue to the next waypoint. Therefore, when performing local path planning, it is necessary to determine the current flight state of the UAV to determine whether the current flight state of the UAV is a stagnant state or a non-stagnation state.

Optionally, when the current flight state of the drone is a non-stagnation state, the first local planning algorithm corresponding to the non-stagnation state is selected to generate the drone to fly from the current flight position to the current For the local flight trajectory of the target path point, the first local planning algorithm is a local motion planning algorithm; when the current flight state of the UAV is the stagnant state, the second local planning algorithm corresponding to the stagnant state is selected to generate all The UAV flies from the current flight position to the local flight path of the current target path point, and the second local planning algorithm is a local path planning algorithm, such as a graph search algorithm.

It is understandable that the difference between the trajectory and the path is that the trajectory is the space position where the drone can actually fly out. The information of each point in the trajectory contains not only the spatial position information, but also the speed, acceleration and other information of the aircraft at that point. ; And the path is the space position that the UAV ideally flies to, and each point in the path only contains the space position information.

It should be noted that for the current moment, only one local path planning is performed in this step. The local path generated by the local path planning this time may be only a part of the corresponding flight path from the current flight position to the current target path point. Subsequent need to repeat at least one step of determining the current target path point and local path planning to complete the remaining part of the path planning.

S104. Add the local path to the last global path corresponding to the last moment, and obtain the current global path corresponding to the current moment, so that the UAV can fly along the current global path.

It can be understood that by adding the generated local path to the previous global path corresponding to the last moment, the current global path corresponding to the current moment is obtained, thereby realizing the update of the global path, and by iterating the embodiments of the present invention The process of the method can make the UAV fly along the corresponding trajectory of the initial global path as a whole, thereby realizing the long-distance tracking flight of the UAV.

Further, as an optional embodiment of the first embodiment, the optimization of the first embodiment further includes:

When the UAV starts to fly, the initial path point queue is determined based on the initial global path.

Wherein, the initial global path may be understood as a preset flight trajectory that the drone is expected to complete. Optionally, the initial global path includes the necessary points through which the drone is expected to fly.

Optionally, the determining the initial path point queue based on the initial global path includes:

Obtain the coordinates of all the sparse global path points in the initial global path, determine each of the coordinates as key point coordinates, and sequentially arrange the key points according to the order of the sparse global path points in the global path. Point coordinates are stored in the first queue; based on a preset sampling step, equidistant sampling between adjacent sparse global path points corresponding to each of the key point coordinates in the first queue, to obtain the initial global path Sampling path points; acquiring the sampling point coordinates corresponding to each of the sampling path points, and together with each of the key point coordinates, according to the order in which each of the sparse global path points and the sampling path points are arranged in the initial global path Stored in the second queue; determining the second queue as the initial waypoint queue.

Wherein, the sparse global path points can be understood as critical path points sparsely distributed on the initial global path. The preset sampling step length is used to perform equidistant sampling between adjacent sparse global path points to obtain the dense path points of the initial global path; optionally, the preset sampling step length may be based on the distribution of the initial global path The scene is determined. For scenes with dense obstacles, drones generally fly at low speeds, and the preset sampling step can be between 3 and 5 meters; for open scenes, such as farmland or grassland, the preset sampling step can be set to 10. Meter, the judgment of the scene can be set by the user before the drone starts flying.

Correspondingly, after generating the local path of the UAV from the current flight position to the current target path point, the method further includes:

The partial path is sampled based on the preset sampling step length, and the corresponding sampling result is obtained; if the sampling result includes a new sampling path point other than the current target path point, each of the A new sampled waypoint is added to the waypoint queue to obtain a new waypoint queue.

It is understandable that after the partial path is generated, if the partial path is longer than the preset sampling step, then the partial path is sampled based on the preset sampling step to obtain a new sample A waypoint, the new sampling waypoint can be added to the waypoint queue to update the waypoint queue.

The foregoing optional embodiment completes the initial determination process of the waypoint queue and the update process of the waypoint queue on the basis of the first embodiment.

Example two

FIG. 2 is a schematic flowchart of a long-distance tracking flight method for an unmanned aerial vehicle according to the second embodiment of the present invention. This embodiment is further optimized on the basis of the first embodiment. In this embodiment, the determination of the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position is embodied as: determining the distance between the current flight position and the previous target waypoint Corresponding first distance; when the first distance is less than a preset distance threshold, determine the next waypoint of the previous target waypoint in the waypoint queue as a candidate target waypoint, and determine the current The second distance corresponding to the flight position and the candidate target waypoint; acquiring the current local map corresponding to the UAV at the current moment, and determining that the candidate target waypoint is located in the obstacle of the current local map When the second distance is less than the radius of the current local map, the next waypoint of the candidate target waypoint is taken as the new candidate target waypoint, and the determination of the second distance is returned. Operation; otherwise, determine the candidate target waypoint as the current target waypoint corresponding to the current moment. When the first distance is greater than or equal to the preset distance threshold, the last target waypoint is determined as the current target waypoint corresponding to the current moment.

In this embodiment, based on the flight position information set of the UAV in the historical time and the current flight position, combined with a preset local planning algorithm, it is also generated to fly the UAV from the current flight position. The local path to the current target waypoint is embodied as: obtaining a set of historical time corresponding to the continuous preset number of history of the drone before the current flight position from the flight position information of the drone in the historical time Flight position, and determine the centroid position corresponding to each of the historical flight positions; determine the theoretical flight distance corresponding to the drone in the historical time based on the preset cruise speed of the drone; determine the current flight The third distance corresponding to the position to the center of mass position, and the ratio of the third distance to the theoretical flight distance; if the ratio is less than the preset ratio threshold, it is determined that the current flight state of the drone is stagnant State; otherwise, it is determined that the current flight state of the UAV is a non-stagnation state; if the current flight state of the UAV is a non-stagnation state, select the first local planning algorithm corresponding to the non-stagnation state to generate The drone flies from the current flight position to the first partial path of the current target path point; if the current flight state of the drone is the stagnant state, the second partial path corresponding to the stagnant state is selected A planning algorithm generates a second local path for the UAV to fly from the current flight position to the current target path point.

As shown in FIG. 2, the long-distance tracking flight method for drones provided in this embodiment specifically includes the following steps:

S201. Obtain the last target waypoint and the waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment.

S202. Determine a first distance corresponding to the current flight position and the last target waypoint.

Wherein, the first distance is the distance between the current flight position and the last target waypoint.

S203. Determine whether the first distance is less than a preset distance threshold; if so, perform S204; otherwise, perform S209.

Optionally, the preset distance threshold may be 3m.

S204: Determine a next waypoint of the previous target waypoint in the waypoint queue as a candidate target waypoint, and determine a second distance corresponding to the current flight position and the candidate target waypoint.

Wherein, the second distance is the distance between the current flight position and the candidate target waypoint.

S205. Obtain a current local map corresponding to the UAV at the current moment.

Wherein, the current local map may be understood as a local map constructed by the UAV at the current moment with the current flight position of the UAV (that is, the UAV itself) as the center. Optionally, the current local map includes coordinate information of the corresponding area, including coordinate information of obstacles.

It can be understood that when the first distance is less than the preset distance threshold, a new target waypoint needs to be determined as the current target waypoint. At this time, the waypoints after the last target waypoint can be selected in sequence from the waypoint queue as candidate target waypoints, and it is determined whether the determined candidate target waypoint can be used as the current target waypoint.

S206. Determine whether the candidate target waypoint is located within the obstacle range of the current local map and the second distance is less than the radius of the current local map; if yes, execute S207; otherwise, execute S208.

It is understandable that when determining whether the determined candidate target waypoint can be used as the current target waypoint, it can be first determined whether the candidate target waypoint is located within the obstacle range of the current local map. If it is, it cannot be The candidate target waypoint is determined as the current target waypoint, because the determined current target waypoint must avoid obstacles; in addition, it is necessary to determine the distance from the current flight position to the candidate target waypoint ( That is, whether the second distance) exceeds the radius of the current local map, if so, the candidate target waypoint cannot be determined as the current target waypoint. This is because once the second distance exceeds the radius , It means that the candidate target waypoint is outside the current local map range. At this time, the candidate target waypoint is uncontrollable. Therefore, whether the candidate target waypoint is located within the obstacle range of the current local map and the second distance is less than the radius of the current local map is used as whether the candidate target waypoint can be determined as the current target Judgement conditions for waypoints.

Optionally, the radius value may take a fixed empirical value, such as 10 m.

S207: Use the next waypoint of the candidate target waypoint as a new candidate target waypoint, and return to S204 to perform an operation of determining the second distance.

S208. Determine the candidate target waypoint as the current target waypoint corresponding to the current moment.

S209. Determine the last target waypoint as the current target waypoint corresponding to the current moment.

S210. Obtain a continuous preset number of historical flight positions corresponding to the current flight position of the UAV from the flight position information of the UAV in the historical time, and determine the corresponding historical flight position of each of the historical flight positions. The position of the center of mass.

Optionally, the mean coordinate point corresponding to each historical flight position is determined as the centroid position corresponding to each historical flight position.

S211: Determine a theoretical flight distance corresponding to the UAV in the historical time based on the preset cruise speed of the UAV.

Wherein, the preset cruise speed may be understood as the desired cruise speed of the drone set by the user before the drone starts to fly. The theoretical flight distance may be determined by the product of the preset cruise speed and the historical time.

S212. Determine a third distance corresponding to the current flying position to the center of mass position, and a ratio of the third distance to the theoretical flying distance.

Wherein, the third distance is the distance from the current flying position to the center of mass position.

S213. Determine whether the ratio is less than a preset ratio threshold, and if so, execute S214; otherwise, execute S216.

Optionally, the preset ratio threshold is set to 0.1.

It is understandable that when the ratio is less than the preset ratio threshold, it can be determined that the drone is in a stagnant state due to obstacles, otherwise, it can be determined that the drone is in a non-stagnant state.

Exemplarily, the flight position of the drone is recorded with the time interval T as the step length. For example, when T is 1, the flight position of the drone is recorded every 1s; the flight position obtained by the last N steps (that is, the preset number of historical flight positions) is stored in a buffer, for Calculate the mean point for all flight position points in the buffer

As the center of mass C; calculate the distance d between the current flight position P and the center of mass C; calculate the theoretical flight distance D=V*N*T the UAV flies in the time N*T, where the speed V is the expected cruise speed of the UAV , Generally also given by the user in advance; the calculation ratio p=d/D, if p<0.1, the UAV is considered to be in a stagnant state; otherwise, it is in a non-stable state.

S214: Determine that the current flight state of the drone is a stagnant state, and execute S215.

S215. Select a second local planning algorithm corresponding to the stagnant state, generate a second local path for the drone to fly from the current flight position to the current target path point, and execute S218.

Wherein, the second local path is a local flight path corresponding to the UAV flying from the current flight position to the current target path point.

S216. Determine that the current flight state of the drone is a non-stalled state.

S217. Select the first local planning algorithm corresponding to the non-stagnation state, generate a first local path for the UAV to fly from the current flight position to the current target path point, and execute S218.

Wherein, the first local path is a local flight trajectory corresponding to the UAV flying from the current flight position to the current target path point.

S218. Add the local path to the last global path corresponding to the last moment, and obtain the current global path corresponding to the current moment, so that the UAV can fly along the current global path.

Exemplarily, FIG. 3 shows an example flow chart of a method for long-distance tracking flight of an unmanned aerial vehicle according to the second embodiment of the present invention.

Example three

Fig. 4 is a schematic flowchart of a long-distance tracking flying device for a UAV according to the third embodiment of the present invention. This embodiment can be adapted to combine a local planning algorithm with a global path to make the UAV follow a preset In the case of the trajectory flying to the end point, the device can be implemented by software and/or hardware. The device specifically includes: an information acquisition module 401, a target determination module 402, a path generation module 403, and a path addition module 404.

The information acquisition module 401 is used to acquire the last target waypoint and the waypoint queue corresponding to the last time of the drone, and the current flight position corresponding to the current time;

The target determination module 402 is configured to determine the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position;

The path generation module 403 is configured to generate the UAV to fly from the current flight position based on the UAV’s flight position information set in the historical time and the current flight position in combination with a preset local planning algorithm. A local path to the current target path point;

The path adding module 404 is configured to add the local path to the previous global path corresponding to the last moment to obtain the current global path corresponding to the current moment, so that the drone follows the current global path flight.

On the basis of the foregoing embodiment, the device further includes:

The initial determination module is used to determine the initial path point queue based on the initial global path when the UAV starts to fly.

On the basis of the foregoing embodiment, the initial determination module includes:

The first sorting unit is configured to obtain the coordinates of all sparse global path points in the initial global path, determine each of the coordinates as key point coordinates, and arrange the sparse global path points in the global path according to Sequentially store the coordinates of each of the key points in the first queue;

The global sampling unit is configured to sample equidistantly between adjacent sparse global path points corresponding to each of the key point coordinates in the first queue based on a preset sampling step to obtain the sampling path of the initial global path point;

The second sorting unit is used to obtain the sampling point coordinates corresponding to each of the sampling path points, and together with each of the key point coordinates, according to the sparse global path points and the sampling path points in the initial global path The arrangement sequence is sequentially stored in the second queue;

The queue determining unit is configured to determine the second queue as the initial waypoint queue.

On the basis of the foregoing embodiment, the target determination module 402 includes:

A first distance determining unit, configured to determine a first distance corresponding to the current flight position and the last target waypoint;

The first distance determining unit is configured to determine the next waypoint of the previous target waypoint in the waypoint queue as a candidate target waypoint when the first distance is less than a preset distance threshold, and determine all the waypoints The second distance corresponding to the current flight position and the candidate target waypoint;

The first target determination unit is configured to obtain the current local map corresponding to the UAV at the current moment, and determine that the candidate target path point is located within the obstacle range of the current local map and the second When the distance is less than the radius of the current local map, the next waypoint of the candidate target waypoint is taken as the new candidate target waypoint, and the operation of determining the second distance is returned; otherwise, the candidate target The waypoint is determined as the current target waypoint corresponding to the current moment.

On the basis of the foregoing embodiment, the target determination module 402 further includes:

The second target determination unit is configured to determine the last target waypoint as the current target waypoint corresponding to the current moment when the first distance is greater than or equal to the preset distance threshold.

On the basis of the foregoing embodiment, the path generation module 403 includes:

The centroid determining unit is configured to obtain a set of historical flight positions corresponding to a continuous preset number of historical flight positions of the UAV before the current flight position from the flight position information of the UAV in the historical time, and determine each of the historical flight positions The position of the center of mass corresponding to the flight position;

The theoretical distance determining unit is configured to determine the theoretical flight distance corresponding to the UAV in the historical time based on the preset cruising speed of the UAV;

A ratio determining unit, configured to determine a third distance corresponding to the current flying position to the center of mass position, and the ratio of the third distance to the theoretical flying distance;

The state determining unit is configured to determine that the current flight state of the drone is a stagnant state if the ratio is less than a preset proportion threshold; otherwise, determine that the current flight state of the drone is a non-stagnant state;

The first path generation unit is configured to select the first local planning algorithm corresponding to the non-stagnation state if the current flight state of the UAV is in the non-stagnation state, and generate the UAV from the current flight position Fly to the first local path of the current target path point;

The second path generating unit is configured to select the second local planning algorithm corresponding to the stagnant state if the current flight state of the drone is in the stagnant state, and generate the drone to fly from the current flight position The second local path of the current target path point.

On the basis of the foregoing embodiment, the device further includes:

The local sampling unit is configured to sample the local path based on the preset sampling step after generating the local path of the UAV from the current flight position to the current target path point, and obtain Corresponding sampling results;

The queue update unit is configured to, if the sampling result contains new sampling path points other than the current target path point, add each of the new sampling path points to the path point queue to obtain a new path Click the queue.

The long-distance tracking flight device for drones provided by the embodiments of the present invention can execute the long-distance tracking flight method for drones provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

Example four

FIG. 5 is a schematic structural diagram of an unmanned aerial vehicle provided by Embodiment 4 of the present invention. As shown in FIG. 5, the unmanned aerial vehicle includes a processor 50, a memory 51, an input device 52, and an output device 53; The number of processors 50 can be one or more. In Figure 5, one processor 50 is taken as an example; the processor 50, memory 51, input device 52 and output device 53 in the drone can be connected by a bus or other means , Figure 5 takes the bus connection as an example.

As a computer-readable storage medium, the memory 51 can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (for example, no The information acquisition module 401, the target determination module 402, the path generation module 403, and the path addition module 404 in the human-machine long-distance tracking flight device). The processor 50 executes various functional applications and data processing of the UAV by running the software programs, instructions, and modules stored in the memory 51, that is, realizes the aforementioned UAV long-distance tracking flight method.

The memory 51 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the terminal, and the like. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some examples, the memory 51 may further include memories remotely provided with respect to the processor 50, and these remote memories may be connected to the drone through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 52 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the drone. The output device 53 may include a display device such as a display screen.

Example five

The fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, when the computer-executable instructions are executed by a computer processor, are used to execute a long-distance tracking flight method of a UAV, the method including:

Of course, a storage medium containing computer-executable instructions provided by an embodiment of the present invention is not limited to the method operations described above, and can also execute the drone pilot provided by any embodiment of the present invention. Related operations in the distance tracking flight method.

Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. . Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk. , Read-Only Memory (ROM), Random Access Memory (RAM), Flash memory (FLASH), hard disk or optical disk, etc., including several instructions to make a computer device (which can be a personal computer) , A server, or a network device, etc.) execute the method described in each embodiment of the present invention.

It is worth noting that in the above embodiments of the UAV long-distance tracking flight device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized That is, in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present invention.

Note that the above are only the preferred embodiments of the present invention and the applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made to those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention. The scope of is determined by the scope of the appended claims.

Claims

A long-distance tracking flight method of an unmanned aerial vehicle, which is characterized in that it includes:

Get the last target waypoint and waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment;

Determining the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position;

Based on the flight position information set of the drone in the historical time and the current flight position, combined with a preset local planning algorithm, the drone is generated to fly from the current flight position to the current target path point Local path;

The local path is added to the last global path corresponding to the last moment, and the current global path corresponding to the current moment is obtained, so that the UAV can fly along the current global path.
The method according to claim 1, further comprising:

When the UAV starts to fly, the initial path point queue is determined based on the initial global path.
The method according to claim 2, wherein the determining the initial path point queue based on the initial global path comprises:

Obtain the coordinates of all the sparse global path points in the initial global path, determine each of the coordinates as key point coordinates, and sequentially arrange the key points according to the order of the sparse global path points in the global path. The point coordinates are stored in the first queue;

Based on a preset sampling step size, equidistant sampling between adjacent sparse global path points corresponding to each of the key point coordinates in the first queue to obtain the sampling path points of the initial global path;

Obtain the sampling point coordinates corresponding to each of the sampling path points, and together with the key point coordinates, store them in the second order in the order of the sparse global path points and the sampling path points in the initial global path. queue;

The second queue is determined as the initial waypoint queue.
The method according to claim 1, wherein the determining the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position comprises:

Determine the first distance corresponding to the current flight position and the last target waypoint;

When the first distance is less than a preset distance threshold, determine the next waypoint of the previous target waypoint in the waypoint queue as a candidate target waypoint, and determine the current flight position and the candidate The corresponding second distance between the target path points;

Acquire the current local map corresponding to the UAV at the current moment, and determine that the candidate target path point is located within the obstacle range of the current local map and the second distance is less than the current local map When the radius is larger, take the next waypoint of the candidate target waypoint as the new candidate target waypoint, and return to perform the operation of determining the second distance; otherwise,

The candidate target waypoint is determined as the current target waypoint corresponding to the current moment.
The method according to claim 4, wherein when the first distance is greater than or equal to the preset distance threshold, the method further comprises:

The last target waypoint is determined as the current target waypoint corresponding to the current moment.
The method according to claim 1, wherein the unmanned aircraft is generated based on the flight position information set of the UAV in the historical time and the current flight position in combination with a preset local planning algorithm. The local path of the aircraft from the current flight position to the current target waypoint includes:

From the flight position information of the UAV in the historical time, the historical flight positions corresponding to the continuous preset number of the UAV before the current flight position are collectively acquired, and the centroid position corresponding to each historical flight position is determined ；

Determining the corresponding theoretical flight distance of the drone within the historical time based on the preset cruising speed of the drone;

Determining a third distance corresponding to the current flying position to the center of mass position, and the ratio of the third distance to the theoretical flying distance;

If the ratio is less than the preset ratio threshold, it is determined that the current flight state of the UAV is a stagnant state; otherwise, it is determined that the current flight state of the UAV is a non-stalled state;

If the current flight state of the drone is a non-stagnation state, select the first local planning algorithm corresponding to the non-stagnation state, and generate the drone to fly from the current flight position to the current target path point The first partial path;

If the current flight state of the drone is the stagnant state, the second local planning algorithm corresponding to the stagnant state is selected to generate the first flight of the drone from the current flight position to the current target path point Two local paths.
The method according to claim 3, characterized in that, after generating the local path of the UAV from the current flight position to the current target path point, the method further comprises:

Sampling the local path based on the preset sampling step, and obtaining a corresponding sampling result;

If the sampling result includes new sampling path points other than the current target path point, each of the new sampling path points is added to the path point queue to obtain a new path point queue.
A long-distance tracking flight device for UAV, which is characterized in that it comprises:

The information acquisition module is used to acquire the last target waypoint and the waypoint queue corresponding to the UAV at the last moment, and the current flight position corresponding to the current moment;

A target determination module, configured to determine the current target waypoint corresponding to the current moment from the waypoint queue based on the current flight position;

The path generation module is used to generate the UAV to fly from the current flight position based on the flight position information set of the UAV in the historical time and the current flight position in combination with a preset local planning algorithm The local path of the current target path point;

The path adding module is used to add the local path to the previous global path corresponding to the last moment to obtain the current global path corresponding to the current moment, so that the UAV can fly along the current global path .
An unmanned aerial vehicle, characterized in that it includes:

One or more processors;

Storage device for storing one or more programs;

The one or more programs are executed by the one or more processors, so that the one or more processors implement the long-distance tracking flight method of an unmanned aerial vehicle according to any one of claims 1-7.
A computer-readable storage medium with a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for long-distance tracking flight of a drone according to any one of claims 1-7 .