Aircraft motion state decision method and device, electronic equipment and storage medium

Abstract

The application provides an aircraft motion state decision method and device, electronic equipment and a storage medium. The method comprises: acquiring a current motion state of an aircraft and an obstacle position of an obstacle; generating a route plan of the aircraft according to the current motion state and the obstacle position, the route plan comprising a plurality of trajectory points; determining, by a simulator, a simulated motion state of the aircraft at each trajectory point and a corresponding simulated power; and determining a target motion state of the aircraft according to the simulated motion state, the simulated power and the obstacle position, the target motion state comprising at least one of a target speed or a target yaw angle. The above scheme determines the target motion state based on the power and the obstacle position, which can ensure that the aircraft neither collides nor runs out of power when reaching the target position, thereby improving the safety of the aircraft.

Description

Technical Field

[0001] This application relates to the field of control methods, and more particularly to a method, apparatus, electronic device, and storage medium for making decisions on the motion state of an aircraft. Background Technology

[0002] With the development of electric technology, building an urban air transport network centered on lightweight electric vertical takeoff and landing (eVTOL) aircraft has become a powerful path for developing new dimensions of urban space. eVTOL aircraft, with their vertical takeoff and landing advantages, do not require runways, thus adapting to various environments, including urban environments.

[0003] With the development of autonomous driving technology, its application can effectively improve the operating efficiency of eVTOL aircraft and reduce user operations. Users only need to input the target location information into the eVTOL aircraft, which can automatically observe the environment, determine the flight route based on the observation results and the target location information, and fly towards the target location according to the flight route.

[0004] In practical applications, the motion states of an eVTOL aircraft include: during the takeoff phase, the eVTOL aircraft flies vertically from the ground to a preset altitude; during the cruise phase, the eVTOL aircraft flies at a preset altitude; and during the landing phase, the eVTOL aircraft flies from a preset altitude to the ground.

[0005] At the same time, the safety of eVTOL aircraft relying entirely on autopilot is a key concern. Summary of the Invention

[0006] This application provides a method, apparatus, electronic device, and storage medium for making decisions on the motion state of an aircraft, thereby improving the safety of the aircraft.

[0007] In a first aspect, this application provides a method for determining the motion state of an aircraft, comprising: acquiring the current motion state of the aircraft and the position of an obstacle; generating a route plan for the aircraft based on the current motion state and the position of the obstacle, the route plan including multiple trajectory points; determining the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point using a simulator; and determining the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the position of the obstacle, the target motion state including at least one of the following: target speed or target yaw angle.

[0008] In one possible implementation, generating a route plan for the aircraft based on the current motion state and the obstacle position includes: obtaining the target position of the aircraft and multiple preset times; and generating a route plan for the aircraft based on the current motion state, the obstacle position, the target position, and the multiple preset times.

[0009] In one possible implementation, the current motion state includes at least one of the following: current position, current speed, or current yaw angle; generating a route plan for the aircraft based on the current motion state, the obstacle position, the target position, and the plurality of preset times includes: generating a flight path for the aircraft based on the current position, the obstacle position, and the target position; generating a trajectory point of the aircraft on the flight path at each preset time based on the current speed, the current yaw angle, the flight path, and the plurality of preset times; and determining the route plan for the aircraft based on the flight path and the trajectory point.

[0010] In one possible implementation, the simulated motion state and corresponding simulated battery level of the aircraft at each trajectory point are determined using a simulator, including: obtaining the current battery level of the aircraft; inputting the current motion state and the route plan into the simulator to obtain the simulated motion state of the aircraft at each trajectory point; and inputting the current motion state, the simulated motion state, and the current battery level into the simulator to obtain the simulated battery level corresponding to the trajectory point of the simulated motion state.

[0011] In one possible implementation, determining the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the obstacle position includes: establishing a value function corresponding to each trajectory point based on the simulated motion state, the simulated battery level, and the obstacle position; updating the initial motion state decision model based on a reinforcement learning algorithm until the value function corresponding to the trajectory point of the simulated motion state converges, thus obtaining an updated motion state decision model; and determining the target motion state through the updated motion state decision model.

[0012] In one possible implementation, for any trajectory point, a value function corresponding to the trajectory point is established based on the simulated motion state, the simulated battery level, and the obstacle position, including: acquiring the power information of the aircraft; determining the simulated battery consumption of the aircraft flying from the trajectory point to the target position based on the simulated motion state and the power information; establishing a battery reward function for the trajectory point based on the difference between the simulated battery level and the simulated battery consumption; determining trajectory points in a cruising flight state from the trajectory points; establishing an obstacle reward function for the trajectory points in the cruising flight state based on the obstacle position; and establishing a value function corresponding to the trajectory point based on the battery reward function and the obstacle reward function.

[0013] In one possible implementation, determining the simulated power consumption of the aircraft flying from the trajectory point to the target location based on the simulated motion state and the power information includes: determining the flight duration of the aircraft flying from the trajectory point to the target location based on the simulated motion state, the flight duration including a first duration of cruise flight and a second duration of vertical flight; and determining the simulated power consumption of the aircraft flying from the trajectory point to the target location based on the flight duration and the power information.

[0014] In one possible implementation, the power information includes cruise flight power and vertical flight power; determining the simulated power consumption of the aircraft from the trajectory point to the target position based on the flight duration and the power information includes: determining the cruise power consumption of the aircraft based on the cruise flight power and the first duration; determining the vertical power consumption of the aircraft based on the vertical flight power and the second duration; and determining the cruise power consumption and the vertical power consumption as the simulated power consumption.

[0015] In one possible implementation, determining the obstacle reward function for the trajectory point of the cruise flight state based on the obstacle position includes: determining a first distance between the trajectory point of the cruise flight state and the obstacle based on the obstacle position; and establishing the obstacle reward function for the trajectory point of the cruise flight state based on the first distance.

[0016] In one possible implementation, determining the target motion state through the updated motion state decision model includes: acquiring the observed motion state and observed battery level of the aircraft at any position; and inputting the observed motion state, the observed battery level, and the obstacle position into the updated motion state decision model to obtain the target motion state.

[0017] Secondly, this application provides an aircraft motion state decision-making device, comprising: an acquisition module for acquiring the current motion state of the aircraft and the obstacle position of an obstacle; a generation module for generating a route plan for the aircraft based on the current motion state and the obstacle position, the route plan including multiple trajectory points; a simulation module for determining the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point using a simulator; and a determination module for determining the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the obstacle position, the target motion state including at least one of the following: target speed or target yaw angle.

[0018] In one possible implementation, the generation module is specifically used to obtain the target position of the aircraft and multiple preset times; the generation module is also specifically used to generate a route plan for the aircraft based on the current motion state, the obstacle position, the target position and the multiple preset times.

[0019] In one possible implementation, the current motion state includes at least one of the following: current position, current speed, or current yaw angle; the generation module is specifically configured to generate the flight path of the aircraft based on the current position, the obstacle position, and the target position; the generation module is further configured to generate the trajectory points of the aircraft in the flight path at each preset time based on the current speed, the current yaw angle, the flight path, and the plurality of preset times; the generation module is further configured to determine the route planning of the aircraft based on the flight path and the trajectory points.

[0020] In one possible implementation, the device further includes: a simulation module for acquiring the current battery level of the aircraft; the simulation module is further configured to input the current motion state and the route plan into the simulator to obtain the simulated motion state of the aircraft at each trajectory point; the simulation module is further configured to input the current motion state, the simulated motion state, and the current battery level into the simulator to obtain the simulated battery level corresponding to the trajectory point corresponding to the simulated motion state.

[0021] In one possible implementation, the device further includes: a decision module, configured to establish a value function corresponding to each trajectory point based on the simulated motion state, the simulated charge, and the obstacle position; the decision module is further configured to update the initial motion state decision model based on a reinforcement learning algorithm until the value function corresponding to the trajectory point of the simulated motion state converges, thereby obtaining an updated motion state decision model; the decision module is further configured to determine the target motion state through the updated motion state decision model.

[0022] In one possible implementation, for any trajectory point; the decision module is specifically configured to acquire the power information of the aircraft; the decision module is further configured to determine the simulated power consumption of the aircraft flying from the trajectory point to the target position based on the simulated motion state and the power information; the decision module is further configured to establish a power reward function for the trajectory point based on the difference between the simulated power consumption and the simulated power consumption corresponding to the trajectory point; the decision module is further configured to determine the trajectory point in the cruise flight state from the trajectory points; the decision module is further configured to establish an obstacle reward function for the trajectory point in the cruise flight state based on the obstacle position; the decision module is further configured to establish a value function corresponding to the trajectory point based on the power reward function and the obstacle reward function.

[0023] In one possible implementation, the decision module is specifically configured to determine the flight time of the aircraft from the trajectory point to the target position based on the simulated motion state, the flight time including a first duration of cruise flight and a second duration of vertical flight; the decision module is further configured to determine the simulated power consumption of the aircraft from the trajectory point to the target position based on the flight time and the power information.

[0024] In one possible implementation, the power information includes cruise flight power and vertical flight power; the decision module is specifically configured to determine the cruise power consumption of the aircraft based on the cruise flight power and the first duration; the decision module is further configured to determine the vertical power consumption of the aircraft based on the vertical flight power and the second duration; the decision module is further configured to determine the cruise power consumption and the vertical power consumption as the simulated power consumption.

[0025] In one possible implementation, the decision module is specifically configured to determine a first distance between the trajectory point of the cruise flight state and the obstacle based on the obstacle's location; the decision module is further configured to establish an obstacle reward function for the trajectory point of the cruise flight state based on the first distance.

[0026] In one possible implementation, the decision module is specifically used to acquire the observed motion state and observed battery level of the aircraft at any position; the decision module is also specifically used to input the observed motion state, the observed battery level, and the obstacle position into the updated motion state decision model to obtain the target motion state.

[0027] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in any one of the first aspects.

[0028] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which are executed by a processor as described in any one of the first aspects.

[0029] The aircraft motion state decision-making method, apparatus, electronic device, and storage medium provided in this application include: acquiring the current motion state of the aircraft and the obstacle positions; generating a route plan for the aircraft based on the current motion state and the obstacle positions, the route plan including multiple trajectory points; determining the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point using a simulator; and determining the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the obstacle positions, the target motion state including at least one of the following: target speed or target yaw angle. This solution, by determining the target motion state based on battery level and obstacle positions, can ensure that the aircraft neither collides nor lacks sufficient battery power to reach the target position, thereby improving the safety of the aircraft. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0031] Figure 1 This is a schematic diagram illustrating an application scenario of an aircraft motion state decision-making method provided in an embodiment of this application.

[0032] Figure 2A flowchart illustrating an aircraft motion state decision-making method provided in an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the generated route planning provided in an embodiment of this application;

[0034] Figure 4 A flowchart illustrating an aircraft motion state decision-making method provided in an embodiment of this application;

[0035] Figure 5 A schematic diagram of the flight status provided in the embodiments of this application;

[0036] Figure 6 This is a schematic diagram of the training of the motion state decision model provided in an embodiment of this application;

[0037] Figure 7 A schematic diagram of the structure of an aircraft motion state decision device provided in an embodiment of this application;

[0038] Figure 8 A schematic diagram of the structure of an aircraft motion state decision-making device provided in an embodiment of this application;

[0039] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0040] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0041] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0042] Figure 1 This is a schematic diagram illustrating an application scenario of an aircraft motion state decision-making method provided in this application embodiment. Using the illustrated scenario as an example: the user specifies a target location, and the aircraft determines an initial route plan from its current location to the target location. If the initial route plan cannot be realized due to obstacles or insufficient power, the aircraft determines its actual location and a modified route plan from its current location to the actual location. Flying according to the modified route plan ensures the aircraft's safety.

[0043] The technical solutions of this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In the description of this application, unless otherwise expressly specified and limited, the terms should be broadly understood within the art. The embodiments of this application will now be described with reference to the accompanying drawings.

[0044] Figure 2 This application provides a flowchart illustrating a method for determining the motion state of an aircraft, which includes the following steps:

[0045] S201. Obtain the current motion status of the aircraft and the location of obstacles.

[0046] As an example, the executing entity of this embodiment can be an aircraft motion state decision-making device, which can be implemented in various ways. For example, it can be program software, or a medium storing relevant computer programs, such as a USB flash drive; or, the device can also be a physical device that integrates or installs relevant computer programs, such as a chip, a smart terminal, a computer, a server, etc.

[0047] The current motion state is obtained by actual detection of the actual state of the aircraft and changes with the current flight plan of the aircraft. The obstacles in this application are fixed obstacles within the range between the current position of the aircraft and the target position, and the position of the obstacles does not change.

[0048] Optionally, the current motion state includes at least one of the following: current position, current speed, or current yaw angle.

[0049] It should be noted that the obstacles in this application are obstacles that the aircraft needs to avoid during cruise flight.

[0050] S202. Based on the current motion state and the location of the obstacle, generate a route plan for the aircraft, the route plan including multiple trajectory points.

[0051] For example, if an aircraft has a limited flight altitude, it may encounter obstacles at that altitude, and the route planning should avoid these obstacles.

[0052] Below, in conjunction with Figure 3 The process of generating the route plan is explained.

[0053] Figure 3 This is a schematic diagram of the generated route planning provided in an embodiment of this application. Figure 3As shown, there are obstacles between the aircraft's current position and the target position. The generated route plan avoids the obstacles. The aircraft will not collide with the obstacles during its flight according to the route plan. The multiple positions that the aircraft passes through during its flight according to the route plan are trajectory points.

[0054] S203. Using a simulator, determine the simulated motion state of the aircraft at each trajectory point and the corresponding simulated battery level.

[0055] Among them, the simulated motion state and simulated power are predicted by the simulator based on the current motion state of the aircraft. The simulator predicts the simulated motion state and the corresponding simulated power when the aircraft flies to each trajectory point in the future.

[0056] Optionally, the simulator can obtain the simulated motion state of the aircraft at each trajectory point and the corresponding simulated electrical charge through simulation calculations.

[0057] S204. Based on the simulated motion state, the simulated battery level, and the obstacle position, determine the target motion state of the aircraft, wherein the target motion state includes at least one of the following: target speed or target yaw angle.

[0058] The simulated battery level is predicted by the simulator, which predicts the remaining battery level of the aircraft when it reaches each trajectory point in the future, based on the aircraft's power.

[0059] Optionally, if the aircraft's simulated battery power is insufficient to fly to the target position, the target position is adjusted so that the aircraft's simulated battery power is sufficient to fly to the target position.

[0060] Alternatively, a preset safe distance exists between the target location and the obstacle.

[0061] It is understandable that by combining the target's motion state with the battery level and the location of obstacles, it is possible to ensure that the aircraft does not collide with other aircraft and to prevent the aircraft from crashing due to insufficient battery power, thereby improving the safety of the aircraft.

[0062] The aircraft motion state decision-making method provided in this application includes: acquiring the current motion state of the aircraft and the obstacle positions; generating a route plan for the aircraft based on the current motion state and the obstacle positions, the route plan including multiple trajectory points; determining the simulated motion state and corresponding simulated battery level of the aircraft at each trajectory point using a simulator; and determining the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the obstacle positions, the target motion state including at least one of the following: target speed or target yaw angle. This scheme, by determining the target motion state based on battery level and obstacle positions, can ensure that the aircraft neither collides nor lacks sufficient battery power to reach the target position, thereby improving the safety of the aircraft.

[0063] Based on any of the above embodiments, the following, in conjunction with Figure 4 This section provides a detailed explanation of the decision-making process for the aircraft's motion state.

[0064] Figure 4 This is a flowchart illustrating an aircraft motion state decision-making method provided in an embodiment of this application. Figure 4 As shown, the method includes:

[0065] S401, Obtain the current motion status of the aircraft and the location of obstacles.

[0066] It should be noted that the execution process of S401 is the same as that of S201, and will not be repeated here.

[0067] S402, Obtain the target position of the aircraft and multiple preset times.

[0068] The methods for obtaining the preset time include, but are not limited to: being specified by the engineer, being randomly generated, and being generated according to a fixed time interval.

[0069] S403. Generate the flight path of the aircraft based on the current position, the position of the obstacle, and the position of the target.

[0070] Optionally, the aircraft's flight path is a route that connects the current position and the target position, while avoiding each obstacle position.

[0071] S404. Based on the current speed, the current yaw angle, the flight path, and the multiple preset times, generate the trajectory points of the aircraft on the flight path at each preset time.

[0072] Optionally, the trajectory point is the position reached by the aircraft at each preset time during its flight along the flight path, and the trajectory point is calculated.

[0073] S405. Determine the route plan for the aircraft based on the flight path and the trajectory points.

[0074] Optionally, the flight path and trajectory points can be combined to obtain a route plan.

[0075] S406. Obtain the current battery level of the aircraft.

[0076] Optionally, the current battery level can be obtained through the aircraft's battery detection function.

[0077] S407. Input the current motion state and the route plan into the simulator to obtain the simulated motion state of the aircraft at each trajectory point.

[0078] The simulator provides a simulation environment, which can acquire high-dimensional abstract information about the aircraft and simulate the aircraft's state based on this information.

[0079] In a scenario example, to avoid obstacles, the aircraft's flight path is a curve. As the aircraft flies along the curve, its position, speed, and yaw angle all change. The simulator can calculate the simulated motion state of the aircraft at each of the trajectory points.

[0080] S408. Input the current motion state, the simulated motion state, and the current battery level into the simulator to obtain the simulated battery level corresponding to the trajectory point of the simulated motion state.

[0081] In a scenario example, an aircraft consumes power during flight. A simulator can calculate the remaining power when the aircraft passes each trajectory point and define the remaining power as the simulated power.

[0082] S409. Based on the simulated motion state, the simulated charge, and the obstacle position, establish a value function corresponding to each trajectory point.

[0083] One feasible implementation involves establishing a value function corresponding to the trajectory point, including: acquiring the power information of the aircraft; determining the simulated power consumption of the aircraft flying from the trajectory point to the target position based on the simulated motion state and the power information; establishing a power reward function for the trajectory point based on the difference between the simulated power consumption and the simulated power consumption; establishing an obstacle reward function for the trajectory point based on the obstacle position; and establishing a value function corresponding to the trajectory point based on the power reward function and the obstacle reward function.

[0084] Optionally, the value function R can be defined as follows:

[0085] R = a1R1 + a2R2 + a3R3 + a4R4

[0086] Where R is the value function, R1 is the reward function for reaching the intermediate point, R2 is the reward function for reaching the target position, R3 is the collision penalty function, R4 is the power penalty function, and a1, a2, a3 and a4 are weighting coefficients.

[0087] In a scenario example, multiple intermediate points are determined based on the aircraft's route planning. These intermediate points are located between the starting and target positions. Each time the aircraft passes an intermediate point, the corresponding intermediate point reward function value is increased. Upon reaching the target position, the target position reward function value is increased. If a collision occurs during flight, the corresponding collision penalty function value is deducted. If the aircraft's battery is insufficient to reach the target position, the corresponding battery penalty function value is deducted. It can be understood that a1 and a2 are greater than 0, and a1 and a2 are less than 0.

[0088] Alternatively, determining the obstacle reward function for the trajectory point includes: determining a first distance between the trajectory point and the obstacle based on the obstacle's position; and establishing an obstacle reward function for the trajectory point based on the first distance.

[0089] In terms of scenario examples, the greater the distance, the closer the aircraft is to the obstacle, the safer the aircraft is, and the higher the value of the reward function.

[0090] Alternatively, the value function may also include a reward function for the aircraft reaching each trajectory point and a reward function for the aircraft reaching the target position.

[0091] Specifically, one feasible implementation involves determining the simulated power consumption of the aircraft from the trajectory point to the target location based on the simulated motion state and the power information. This includes: determining the flight duration of the aircraft from the trajectory point to the target location based on the simulated motion state, wherein the flight duration includes a first duration for cruise flight and a second duration for vertical flight; and determining the simulated power consumption of the aircraft from the trajectory point to the target location based on the flight duration and the power information.

[0092] Below, in conjunction with Figure 5 The flight status is described.

[0093] Figure 5 This is a schematic diagram of the flight state provided for an embodiment of this application. Figure 5 As shown, the aircraft ascends from the starting position in a vertical flight state to transition point 1, then flies horizontally from transition point 1 in a cruise flight state to transition point 2, and finally descends from transition point 2 in a vertical flight state to the target position.

[0094] In this feasible implementation method, since the operating conditions of cruise flight and vertical flight are different, the simulated power consumption is obtained by calculating the power consumption of cruise and vertical flight respectively, and the calculation results are more accurate.

[0095] Furthermore, in one feasible implementation, the power information includes cruise flight power and vertical flight power; determining the simulated power consumption of the aircraft from the trajectory point to the target position based on the flight duration and the power information includes: determining the cruise power consumption of the aircraft based on the cruise flight power and the first duration; determining the vertical power consumption of the aircraft based on the vertical flight power and the second duration; and determining the cruise power consumption and the vertical power consumption as the simulated power consumption.

[0096] Optionally, power consumption can be calculated based on power and time.

[0097] For example, the formula for calculating cruise power P1 is:

[0098]

[0099] Where W is the weight of the aircraft, V v Let V be the vertical velocity component of the aircraft, V be the forward velocity of the aircraft, L / D be the lift drag of the aircraft, and η1 be the energy conversion efficiency of the aircraft during cruise flight.

[0100] The formula for calculating the cruise flight battery power E1 is:

[0101]

[0102] Where t is the first duration.

[0103] To illustrate with a scenario example, the power consumption of the aircraft at each moment of cruise flight is integrated to obtain the total electricity consumed during cruise flight.

[0104] For example, the formula for calculating vertical flight power P2 is:

[0105]

[0106] Where f is the correction factor for the aircraft's own interference, FoM is the ratio of ideal rotor power to actual rotor power, A is the rotor disk area, ρ is the air density, and V climb,v η is the climb rate of the aircraft, and η2 is the energy conversion efficiency of the aircraft during vertical flight.

[0107] Similarly, the power consumption for vertical flight can be calculated based on the vertical flight power P2.

[0108] S410. Based on the reinforcement learning algorithm, the initial motion state decision model is updated until the value function corresponding to the trajectory point of the simulated motion state converges, thus obtaining the updated motion state decision model.

[0109] In a scenario example, the initial motion state decision model is trained by simulating the motion state of each trajectory point until the value function corresponding to the trajectory point converges, at which point the training stops.

[0110] Optionally, a maximum number of training rounds can be set, and training will stop if the maximum number of training rounds is reached.

[0111] Below, in conjunction with Figure 6 The training of the motion state decision model is explained.

[0112] Figure 6 This is a schematic diagram illustrating the training of the motion state decision model provided in an embodiment of this application. Figure 6 As shown, the simulated motion state corresponding to the trajectory point is determined, the initial model is trained based on the corresponding simulated motion state, and the value function corresponding to the trajectory point is established. If the value function converges or the training reaches the maximum number of rounds, the training stops; otherwise, the next trajectory point is determined and the above operation is performed.

[0113] Alternatively, the evaluation parameters of the reinforcement learning algorithm can be calculated, and the trained motion state decision model can be evaluated using these parameters.

[0114] S411. Obtain the observed motion state and observed battery level of the aircraft at any position.

[0115] In the context of the scenario, the observed motion state and the observed battery level are obtained by actual measurement when the aircraft flies to any position.

[0116] S412. Input the observed motion state, the observed electrical charge, and the obstacle position into the updated motion state decision model to obtain the target motion state.

[0117] Optionally, the observed motion state, observed charge level, and obstacle position are input into the updated motion state decision model to obtain the target speed and target yaw angle of the aircraft output by the updated motion state decision model. The aircraft then adjusts its control according to the target speed and target yaw angle to fly.

[0118] Figure 7 This is a schematic diagram of the structure of an aircraft motion state decision-making device provided in an embodiment of this application. Figure 7 As shown, the aircraft motion state decision-making device 70 may include: an acquisition module 71, a generation module 72, a simulation module 73, and a determination module 74, wherein,

[0119] The acquisition module 71 is used to acquire the current motion state of the aircraft and the position of the obstacles.

[0120] The generation module 72 is used to generate a route plan for the aircraft based on the current motion state and the position of the obstacle. The route plan includes multiple trajectory points.

[0121] The simulation module 73 is used to determine the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point using a simulator.

[0122] The determining module 74 is used to determine the target motion state of the aircraft based on the simulated motion state, the simulated battery level, and the obstacle position. The target motion state includes at least one of the following: target speed or target yaw angle.

[0123] Optionally, module 71 can be executed. Figure 2 S201 in the embodiment.

[0124] Optionally, the generation module 72 can be executed. Figure 2 S202 in the embodiment.

[0125] Optionally, simulation module 73 can execute Figure 2 S203 in the embodiment.

[0126] Optionally, module 74 can be executed. Figure 2 S204 in the embodiment.

[0127] It should be noted that the aircraft motion state decision-making device shown in the embodiments of this application can execute the technical solutions shown in the above method embodiments, and its implementation principle and beneficial effects are similar, so they will not be described again here.

[0128] In one possible implementation, the generation module 72 is specifically used for:

[0129] Obtain the target position of the aircraft and multiple preset times;

[0130] Based on the current motion state, the obstacle position, the target position, and the multiple preset times, a route plan for the aircraft is generated.

[0131] In one possible implementation, the current motion state includes at least one of the following: current position, current speed, or current yaw angle; the generation module 72 is specifically used for:

[0132] The flight path of the aircraft is generated based on the current position, the position of the obstacle, and the target position;

[0133] Based on the current speed, the current yaw angle, the flight path, and the multiple preset times, generate the trajectory points of the aircraft on the flight path at each preset time;

[0134] Based on the flight path and the trajectory points, the route plan for the aircraft is determined.

[0135] Figure 8 This is a schematic diagram of the structure of an aircraft motion state decision-making device provided in an embodiment of this application. Figure 7 Based on the illustrated embodiments, as Figure 8 As shown, the aircraft motion state decision-making device 80 further includes: a simulation module 75 and a decision-making module 76, wherein:

[0136] The simulation module 75 is used for:

[0137] Obtain the current battery level of the aircraft;

[0138] The current motion state and the route plan are input into the simulator to obtain the simulated motion state of the aircraft at each trajectory point;

[0139] The current motion state, the simulated motion state, and the current battery level are input into the simulator to obtain the simulated battery level corresponding to the trajectory point of the simulated motion state.

[0140] The decision module 76 is used for:

[0141] Based on the simulated motion state, the simulated battery level, and the obstacle position, a value function is established for each trajectory point.

[0142] Based on the reinforcement learning algorithm, the initial motion state decision model is updated until the value function corresponding to the trajectory point of the simulated motion state converges, and the updated motion state decision model is obtained.

[0143] The target motion state is determined by the updated motion state decision model.

[0144] In one possible implementation, the decision module 76 is specifically used for:

[0145] Obtain the power information of the aircraft;

[0146] Based on the simulated motion state and the power information, the simulated power consumption of the aircraft from the trajectory point to the target position is determined;

[0147] Based on the difference between the simulated power consumption and the simulated power consumption corresponding to the trajectory point, a power reward function for the trajectory point is established.

[0148] Determine the trajectory points for cruise flight from the aforementioned trajectory points;

[0149] Based on the location of the obstacle, establish the obstacle reward function for the trajectory point;

[0150] A value function corresponding to the trajectory point is established based on the power reward function and the obstacle reward function corresponding to the trajectory point.

[0151] In one possible implementation, the decision module 76 is specifically used for:

[0152] Based on the simulated motion state, the flight time of the aircraft from the trajectory point to the target position is determined, and the flight time includes a first time for cruise flight and a second time for vertical flight.

[0153] Based on the flight duration and the power information, the simulated power consumption of the aircraft from the trajectory point to the target location is determined.

[0154] In one possible implementation, the power information includes cruise flight power and vertical flight power; the decision module 76 is specifically used for:

[0155] The power consumption of the aircraft during cruise is determined based on the cruise flight power and the first duration.

[0156] The vertical power consumption of the aircraft is determined based on the vertical flight power and the second duration.

[0157] The power consumption during cruise and the power consumption during vertical movement are determined as the simulated power consumption.

[0158] In one possible implementation, the decision module 76 is specifically used for:

[0159] Based on the location of the obstacle, determine the first distance between the trajectory point of the cruise flight state and the obstacle;

[0160] Based on the first distance, an obstacle reward function is established for the trajectory points of the cruise flight state.

[0161] In one possible implementation, the decision module 76 is specifically used for:

[0162] The observed motion state and observed battery level of the aircraft at any location are obtained;

[0163] The observed motion state, the observed electrical charge, and the obstacle position are input into the updated motion state decision model to obtain the target motion state.

[0164] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 9 As shown, the electronic device includes:

[0165] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 can invoke logical instructions stored in the memory 292 to execute the methods of the above embodiments.

[0166] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0167] The memory 292, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, thereby implementing the methods in the above-described method embodiments.

[0168] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.

[0169] This application provides a non-transitory computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods described in the foregoing embodiments.

[0170] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0171] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0172] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining the motion state of an aircraft, characterized in that, include: Obtain the current motion state of the aircraft and the position of obstacles; Based on the current motion state and the location of the obstacle, a route plan for the aircraft is generated, and the route plan includes multiple trajectory points; The simulator is used to determine the simulated motion state of the aircraft at each trajectory point and the corresponding simulated battery level. Based on the simulated motion state, the simulated battery level, and the obstacle position, a value function is established for each trajectory point. Based on the reinforcement learning algorithm, the initial motion state decision model is updated until the value function corresponding to the trajectory point of the simulated motion state converges, and the updated motion state decision model is obtained. The target motion state is determined by the updated motion state decision model, and the target motion state includes at least one of the following: target speed or target yaw angle; Specifically, for any trajectory point, a value function is established based on the simulated motion state, the simulated battery level, and the obstacle position, including: Obtain the power information of the aircraft; Based on the simulated motion state, the flight time of the aircraft from the trajectory point to the target position is determined, and the flight time includes a first time for cruise flight and a second time for vertical flight. Based on the flight duration and the power information, the simulated power consumption of the aircraft from the trajectory point to the target location is determined; Based on the difference between the simulated power consumption and the simulated power consumption corresponding to the trajectory point, a power reward function for the trajectory point is established. Determine the trajectory points for cruise flight from the aforementioned trajectory points; Based on the location of the obstacle, establish an obstacle reward function for the trajectory points of the cruise flight state; Based on the power reward function and the obstacle reward function, a value function corresponding to the trajectory point is established.

2. The method according to claim 1, characterized in that, Based on the current motion state and the location of the obstacle, a route plan for the aircraft is generated, including: Obtain the target position of the aircraft and multiple preset times; Based on the current motion state, the obstacle position, the target position, and the multiple preset times, a route plan for the aircraft is generated.

3. The method according to claim 2, characterized in that, The current motion state includes at least one of the following: current position, current speed, or current yaw angle; based on the current motion state, the obstacle position, the target position, and the multiple preset times, a route plan for the aircraft is generated, including: The flight path of the aircraft is generated based on the current position, the position of the obstacle, and the target position; Based on the current speed, the current yaw angle, the flight path, and the multiple preset times, generate the trajectory points of the aircraft on the flight path at each preset time. Based on the flight path and the trajectory points, the route plan for the aircraft is determined.

4. The method according to any one of claims 1-3, characterized in that, The simulator is used to determine the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point, including: Obtain the current battery level of the aircraft; The current motion state and the route plan are input into the simulator to obtain the simulated motion state of the aircraft at each trajectory point; The current motion state, the simulated motion state, and the current battery level are input into the simulator to obtain the simulated battery level corresponding to the trajectory point of the simulated motion state.

5. The method according to claim 1, characterized in that, The power information includes cruise flight power and vertical flight power; based on the flight duration and the power information, the simulated power consumption of the aircraft from the trajectory point to the target location is determined, including: The power consumption of the aircraft during cruise is determined based on the cruise flight power and the first duration. The vertical power consumption of the aircraft is determined based on the vertical flight power and the second duration. The power consumption during cruise and the power consumption during vertical movement are determined as the simulated power consumption.

6. The method according to claim 1, characterized in that, Based on the location of the obstacle, an obstacle reward function is established for the trajectory points of the cruise flight state, including: Based on the location of the obstacle, determine the first distance between the trajectory point of the cruise flight state and the obstacle; Based on the first distance, an obstacle reward function is established for the trajectory points of the cruise flight state.

7. The method according to claim 1, characterized in that, Determining the target motion state using the updated motion state decision model includes: The observed motion state and observed battery level of the aircraft at any location are obtained; The observed motion state, the observed electrical charge, and the obstacle position are input into the updated motion state decision model to obtain the target motion state.

8. A device for determining the motion state of an aircraft, characterized in that, include: The acquisition module is used to acquire the current motion state of the aircraft and the position of obstacles. A generation module is used to generate a route plan for the aircraft based on the current motion state and the position of the obstacle. The route plan includes multiple trajectory points. The simulation module is used to determine the simulated motion state of the aircraft and the corresponding simulated battery level at each trajectory point using a simulator. The determination module is used to establish a value function corresponding to each trajectory point based on the simulated motion state, the simulated power level, and the obstacle position. Based on reinforcement learning algorithms, the initial motion state decision model is updated until the value function corresponding to the trajectory point of the simulated motion state converges, thus obtaining the updated motion state decision model; the target motion state is determined through the updated motion state decision model, and the target motion state includes at least one of the following: target speed or target yaw angle; The decision module is used to acquire the power information of the aircraft; determine the flight time of the aircraft from the trajectory point to the target position based on the simulated motion state, the flight time including a first time for cruise flight and a second time for vertical flight; determine the simulated power consumption of the aircraft from the trajectory point to the target position based on the flight time and the power information; establish a power reward function for the trajectory point based on the difference between the simulated power consumption and the simulated power consumption corresponding to the trajectory point; determine the trajectory points for cruise flight from the trajectory points; establish an obstacle reward function for the trajectory points for cruise flight based on the obstacle positions; and establish a value function corresponding to the trajectory point based on the power reward function and the obstacle reward function.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, is used to implement the method of any one of claims 1-7.

Images