A method, system, device and medium for aircraft path planning

Abstract

The present application relates to the field of path planning technology, and discloses a method, system, device and medium for aircraft path planning, including: determining a speed sampling window based on the physical structure and obstacle information of the aircraft; using the speed sampling window to obtain the speed combination of the aircraft within the sampling time, and generating an aircraft simulation trajectory corresponding to the speed combination; based on a preset dynamic window evaluation function, using a locust algorithm to determine the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory to achieve path planning. Its beneficial effect is to reduce the complexity of the algorithm, achieve a more refined speed space search in a short time, thereby improving the efficiency and real-time performance of aircraft obstacle avoidance path planning, and enhancing its ability to cope with dynamic obstacle avoidance.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to an aircraft path planning method, system, device and medium. Background Art

[0002] In the field of aircraft obstacle avoidance and path planning, the dynamic window method (DWA), as a local path planning algorithm, faces the following problems: First, the high computational overhead of the DWA algorithm makes it difficult to process a large amount of state space in real time, thus affecting the real-time performance and response speed of the system. Second, the changes in obstacles in a dynamic environment increase the complexity of the state space, making it difficult for traditional DWA to adapt quickly. In addition, the inefficient path evaluation makes it impossible for the aircraft to respond in time at critical moments, and the handling of dynamic constraints is insufficient, increasing potential safety risks.

[0003] Therefore, how to reduce the complexity of the algorithm by optimizing the search process and achieve a more precise speed space search in a short time, thereby improving the efficiency and real-time performance of the vehicle's obstacle avoidance path planning and enhancing its ability to cope with dynamic obstacle avoidance, is a problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides an aircraft path planning method, system, device and medium, which solve the technical problems of complex computing power and large amount of calculation in the path planning process, achieve the technical effect of reducing algorithm complexity, realizing more precise speed space search in a short time, and improving the efficiency and real-time performance of aircraft obstacle avoidance path planning.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0006] In a first aspect, an embodiment of the present application provides a method for aircraft path planning, the method comprising:

[0007] Determine the speed sampling window based on the physical structure of the spacecraft and obstacle information;

[0008] The speed sampling window is used to obtain a speed combination of the aircraft within a sampling time, and a simulated trajectory of the aircraft corresponding to the speed combination is generated;

[0009] Based on a preset dynamic window evaluation function, a locust algorithm is used to determine a target aircraft simulation trajectory corresponding to an optimal evaluation function value from the aircraft simulation trajectory to achieve path planning.

[0010] The present embodiment provides a method for aircraft path planning, which avoids unrealistic speed combinations and ensures feasibility and safety by setting a suitable speed sampling window based on the physical structure and obstacle information of the aircraft. Then, the speed combination is obtained within this speed sampling window and a real simulated trajectory is generated, which enhances the diversity of path planning. Finally, the dynamic window evaluation function and locust algorithm are used to quickly evaluate and determine the optimal path from the generated trajectory, ensuring that the aircraft can effectively avoid obstacles in a complex environment, and realizing efficient, flexible and safe trajectory generation.

[0011] Optionally, determining the speed sampling window based on the physical structure and obstacle information of the aircraft includes:

[0012] Determining a kinematic velocity space achieved by the aircraft under kinematic performance constraints according to constraints on linear velocity and angular velocity in the physical structure of the aircraft;

[0013] Determining the dynamic speed space achieved by the aircraft under the constraints of dynamic performance according to the constraints of active force and steering torque in the physical structure of the aircraft;

[0014] Determining a safe speed space that the aircraft can reach under safety conditions according to the constraint of the collision distance between the aircraft and the obstacle information;

[0015] The speed sampling window is determined based on the kinematic speed space, the dynamic speed space and the safety speed space.

[0016] This embodiment clarifies the feasible kinematic speed space under the kinematic performance constraints based on the constraints of the linear velocity and angular velocity in the physical structure of the aircraft. It ensures that the generated speed combination is physically feasible. Next, considering the constraints of the aircraft's main power and steering torque, its dynamic speed space under the dynamic performance constraints is determined, which enhances the aircraft's dynamic adaptability and propulsion efficiency. Finally, based on the collision distance constraint between the aircraft and the obstacle, its safe speed space under safety conditions is defined. This measure significantly improves the safety of navigation and effectively reduces the risk of accidents. Through the comprehensive implementation of these three speed spaces, the speed sampling window of the aircraft can be effectively determined, thereby improving its motion performance and safety.

[0017] Optionally, the adopting the speed sampling window to obtain a speed combination of the aircraft within a sampling time, and generating a simulated trajectory of the aircraft corresponding to the speed combination, comprises:

[0018] In the speed sampling window, sampling is performed according to the sampling time to obtain the speed combination;

[0019] The trajectory of the speed combination is simulated using the aircraft kinematic model to obtain the simulated trajectory of the aircraft.

[0020] This embodiment obtains rich speed data by sampling the speed combination of the aircraft according to the sampling time within the set speed sampling window, thereby enhancing the flexibility of the aircraft to adapt to different navigation environments. Then, the kinematic model of the aircraft is used to simulate the trajectory of these speed combinations, thereby accurately predicting the trajectory of the aircraft at different speeds.

[0021] Optionally, the preset dynamic window evaluation function is:

[0022]

[0023] Among them, heading(v,w) is the azimuth evaluation function; α is the weight of the azimuth evaluation function; velocity(v,w) is the speed evaluation function; β is the weight of the speed evaluation function; dist(v,w) is the distance evaluation function; γ is the weight of the distance evaluation function; traj_dist(v,w) is the trajectory point distance evaluation function; δ is the weight of the trajectory point distance evaluation function; lead_dist(v,w) is the guide point distance evaluation function; ε is the weight of the guide point distance evaluation function; σ is a smoothing function, which normalizes each evaluation function.

[0024] The new dynamic window evaluation function of this embodiment enhances the comprehensive evaluation capability of the simulated trajectory of the aircraft by introducing the trajectory point distance evaluation function and the guide point distance evaluation function. By optimizing the trajectory of the aircraft moving to the side and rear of the obstacle, it complies with the international maritime collision regulations and improves the overall navigation safety. This enables the aircraft to avoid obstacles more effectively in complex environments, improving the efficiency and success rate of obstacle avoidance. At the same time, combined with the weighted combination of the original azimuth evaluation function, speed evaluation function and distance evaluation function, it not only ensures the safety of the aircraft, but also encourages it to move at a higher speed, thereby improving navigation efficiency. In addition, the weight factor can be adjusted in real time to adapt to different navigation conditions and obstacle distributions, showing greater flexibility.

[0025] Optionally, the trajectory point distance evaluation function and the guide point distance evaluation function include the predicted characteristic state corresponding to the obstacle;

[0026] The method for obtaining the predicted characteristic state corresponding to the obstacle includes:

[0027] Acquire the current characteristic state of the obstacle based on the AIS system;

[0028] According to the current characteristic state, a Kalman wave filter is used to generate a predicted characteristic state corresponding to the obstacle.

[0029] This embodiment obtains the current characteristic state of obstacles in real time based on the AIS system, providing a data basis for subsequent processing and enhancing the perception ability of the aircraft. Subsequently, the Kalman filter is used to process these characteristic states to generate a prediction of the obstacle's motion trajectory. This process improves the obstacle detection accuracy, enables the aircraft to formulate a more reasonable obstacle avoidance strategy, reduces the risk of collision, and thus improves the overall navigation safety.

[0030] Optionally, the generating, according to the current characteristic state, the predicted characteristic state corresponding to the obstacle by using a Kalman wave filter includes:

[0031] Construct the state equation X of the obstacle k , measurement equation Z k And the prediction matrix A k :

[0032]

[0033]

[0034]

[0035]

[0036]

[0037] Among them, x k is the state vector at the kth moment; u k is the input vector at the kth moment; f(x k-1 ,u k-1 ) is the nonlinear state equation; WQ k-1 is the process noise at the k-1th moment; long k is the longitude of the obstacle at the kth moment; vt k is the speed of the obstacle at the kth moment; βt k is the direction of the obstacle at the kth moment; k is the latitude of the obstacle at the kth moment; T is the time interval from the k-1th moment to the kth moment;

[0038] Get the prediction matrix A at the previous moment k-1 , the state equation at the previous moment X k-1 , the state covariance matrix P at the previous moment k-1 , the process noise covariance matrix Q at the previous moment k-1 , the current measurement noise covariance matrix R k , the measurement equation Z at the current moment k ;

[0039] Predict the feature state at the current moment ,in, ;

[0040] Predict the predicted state covariance matrix at the current moment ,in, ;

[0041] Calculate the Kalman gain K at the current moment k ,in, ;

[0042] Update the current state to obtain the updated predicted feature state ,in, ;

[0043] Update the current prediction state covariance matrix to obtain the updated prediction state covariance matrix P k ,in, , I is the identity matrix.

[0044] This embodiment accurately estimates the position, velocity and heading of the obstacle by constructing nonlinear state equations and measurement equations, and dynamically updating the state vector and input vector. At the same time, the covariance matrix of process noise and measurement noise is used to effectively filter system noise and improve estimation accuracy. The combination of the prediction step and the update mechanism ensures dynamic tracking of the motion state and timely reflection of feature changes. In addition, the calculation of the Kalman gain reasonably distributes the weight of the measurement data in the state update, optimizes the estimation results, and reduces uncertainty. Finally, the updated state covariance matrix reflects the dynamic evaluation of the uncertainty of the obstacle state, ensuring the real-time and reliability of the estimation.

[0045] Optionally, the method of using a locust algorithm to determine a target aircraft simulation trajectory corresponding to an optimal evaluation function value from the aircraft simulation trajectory based on a preset dynamic window evaluation function comprises:

[0046] Acquire a preset number of current speed combinations, and use the current speed combinations as a current population; wherein any current speed combination in the current population represents a simulated trajectory of an aircraft;

[0047] Based on a preset dynamic window evaluation function, obtaining an initial evaluation function value of each current speed combination in the current population;

[0048] Iterative update: keeping the position of the current speed combination corresponding to the best evaluation function value in the initial evaluation function value unchanged, updating the positions of the remaining current speed combinations using the force function, and re-obtaining the updated evaluation function values ​​of the remaining current speed combinations;

[0049] Comparing the evaluation function value with the updated evaluation function value, and determining an updated optimal evaluation function value according to the comparison result;

[0050] The iterative update is repeated until a preset condition is met, a target speed combination corresponding to the optimal target evaluation function value is obtained, and the aircraft simulation trajectory corresponding to the target speed combination is determined as the target aircraft simulation trajectory.

[0051] This embodiment obtains a preset number of current speed combinations to form a dynamic speed combination group, allowing the aircraft to perform diversified trajectory simulations in complex environments. The current speed combination is preliminarily evaluated using a dynamic window evaluation function, providing a quantitative basis for subsequent iterative updates. The best speed combination is kept unchanged, and the positions of the remaining combinations are updated. This strategy combines the advantages of local search and global optimization. It can further explore other possible optimal solutions while maintaining the known best solution, thereby improving the overall optimization efficiency. By comparing the evaluation function value and the updated value, the position of the speed combination can be adjusted in real time to continuously optimize the aircraft trajectory. Until the preset conditions are met, it is ensured that the final target speed combination is the optimal solution after multiple rounds of evaluation. This convergence capability enables the aircraft to find the best navigation path in a complex environment, improving safety and obstacle avoidance capabilities.

[0052] In a second aspect, an embodiment of the present application provides an aircraft path planning system, the system comprising:

[0053] A window determination unit, used to determine a speed sampling window based on the physical structure of the aircraft and obstacle information;

[0054] A speed determination unit, configured to obtain a speed combination of the aircraft within a sampling time by using the speed sampling window, and generate a simulated trajectory of the aircraft corresponding to the speed combination;

[0055] The path planning unit is used to determine the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory by using the locust algorithm based on a preset dynamic window evaluation function to achieve path planning.

[0056] In a third aspect, an embodiment of the present application provides a computer device, including:

[0057] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above-mentioned aircraft path planning method by executing the computer instructions.

[0058] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above-mentioned aircraft path planning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A flow chart of a method for aircraft path planning provided in an embodiment of the present application;

[0061] Figure 2 A flowchart of step S1 provided in an embodiment of the present application;

[0062] Figure 3 A schematic diagram of a speed sampling window provided in an embodiment of the present application;

[0063] Figure 4 A flowchart of step S3 provided in an embodiment of the present application;

[0064] Figure 5 A flowchart of a method for obtaining a predicted characteristic state corresponding to an obstacle provided in an embodiment of the present application;

[0065] Figure 6 A flowchart of step S53 provided in an embodiment of the present application;

[0066] Figure 7 A flowchart of a method for constructing a trajectory point distance evaluation function provided in an embodiment of the present application;

[0067] Figure 8 A schematic diagram of the scope of action of the trajectory point distance evaluation function provided in an embodiment of the present application;

[0068] Fig. 9 A schematic diagram of a trajectory point distance evaluation function provided in an embodiment of the present application;

[0069] Fig.10 A flowchart of step S511 provided in an embodiment of the present application;

[0070] Fig.11 A flowchart of a method for constructing a guide point distance evaluation function provided in an embodiment of the present application;

[0071] Fig.12A schematic diagram of the scope of action of the guidance point distance evaluation function provided in an embodiment of the present application;

[0072] Fig.13 A schematic diagram of a guide point distance evaluation function provided in an embodiment of the present application;

[0073] Fig.14 A flowchart of step S521 provided in an embodiment of the present application;

[0074] Fig.15 A flowchart of step S5 provided in an embodiment of the present application;

[0075] Fig.16 A block diagram of an aircraft path planning system provided in an embodiment of the present application;

[0076] Fig.17 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0078] In the field of aircraft obstacle avoidance and path planning, the dynamic window algorithm (DWA), as a local path planning algorithm, faces the following main problems: The DWA algorithm needs to process a large amount of state space in real time to evaluate multiple possible movement paths. This traversal search method will cause a significant computational burden in complex environments, thus affecting the real-time performance and response speed of the system. In a dynamic environment, the changes in obstacles cause the state space to be constantly updated, and traditional DWA is difficult to adapt to these changes quickly. The possible speed combinations need to be recalculated each time, which increases the calculation time. Traditional path evaluation methods may not be able to quickly identify the optimal path, especially when facing dynamic obstacles, which may cause the aircraft to fail to respond in time at critical moments. Although DWA takes into account the dynamic limitations of the aircraft (such as speed and acceleration), in complex environments, the impact of these limitations is often not fully utilized, leading to potential safety risks.

[0079] In order to solve the above technical problems, this application introduces the locust optimization algorithm, which reduces the complexity of the search algorithm by optimizing the search process, so that the aircraft can search a finer speed space in a shorter decision time. This improvement not only improves the efficiency of the algorithm, but also enhances the real-time performance of the system, so that the aircraft's planned path can better cope with the challenge of dynamic obstacle avoidance.

[0080] According to an embodiment of the present application, an embodiment of an aircraft path planning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0081] In this embodiment, a method for aircraft path planning is provided. Figure 1 A flow chart of a method for aircraft path planning provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the process includes the following steps:

[0082] Step S1, determining a speed sampling window based on the physical structure of the aircraft and obstacle information.

[0083] The speed sampling window is a set of feasible navigation speed spaces, including the combination of forward speed and steering angle, i.e. angular velocity, which needs to meet the kinematic performance constraints, dynamic performance constraints and safety speed of the aircraft. Therefore, the speed sampling space is determined based on the physical structure of the aircraft and obstacle information.

[0084] Specifically, the minimum linear velocity v that the aircraft can reach can be determined based on the physical structure of the aircraft. min and maximum linear velocity v max , and the minimum angular velocity w that the spacecraft can achieve min and the maximum angular velocity w max . Define the kinematic velocity space V k , kinematic velocity space V k It includes all possible combinations of linear velocity v and angular velocity w that satisfy the kinematic performance constraints of the vehicle.

[0085]

[0086] Due to the limitation of the active force and steering torque of the spacecraft, the speed variation range of the spacecraft within the sampling period is limited, so there is no need to consider speed samples beyond this range, which further narrows the search range of the speed space. According to the physical structure of the spacecraft, the current linear speed v of the spacecraft can be determined c and angular velocity w c; and the maximum linear acceleration a of the vehicle v and the maximum angular acceleration a w . Determine the sampling period Δt, which is the time interval from the current moment to the next evaluation moment. Define the dynamics velocity space V d , dynamic speed space V d It includes all possible combinations of linear velocity v and angular velocity w that can be achieved under the constraints of dynamic performance.

[0087]

[0088] In order to ensure that the aircraft can reduce its speed to 0 m / s before colliding with an obstacle, the speed of the aircraft must be limited to a safe range. According to the constraint S of the collision distance between the aircraft and the obstacle information min , S min The minimum safe distance between the simulated trajectory of the aircraft and the surrounding obstacles corresponding to the speed combination (v, w). It is usually determined based on the size of the obstacle area, the size of the aircraft, and the safety buffer. It can also be determined based on historical data. Define the safe speed space V s , safe speed space V s Contains all combinations of linear velocity v and angular velocity w that meet the safety conditions.

[0089]

[0090] Combining the intersection of the above three constraints, that is, , get the speed sampling window.

[0091] Step S3, using the speed sampling window to obtain the speed combination of the aircraft within the sampling time, and generating the aircraft simulation trajectory corresponding to the speed combination.

[0092] Specifically, the speed sampling window V is discretized according to the sampling time to obtain a series of discrete speed combinations (v, w). Each speed combination can be simulated using the aircraft's motion model to obtain the aircraft's simulated trajectory.

[0093] Assume (X t ,Y t ) represents the position coordinates of the spacecraft in the global coordinate system at time t, θ t represents the heading angle of the vehicle at time t, v t 、w t Respectively represent the linear velocity and angular velocity of the spacecraft at time t, which is equivalent to a discrete velocity combination. Then, in the Δt time period, the global displacement generated by the velocity components of the X-axis and Y-axis of the spacecraft in the spacecraft coordinate system is:

[0094]

[0095]

[0096] therefore, The position and posture of the aircraft at this moment can be obtained through the aircraft's motion model to obtain the aircraft's simulated trajectory:

[0097]

[0098] That is, the simulated trajectory of the aircraft can be generated by the aircraft's motion model given a discrete velocity combination (v, w).

[0099] Step S5, based on the preset dynamic window evaluation function, the locust algorithm is used to determine the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory to achieve path planning.

[0100] The traditional DWA algorithm scores the simulated trajectory of the aircraft corresponding to each speed combination through a dynamic window evaluation function, and then selects the speed combination with the highest score to execute the simulated trajectory of the aircraft. This will make the calculation amount large and time-consuming. Therefore, the embodiment of the present application adopts the locust algorithm for optimization, which can reduce the calculation amount and quickly find the optimal solution.

[0101] Specifically, a part of the speed combinations are randomly sampled to form the initial population, and then the dynamic window function value is evaluated for the sampled speed combinations, and the speed combination corresponding to the best evaluation function value is found, and it is marked as the current optimal speed combination. Due to the interaction between the populations, the other (n-1) speed combinations will be affected. The function that adjusts the strength of the interaction force is used to update the other (n-1) speed combinations to a new position, and the new speed combination position is re-evaluated after the update, and the speed combination with the best evaluation function value is found again. Repeat the above evaluation and update steps until the stop condition is met (such as reaching the maximum number of iterations or the change in the best evaluation function value is less than the threshold). Finally, the speed combination corresponding to the best evaluation function value is obtained, and the aircraft simulation trajectory corresponding to the speed combination is determined as the target aircraft simulation trajectory. It can make real-time obstacle avoidance decisions in complex environments, and finally achieve efficient path planning and reduce computing power overhead by continuously evaluating and updating the speed combination position.

[0102] The present embodiment provides a method for aircraft path planning, which avoids unrealistic speed combinations and ensures feasibility and safety by setting a suitable speed sampling window based on the physical structure and obstacle information of the aircraft. Then, the speed combination is obtained within this speed sampling window and a real simulated trajectory is generated, which enhances the diversity of path planning. Finally, the dynamic window evaluation function and locust algorithm are used to quickly evaluate and determine the optimal path from the generated trajectory, ensuring that the aircraft can effectively avoid obstacles in a complex environment, and realizing efficient, flexible and safe trajectory generation.

[0103] Figure 2 The flowchart of step S1 provided in the embodiment of the present application may include the following steps:

[0104] Step S11, according to the constraints of linear velocity and angular velocity in the physical structure of the aircraft, determine the kinematic velocity space reached by the aircraft under the constraints of kinematic performance.

[0105] Specifically, the minimum linear velocity v that the aircraft can reach can be determined based on the physical structure of the aircraft. min and maximum linear velocity v max , and the minimum angular velocity w that the spacecraft can achieve min and the maximum angular velocity w max . Define the kinematic velocity space V k , kinematic velocity space V k It includes all possible combinations of linear velocity v and angular velocity w that satisfy the kinematic performance constraints of the vehicle.

[0106]

[0107] Step S13, determining the dynamic speed space reached by the aircraft under the constraints of dynamic performance according to the constraints of the active force and steering torque in the physical structure of the aircraft.

[0108] Specifically, due to the limitation of the active force and steering torque of the aircraft, the speed variation range of the aircraft within the sampling period is limited, so there is no need to consider speed samples beyond this range, thereby further narrowing the search range of the speed space. According to the physical structure of the aircraft, the current linear speed v of the aircraft can be determined c and angular velocity w c ; and the maximum linear acceleration a of the vehicle v and the maximum angular acceleration a w . Determine the sampling period Δt, which is the time interval from the current moment to the next evaluation moment. Define the dynamics velocity space V d , dynamic speed space V d It includes all possible combinations of linear velocity v and angular velocity w that can be achieved under the constraints of dynamic performance.

[0109]

[0110] Step S15, determining a safe speed space that the aircraft can reach under safety conditions according to the constraint of the collision distance between the aircraft and the obstacle information.

[0111] Specifically, in order to ensure that the aircraft can reduce its speed to 0 m / s before colliding with an obstacle, the speed of the aircraft must be limited to a safe range. min , S min The minimum safe distance between the simulated trajectory of the aircraft and the surrounding obstacles corresponding to the speed combination (v, w). It is usually determined based on the size of the obstacle area, the size of the aircraft, and the safety buffer zone, and can also be determined based on historical data. Define the safe speed space V s , safe speed space V s Contains all combinations of linear velocity v and angular velocity w that meet the safety conditions.

[0112]

[0113] Step S17, determining a speed sampling window based on the kinematic speed space, the dynamic speed space and the safety speed space.

[0114] Specifically, see Figure 3 , Figure 3 A schematic diagram of a speed sampling window provided in an embodiment of the present application; the intersection of three constraints is integrated, namely, , get the speed sampling window.

[0115] and Figure 1 Compared with the embodiment shown in the figure, this embodiment clarifies the feasible kinematic speed space under the kinematic performance constraints based on the constraints of the linear velocity and angular velocity in the physical structure of the aircraft. It ensures that the generated speed combination is physically feasible. Next, considering the constraints of the main power and steering torque of the aircraft, its dynamic speed space under the dynamic performance constraints is determined, which enhances the dynamic adaptability and propulsion efficiency of the aircraft. Finally, based on the collision distance constraint between the aircraft and the obstacle, its safe speed space under safe conditions is defined. This measure significantly improves the safety of navigation and effectively reduces the risk of accidents. Through the comprehensive implementation of these three speed spaces, the speed sampling window of the aircraft can be effectively determined, thereby improving its motion performance and safety.

[0116] Figure 4 The flowchart of step S3 provided in the embodiment of the present application may include the following steps:

[0117] Step S31, sampling is performed within the speed sampling window according to the sampling time to obtain a speed combination.

[0118] Step S33, using the aircraft kinematic model to simulate the trajectory of the velocity combination to obtain the aircraft simulation trajectory.

[0119] Specifically, the speed sampling window V is discretized according to the sampling time to obtain a series of discrete speed combinations (v, w). Each speed combination can be simulated using the aircraft's motion model to obtain the aircraft's simulated trajectory.

[0120] Assume (X t ,Y t ) represents the position coordinates of the spacecraft in the global coordinate system at time t, θ t represents the heading angle of the vehicle at time t, v t 、w t Respectively represent the linear velocity and angular velocity of the spacecraft at time t, which is equivalent to a discrete velocity combination. Then, in the Δt time period, the global displacement generated by the velocity components of the X-axis and Y-axis of the spacecraft in the spacecraft coordinate system is:

[0121]

[0122]

[0123] therefore, The position and posture of the aircraft at this moment can be obtained through the aircraft's motion model to obtain the aircraft's simulated trajectory:

[0124]

[0125] That is, the simulated trajectory of the aircraft can be generated by the aircraft's motion model given a discrete velocity combination (v, w).

[0126] and Figure 1 Compared with the embodiment shown, this embodiment samples the speed combination of the aircraft according to the sampling time within the set speed sampling window to obtain rich speed data, thereby enhancing the flexibility of the aircraft to adapt to different navigation environments. Then, the kinematic model of the aircraft is used to simulate the trajectory of these speed combinations, thereby accurately predicting the trajectory of the aircraft at different speeds.

[0127] In a preferred embodiment, the preset dynamic window evaluation function is:

[0128]

[0129] Among them, heading(v,w) is the azimuth evaluation function; α is the weight of the azimuth evaluation function; velocity(v,w) is the speed evaluation function; β is the weight of the speed evaluation function; dist(v,w) is the distance evaluation function; γ is the weight of the distance evaluation function; traj_dist(v,w) is the trajectory point distance evaluation function; δ is the weight of the trajectory point distance evaluation function; lead_dist(v,w) is the guide point distance evaluation function; ε is the weight of the guide point distance evaluation function; σ is a smoothing function, which normalizes each evaluation function.

[0130] In the traditional dynamic window method (DWA), the evaluation function is used to evaluate the quality of simulated trajectories under different speed combinations (v, w). This evaluation function G(v, w) is a weighted sum of three parts, each of which reflects different aspects of the trajectory.

[0131] The evaluation function of traditional DWA is defined as:

[0132]

[0133] Among them, heading(v,w) is the azimuth evaluation function, which measures the directional deviation between the direction of the end of the simulated trajectory and the target point at the current set speed; velocity(v,w) is the speed evaluation function, which takes into account the linear speed of the aircraft, encourages the aircraft to move forward at a higher speed, and tends to choose a trajectory that can move forward at a higher speed while satisfying obstacle avoidance; dist(v,w) is the distance evaluation function, which evaluates the minimum distance between the predicted trajectory end point and the surrounding obstacles. A safe trajectory should avoid being too close to obstacles, so the distance evaluation function will give a higher score to those trajectories that keep a long distance from obstacles; α, β, and γ are the weight factors of the three evaluation functions; σ is a smoothing function, which normalizes each evaluation function.

[0134] Specifically, the embodiment of the present application introduces the trajectory point distance evaluation function traj_dist(v,w) and the guide point distance evaluation function lead_dist(v,w) into the original DWA algorithm. The trajectory point distance evaluation function traj_dist(v,w) is used to measure the positional relationship between the simulated trajectory of the aircraft and the simulated trajectory of the obstacle; the guide point distance evaluation function lead_dist(v,w) is used to guide the aircraft to detour in the specified direction to reduce the randomness of the obstacle avoidance movement. According to the International Collision Rules at Sea COLREGS, the side and rear of the dynamic obstacle aircraft is the best area for detour. Therefore, the embodiment of the present application uses the guide point distance evaluation function to guide the aircraft to the side and rear of the obstacle, thereby realizing an effective obstacle avoidance function.

[0135] The trajectory point distance evaluation function is:

[0136]

[0137]

[0138]

[0139] Among them, traj_dist(v,w) is the trajectory point distance evaluation function; R is the radius of the spacecraft; p end is the coordinate of the end point of the simulated trajectory of the aircraft; obi is the coordinate of the simulated trajectory point of the i-th obstacle; τ i is the weight of each first potential threat obstacle; n is the number of first potential threat obstacles; d traj The Euclidean distance between the coordinates of the obstacle simulation trajectory point and the coordinates of the end point of the aircraft simulation trajectory; dist ci is the distance between the aircraft and the first potential threatening obstacle; cj is the distance between the aircraft and the jth first potential threat obstacle.

[0140] The evaluation function of the guide point distance is:

[0141]

[0142]

[0143]

[0144] Among them, lead_dist(v,w) is the evaluation function of the distance between the leading points; R is the radius of the spacecraft; p end is the coordinate of the end point of the simulated trajectory of the aircraft; oba Simulate the coordinates of the guiding point for the ath obstacle; τ a is the weight of each second potential threat obstacle; m is the number of second potential threat obstacles; d lead The Euclidean distance between the coordinates of the obstacle simulation guide point and the coordinates of the end point of the vehicle simulation trajectory; dist ca is the distance between the aircraft and the ath second potential threat obstacle; cb is the distance between the aircraft and the bth second potential threat obstacle.

[0145] and Figure 1Compared with the embodiment shown, the new dynamic window evaluation function of this embodiment enhances the comprehensive evaluation capability of the simulated trajectory of the aircraft by introducing the trajectory point distance evaluation function and the guide point distance evaluation function. By optimizing the trajectory of the aircraft moving to the side and rear of the obstacle, it complies with the international maritime collision regulations and improves the overall navigation safety. This enables the aircraft to avoid obstacles more effectively in complex environments, improving the efficiency and success rate of obstacle avoidance. At the same time, combined with the weighted combination of the original azimuth evaluation function, speed evaluation function and distance evaluation function, it not only ensures the safety of the aircraft, but also encourages it to move at a higher speed, thereby improving navigation efficiency. In addition, the weight factor can be adjusted in real time to adapt to different navigation conditions and obstacle distributions, showing greater flexibility.

[0146] Figure 5 A flowchart of a method for obtaining a characteristic state of an obstacle corresponding to a prediction provided in an embodiment of the present application, wherein the trajectory point distance evaluation function and the guide point distance evaluation function include the characteristic state of the obstacle corresponding to the prediction; the process may include the following steps:

[0147] Step S51, obtaining the current characteristic state of the obstacle based on the AIS system.

[0148] Step S53: Based on the current characteristic state, a Kalman wave filter is used to generate a predicted characteristic state corresponding to the obstacle.

[0149] In order to implement an effective collision avoidance strategy, the motion state of obstacles needs to be accurately predicted.

[0150] Specifically, the current characteristic state of the obstacle, including longitude and latitude, speed and heading, is obtained through the AIS system. The Kalman filter is used to predict the future state of the obstacle based on its current state. The Kalman filter is a recursive filter that uses state equations and observation data to estimate the state at the next moment.

[0151] and Figure 1 Compared with the embodiment shown in the figure, this embodiment obtains the current characteristic state of the obstacle in real time based on the AIS system, provides a data basis for subsequent processing, and enhances the perception ability of the aircraft. Subsequently, the Kalman filter is used to process these characteristic states to generate a prediction of the obstacle's motion trajectory. This process improves the obstacle detection accuracy, enables the aircraft to formulate a more reasonable obstacle avoidance strategy, reduces the risk of collision, and thus improves the overall navigation safety.

[0152] Figure 6 The flowchart of step S53 provided in the embodiment of the present application may include the following steps:

[0153] Step S531, construct the state equation X of the obstacle k , measurement equation Zk And the prediction matrix A k :

[0154]

[0155]

[0156]

[0157]

[0158]

[0159] Among them, x k is the state vector at the kth moment; u k is the input vector at the kth moment; f(x k-1 ,u k-1 ) is the nonlinear state equation; WQ k-1 is the process noise at the k-1th moment; long k is the longitude of the obstacle at the kth moment; vt k is the speed of the obstacle at the kth moment; βt k is the direction of the obstacle at the kth moment; k is the latitude of the obstacle at the kth moment; T is the time interval from the k-1th moment to the kth moment.

[0160] Step S532, obtain the prediction matrix A at the previous moment k-1 , the state equation at the previous moment X k-1 , the state covariance matrix P at the previous moment k-1 , the process noise covariance matrix Q at the previous moment k-1 , the current measurement noise covariance matrix R k , the measurement equation Z at the current moment k .

[0161] Step S533: predict the feature state at the current moment ,in, .

[0162] Step S534: predict the current state covariance matrix ,in, .

[0163] Step S535, calculate the Kalman gain K at the current moment k ,in, .

[0164] Specifically, the Kalman gain determines the weight of the current measurement when updating the state, ensuring that measurement uncertainty is properly accounted for.

[0165] Step S536: Update the current state to obtain an updated predicted feature state. ,in, .

[0166] Step S537, updating the current prediction state covariance matrix to obtain an updated prediction state covariance matrix P k ,in, , I is the identity matrix.

[0167] Specifically, the update combines the predicted state and the measured difference, using the Kalman gain to correct the prediction, achieving real-time estimation of the obstacle's motion state.

[0168] and Figure 5 Compared with the embodiment shown in the figure, this embodiment accurately estimates the position, speed and heading of the obstacle by constructing nonlinear state equations and measurement equations and dynamically updating the state vector and input vector. At the same time, the covariance matrix of process noise and measurement noise is used to effectively filter system noise and improve estimation accuracy. The combination of the prediction step and the update mechanism ensures dynamic tracking of the motion state and timely reflection of feature changes. In addition, the calculation of the Kalman gain reasonably distributes the weight of the measurement data in the state update, optimizes the estimation result, and reduces uncertainty. Finally, the updated state covariance matrix reflects the dynamic evaluation of the uncertainty of the obstacle state, ensuring the real-time and reliability of the estimation.

[0169] Figure 7 A flowchart of a method for constructing a trajectory point distance evaluation function provided in an embodiment of the present application, the process may include the following steps:

[0170] Step S511, determining a first set of potential threat obstacles within the range of action of a preset trajectory point distance evaluation function.

[0171] The scope of the trajectory point distance evaluation function refers to determining which obstacles pose a potential threat to the current motion trajectory of the aircraft.

[0172] Specifically, see Figure 8 , it is necessary to obtain the velocity combination obtained by the aircraft in the velocity sampling window. The velocity combination has a corresponding velocity vector, which is defined as the aircraft velocity vector V c ; Define R as the radius of the aircraft area, which represents the safe distance range determined by the size of the aircraft itself. Define θ f It is used to identify obstacles in front of the aircraft. It is the angle between the aircraft's travel direction and the obstacle's travel direction, usually set to 90-135°. is the set of all current obstacles; define θ pFor each obstacle DO i The line between them and the vehicle velocity vector V c The angle between the directions; definition d oc DO for the aircraft and each obstacle i Through the constraints of angle and distance, the first potential threat obstacle set O within the range of the trajectory point distance evaluation function is screened out. t :

[0173]

[0174] This means that only those f Only obstacles within a distance of R will be considered.

[0175] Step S513, obtaining speed information and position information of the first potential threat obstacle in the first potential threat obstacle set, and generating obstacle simulation trajectory point coordinates corresponding to the first potential threat obstacle by using the trajectory point simulation model.

[0176] Specifically, see Fig. 9 The speed information and position information of the first potential threat obstacle are obtained according to the predicted characteristic state corresponding to the obstacle obtained in step S53, and the speed vector of the obstacle in the predicted characteristic state is defined as V p , that is, V p is the speed information of the first potential threat obstacle; the longitude and latitude of the obstacle in the predicted characteristic state is defined as (x oa ,y oa ), that is, (x oa ,y oa ) is the predicted position information of the first potential threat obstacle; then the trajectory point simulation model is used to generate the obstacle simulation trajectory point coordinates corresponding to the first potential threat obstacle.

[0177] In some preferred embodiments, the trajectory point simulation model is:

[0178]

[0179] Among them, (x traj ,y traj ) is the coordinate of the obstacle simulation trajectory point; (x oa ,y oa ) is the position information of the first potential threat obstacle; V p is the speed information of the first potential threat obstacle; θ c V p Angle with the horizontal direction; The simulation time for simulating trajectories for obstacles.

[0180] Step S515, constructing a trajectory point distance evaluation function based on the coordinates of the obstacle simulation trajectory points, the distance between the aircraft and the first potential threat obstacle, and the aircraft simulation trajectory.

[0181] Specifically, the purpose of constructing the trajectory point distance evaluation function traj_dist(v,w) is to evaluate the safe distance between the simulated trajectory of the aircraft and the simulated trajectory of the obstacle under a specific speed combination (v,w).

[0182] The trajectory point distance evaluation function is:

[0183]

[0184]

[0185]

[0186] Among them, traj_dist(v,w) is the trajectory point distance evaluation function; R is the radius of the spacecraft; p end is the coordinate of the end point of the simulated trajectory of the aircraft; obi is the coordinate of the simulated trajectory point of the i-th obstacle; τ i is the weight of each first potential threat obstacle; n is the number of first potential threat obstacles; d traj The Euclidean distance between the coordinates of the obstacle simulation trajectory point and the coordinates of the end point of the aircraft simulation trajectory; dist ci is the distance between the aircraft and the first potential threatening obstacle; cj is the distance between the aircraft and the jth first potential threat obstacle. Select the speed combination that maximizes traj_dist(v,w), that is, the speed combination with the largest distance between the obstacle and the end point of the aircraft simulation trajectory, to avoid collision with the obstacle.

[0187] and Figure 1Compared with the embodiment shown in the figure, this embodiment can effectively screen out obstacles that pose a threat to the safety of the aircraft and improve the obstacle avoidance capability of the aircraft by determining the first set of potential threat obstacles within the range of action of the pre-set trajectory point distance evaluation function. Next, the speed and position information of these potential threat obstacles are obtained, and the corresponding obstacle simulation trajectory point coordinates are generated using the trajectory point simulation model. It not only provides the dynamic characteristics of potential obstacles, but also lays the foundation for subsequent trajectory analysis, which helps to predict its future position more accurately. Finally, based on the coordinates of the obstacle simulation trajectory points, the distance between the aircraft and the potential threat obstacle, and the simulated trajectory of the aircraft, a trajectory point distance evaluation function is constructed. This evaluation function can comprehensively consider various factors and evaluate the relative position relationship between the aircraft and the obstacle in real time, thereby providing a scientific basis for subsequent path planning for navigation.

[0188] Fig.10 The flowchart of step S511 provided in the embodiment of the present application may include the following steps:

[0189] Step S5111, for any obstacle, determine the first angle between the line between the aircraft and any obstacle and the velocity vector in the velocity combination, as well as the straight-line distance between the aircraft and any obstacle.

[0190] Step S5113, any obstacle whose first angle is less than or equal to the first angle threshold and whose straight-line distance is less than or equal to the aircraft's field radius is formed into a first potential threat obstacle set; wherein the aircraft's field radius represents a safe distance range determined by the size of the aircraft itself.

[0191] Specifically, for each obstacle, the line between the aircraft and the obstacle and the aircraft velocity vector V are calculated. c The angle between them is called the first angle. Calculate the straight-line distance between the aircraft and each obstacle. Define the first angle threshold, which is usually an angle value used to determine whether the obstacle is in front of the aircraft or in the threat area. The first angle threshold is preferably 90-135°. Define the aircraft field radius R, which characterizes the safe distance range determined by the aircraft's own size. According to the first angle threshold and the aircraft field radius, screen out those obstacles whose first angle is less than or equal to the first angle threshold and whose straight-line distance is less than or equal to the aircraft field radius. The screened obstacles form the first potential threat obstacle set.

[0192] and Figure 7Compared with the embodiment shown, this embodiment determines the first angle between the line between the aircraft and the obstacle and the velocity vector in the velocity combination, as well as the straight-line distance between the two for any obstacle. This process can evaluate the movement trend and distance of the obstacle relative to the aircraft, and help identify potential collision risks. By including obstacles whose first angle is less than or equal to the first angle threshold and whose straight-line distance is less than or equal to the aircraft's field radius into the first potential threat obstacle set, this screening mechanism ensures that only those obstacles that are within the aircraft's safety range and may affect the navigation path are identified as potential threats. The setting of the aircraft's field radius is a safe distance range determined based on the size of the aircraft, which further increases the safety of the aircraft. The implementation method of the present application can effectively construct a dynamic potential threat obstacle set by accurately evaluating the movement state of the obstacle and its relative position to the aircraft, thereby improving the aircraft's safety identification capability and response efficiency in complex environments.

[0193] Fig.11 A flowchart of a method for constructing a guide point distance evaluation function provided in an embodiment of the present application, the process may include the following steps:

[0194] Step S521: determine a second set of potential threat obstacles within the range of action of a preset guidance point distance evaluation function.

[0195] The definition of the scope of the guidance point distance evaluation function is to determine which obstacles the current motion trajectory of the guiding vehicle should be circumvented to the side and rear of, reduce the randomness of the obstacle avoidance motion, and thus improve the stability of the algorithm.

[0196] Specifically, see Fig.12 , it is necessary to obtain the velocity combination obtained by the aircraft in the velocity sampling window. The velocity combination has a corresponding velocity vector, which is defined as the aircraft velocity vector V c ; Define R as the radius of the aircraft area, which represents the safe distance range determined by the size of the aircraft itself. Define θ f’ It is used to identify obstacles in front of the aircraft. It is the angle between the aircraft's travel direction and the obstacle's travel direction, usually set to 0-90°; assuming is the set of all current obstacles; define θ p For each obstacle DO i The line between them and the vehicle velocity vector V c The angle between the directions; definition d oc DO for the aircraft and each obstacle i Through the constraints of angle and distance, the second potential threat obstacle set O within the range of the guidance point distance evaluation function is screened out. l :

[0197]

[0198] This means that only those f’ Only obstacles within a distance of R will be considered.

[0199] Step S523, obtaining speed information and position information of the second potential threat obstacle in the second potential threat obstacle set, and generating obstacle simulation guidance point coordinates corresponding to the second potential threat obstacle by using the guidance point simulation model.

[0200] Specifically, see Fig.13 The speed information and position information of the second potential threat obstacle are obtained according to the predicted characteristic state corresponding to the obstacle obtained in step S53, and the speed vector of the obstacle in the predicted characteristic state is defined as V p’ , that is, V p’ is the speed information of the second potential threat obstacle; the longitude and latitude of the obstacle in the predicted characteristic state is defined as (x ob ,y ob ), that is, (x ob ,y ob ) is the predicted position information of the second potential threat obstacle; then the guide point simulation model is used to generate the obstacle simulation guide point coordinates corresponding to the second potential threat obstacle.

[0201] In some preferred embodiments, the obstacle simulation guide point coordinates include obstacle simulation left guide point coordinates and obstacle simulation right guide point coordinates; generating the obstacle simulation guide point coordinates corresponding to the second potential threat obstacle includes:

[0202] The second potential threat obstacles in the second potential threat obstacle set are classified to obtain left potential conflict obstacles and right potential conflict obstacles.

[0203] Specifically, the purpose of classifying the second potential threat obstacles is to more effectively guide the avoidance direction of the aircraft and improve the path planning efficiency of the aircraft. For each second potential threat obstacle, determine the angle θ between its moving direction and the moving direction of the aircraft. v Define the threshold θ k In order to prevent the second potential threat obstacle from shaking in the boundary area and causing the category to change continuously, the classification criteria are obtained through experience or historical data fitting.

[0204] Table 1 Classification criteria

[0205]

[0206] The coordinates of the left-side guide point of the obstacle simulation corresponding to the potential conflicting obstacle on the left are determined, and the coordinates of the right-side guide point of the obstacle simulation corresponding to the potential conflicting obstacle on the right are determined.

[0207] Specifically, in the path planning and obstacle avoidance strategy, the simulated guide point coordinates of the left and right potential conflicting obstacles are determined to guide the aircraft to bypass these obstacles. For each obstacle classified as a potential conflict on the left, its left guide point coordinates are calculated. The left guide point coordinates are usually located on the left side of the obstacle and on the obstacle avoidance path of the aircraft. For each obstacle classified as a potential conflict on the right, its right guide point coordinates are calculated. The right guide point coordinates are usually located on the right side of the obstacle and on the obstacle avoidance path of the aircraft.

[0208] In some preferred embodiments, the guide point simulation model used to determine the coordinates of the left guide point of the obstacle simulation corresponding to the left potential conflict obstacle is:

[0209]

[0210] The guidance point simulation model used to determine the right guidance point coordinates of the obstacle simulation corresponding to the potential conflict obstacle on the right is:

[0211]

[0212] Among them, (x lead ,y lead ) is the coordinate of the obstacle simulation guide point; (x ob ,y ob ) is the position information of the second potential threat obstacle; θ c is the angle between the velocity information of the second potential threat obstacle and the horizontal direction; , The simulation time for simulating guide points for obstacles.

[0213] Step S525, constructing a guidance point distance evaluation function based on the obstacle simulation guidance point coordinates, the distance between the aircraft and the second potential threat obstacle, and the aircraft simulation trajectory.

[0214] Specifically, the purpose of constructing the lead point distance evaluation function lead_dist(v,w) is to evaluate the distance between the simulated trajectory of the vehicle under a specific speed combination (v,w) and the obstacle simulation lead point.

[0215] The evaluation function of the guide point distance is:

[0216]

[0217]

[0218]

[0219] Among them, lead_dist(v,w) is the evaluation function of the distance between the leading points; R is the radius of the spacecraft; p end is the coordinate of the end point of the simulated trajectory of the aircraft; oba Simulate the coordinates of the guiding point for the ath obstacle; τ a is the weight of each second potential threat obstacle; m is the number of second potential threat obstacles; d lead The Euclidean distance between the coordinates of the obstacle simulation guide point and the coordinates of the end point of the vehicle simulation trajectory; dist ca is the distance between the aircraft and the ath second potential threat obstacle; cb is the distance between the aircraft and the bth second potential threat obstacle.

[0220] and Figure 1 Compared with the embodiment shown, this embodiment determines the second potential threat obstacle set within the range of action of the preset guidance point distance evaluation function. It can effectively screen out obstacles related to the aircraft path. By obtaining the speed information and position information of the second potential threat obstacle and using the guidance point simulation model to generate the corresponding obstacle simulation guidance point coordinates, it is possible to dynamically reflect the movement state of the obstacle and provide support for the subsequent guidance of the aircraft to bypass the designated side and rear of the obstacle. The guidance point distance evaluation function is constructed based on the obstacle simulation guidance point coordinates, the distance between the aircraft and the second potential threat obstacle, and the aircraft simulation trajectory, which can achieve a comprehensive analysis of the potential threat of obstacles, so that it can respond faster and more accurately in complex environments to enhance overall navigation safety.

[0221] Fig.14 The flowchart of step S521 provided in the embodiment of the present application may include the following steps:

[0222] Step S5211, for any obstacle, determine the second angle between the line between the aircraft and any obstacle and the velocity vector in the velocity combination, as well as the straight-line distance between the aircraft and any obstacle.

[0223] Step S5213, any obstacle whose second angle is less than or equal to the second angle threshold and whose straight-line distance is less than or equal to the aircraft's field radius is formed into a second potential threat obstacle set; wherein the aircraft's field radius represents a safe distance range determined by the size of the aircraft itself.

[0224] Specifically, for each obstacle, the line between the aircraft and the obstacle and the aircraft velocity vector V are calculated. cThe angle between them is called the second angle. Calculate the straight-line distance between the aircraft and each obstacle. Define the second angle threshold, which is usually an angle value used to identify obstacles in front of the aircraft. The second angle threshold is preferably 0-90°. Define the aircraft field radius R, which characterizes the safe distance range determined by the size of the aircraft itself. According to the second angle threshold and the aircraft field radius, screen out those obstacles whose second angle is less than or equal to the second angle threshold and whose straight-line distance is less than or equal to the aircraft field radius. The screened obstacles form the second potential threat obstacle set.

[0225] and Fig.11 Compared with the embodiment shown in the figure, this embodiment effectively analyzes the relative position relationship between the movement direction of the obstacle and the aircraft to provide basic data for subsequent threat assessment. By setting the second angle threshold of the second angle and the straight-line distance, obstacles that meet the conditions are screened out to form a second potential threat obstacle set, thereby improving the safety recognition capability and response efficiency of the aircraft in complex environments.

[0226] Fig.15 The flowchart of step S5 provided in the embodiment of the present application may include the following steps:

[0227] Step S501, obtaining a preset number of current speed combinations, and using the current speed combinations as the current population; wherein any current speed combination in the current population represents a simulated trajectory of an aircraft.

[0228] The traditional DWA algorithm scores the aircraft simulation trajectory corresponding to each speed combination through a dynamic window evaluation function, and then selects the speed combination with the highest score to execute the aircraft simulation trajectory. This makes the calculation amount large and time-consuming. For this reason, the embodiment of the present application adopts the locust algorithm for optimization, which can reduce the amount of calculation and quickly find the optimal solution.

[0229] Specifically, a set of random number n speed combinations is generated as the current population, and each speed combination represents a potential simulated trajectory of the aircraft. The speed combination corresponding to the current population is (v i ,w i ), i=1,2,3,…,n; where v is the linear velocity of the spacecraft and w is the angular velocity of the spacecraft.

[0230] Step S503: based on a preset dynamic window evaluation function, obtaining an initial evaluation function value of each current speed combination in the current population.

[0231] Specifically, each speed combination is scored using a preset dynamic window evaluation function to obtain an initial evaluation function value corresponding to each speed combination.

[0232] Step S505, iterative update: keep the position of the current speed combination corresponding to the best evaluation function value in the initial evaluation function value unchanged, use the force function to update the positions of the remaining current speed combinations, and re-acquire the updated evaluation function values ​​of the remaining current speed combinations.

[0233] Specifically, the objective of iterative update is expressed as:

[0234]

[0235] By simulating the group behavior of locusts, the speed combination in the current population is updated according to the evaluation function value to find the optimal solution. First, the current n initial evaluation function values ​​are compared, and the speed combination corresponding to the best evaluation function value among these initial evaluation function values ​​is screened out, and the position of the speed combination is kept unchanged. The position of the remaining n-1 populations is determined by the force function. The force function is:

[0236]

[0237]

[0238]

[0239] Where N is the total number of individuals in the population, d ij is the distance between the ith population and the jth population, s(d ij ) is the attraction intensity between the two populations, f is the attraction coefficient, and l is the attraction range.

[0240] The attraction coefficient f controls the strength of mutual attraction between populations. Larger values ​​of f increase the attraction between populations, causing the algorithm to tend to gather together faster, which helps the algorithm's local search. Conversely, smaller values ​​of f reduce attraction, giving the algorithm better global search capabilities. In practical applications, the value of f is usually between 0 and 1, and a commonly used starting value is 0.5. The attraction range l defines the effective distance over which the attraction acts. When the distance between populations exceeds this range, the interaction force between them will weaken or disappear. The value of l is usually set to a small positive number, such as 1.5, which allows interactions to be maintained within a certain distance while avoiding invalid interactions between populations that are too far away.

[0241] Step S507, comparing the evaluation function value and the updated evaluation function value, and determining the updated optimal evaluation function value according to the comparison result.

[0242] Step S509, repeat the iterative update until the preset conditions are met, obtain the target speed combination corresponding to the best target evaluation function value, and determine the aircraft simulation trajectory corresponding to the target speed combination as the target aircraft simulation trajectory.

[0243] Specifically, in each iteration, the position of the best speed combination is kept unchanged, while the positions of other speed combinations are updated. For each updated speed combination, its evaluation function value is recalculated to evaluate its performance, and the iteration continues until the preset number of iterations is reached, or the evaluation function value no longer changes, and the aircraft simulation trajectory corresponding to the final target speed combination is obtained and determined as the target aircraft simulation trajectory.

[0244] and Figure 1 Compared with the embodiment shown, this embodiment forms a dynamic speed combination group by obtaining a preset number of current speed combinations, allowing the aircraft to perform diversified trajectory simulations in complex environments. The current speed combination is preliminarily evaluated using a dynamic window evaluation function, providing a quantitative basis for subsequent iterative updates. The best speed combination is kept unchanged, and the positions of the remaining combinations are updated. This strategy combines the advantages of local search and global optimization. It can further explore other possible optimal solutions while maintaining the known best solution, thereby improving the overall optimization efficiency. By comparing the evaluation function value and the update value, the position of the speed combination can be adjusted in real time, and the aircraft trajectory can be continuously optimized. Until the preset conditions are met, it is ensured that the final target speed combination is the optimal solution after multiple rounds of evaluation. This convergence capability enables the aircraft to find the best navigation path in a complex environment, improving safety and obstacle avoidance capabilities.

[0245] Accordingly, please refer to Fig.16 A block diagram of an aircraft path planning system provided in an embodiment of the present application, the system comprising:

[0246] The window determination unit S001 is used to determine the speed sampling window based on the physical structure of the aircraft and obstacle information;

[0247] The speed determination unit S003 is used to obtain the speed combination of the aircraft within the sampling time by using the speed sampling window, and generate a simulated trajectory of the aircraft corresponding to the speed combination;

[0248] The path planning unit S005 is used to determine the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory based on a preset dynamic window evaluation function using the locust algorithm to achieve path planning.

[0249] In some optional implementations, the window determining unit S001 includes:

[0250] According to the constraints of linear velocity and angular velocity in the physical structure of the spacecraft, the kinematic velocity space reached by the spacecraft under the constraints of kinematic performance is determined;

[0251] According to the constraints of active force and steering torque in the physical structure of the spacecraft, the dynamic speed space that the spacecraft can reach under the constraints of dynamic performance is determined;

[0252] According to the constraints of the collision distance between the aircraft and the obstacle information, determine the safe speed space that the aircraft can reach under safety conditions;

[0253] The speed sampling window is determined based on the kinematic speed space, the dynamic speed space and the safety speed space.

[0254] In some optional implementations, the speed determination unit S003 includes:

[0255] In the speed sampling window, sampling is performed according to the sampling time to obtain a speed combination;

[0256] The trajectory of the velocity combination is simulated using the aircraft kinematic model to obtain the aircraft simulation trajectory.

[0257] In some optional implementations, the preset dynamic window evaluation function is:

[0258]

[0259] Among them, heading(v,w) is the azimuth evaluation function; α is the weight of the azimuth evaluation function; velocity(v,w) is the speed evaluation function; β is the weight of the speed evaluation function; dist(v,w) is the distance evaluation function; γ is the weight of the distance evaluation function; traj_dist(v,w) is the trajectory point distance evaluation function; δ is the weight of the trajectory point distance evaluation function; lead_dist(v,w) is the guide point distance evaluation function; ε is the weight of the guide point distance evaluation function; σ is a smoothing function, which normalizes each evaluation function.

[0260] In some optional embodiments, the trajectory point distance evaluation function and the guide point distance evaluation function include characteristic states corresponding to the predictions of the obstacles;

[0261] The methods for obtaining the predicted characteristic state of the obstacle include:

[0262] Obtain the current characteristic status of obstacles based on the AIS system;

[0263] According to the current characteristic state, the Kalman wave filter is used to generate the predicted characteristic state corresponding to the obstacle.

[0264] In some optional implementations, according to the current characteristic state, a Kalman wave filter is used to generate a characteristic state corresponding to a predicted obstacle, including:

[0265] Construct the state equation of the obstacle Xk , measurement equation Z k And the prediction matrix A k :

[0266]

[0267]

[0268]

[0269]

[0270]

[0271] Among them, x k is the state vector at the kth moment; u k is the input vector at the kth moment; f(x k-1 ,u k-1 ) is the nonlinear state equation; WQ k-1 is the process noise at the k-1th moment; long k is the longitude of the obstacle at the kth moment; vt k is the speed of the obstacle at the kth moment; βt k is the direction of the obstacle at the kth moment; k is the latitude of the obstacle at the kth moment; T is the time interval from the k-1th moment to the kth moment;

[0272] Get the prediction matrix A at the previous moment k-1 , the state equation at the previous moment X k-1 , the state covariance matrix P at the previous moment k-1 , the process noise covariance matrix Q at the previous moment k-1 , the current measurement noise covariance matrix R k , the measurement equation Z at the current moment k ;

[0273] Predict the feature state at the current moment ,in, ;

[0274] Predict the predicted state covariance matrix at the current moment ,in, ;

[0275] Calculate the Kalman gain K at the current moment k ,in, ;

[0276] Update the current state to get the updated predicted feature state ,in, ;

[0277] Update the current prediction state covariance matrix to obtain the updated prediction state covariance matrix P k ,in, , I is the identity matrix.

[0278] In some optional implementations, the path planning unit S005 includes:

[0279] Obtain a preset number of current speed combinations, and use the current speed combinations as a current population; wherein any current speed combination in the current population represents a simulated trajectory of the aircraft;

[0280] Based on a preset dynamic window evaluation function, an initial evaluation function value of each current speed combination in the current population is obtained;

[0281] Iterative update: keep the position of the current speed combination corresponding to the best evaluation function value in the initial evaluation function value unchanged, use the force function to update the position of the remaining current speed combinations, and re-obtain the updated evaluation function values ​​of the remaining current speed combinations;

[0282] Comparing the evaluation function value and the updated evaluation function value, and determining the updated optimal evaluation function value according to the comparison result;

[0283] Repeat the iterative update until the preset conditions are met, obtain the target speed combination corresponding to the best target evaluation function value, and determine the aircraft simulation trajectory corresponding to the target speed combination as the target aircraft simulation trajectory.

[0284] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0285] In this embodiment, an aircraft path planning system is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0286] See also Fig.17 , Fig.17 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown in FIG. Fig.17As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.17 A processor 10 is taken as an example.

[0287] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0288] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0289] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0290] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0291] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0292] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0293] The systems, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0294] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0295] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods and systems. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0296] The present application is described with reference to the flowcharts and / or block diagrams of the methods and systems according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0297] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0298] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0299] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0300] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0301] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0302] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for aircraft path planning, characterized in that: The method comprises: Determine the speed sampling window based on the physical structure of the spacecraft and obstacle information; The speed sampling window is used to obtain a speed combination of the aircraft within a sampling time, and a simulated trajectory of the aircraft corresponding to the speed combination is generated; Based on a preset dynamic window evaluation function, a locust algorithm is used to determine a target aircraft simulation trajectory corresponding to an optimal evaluation function value from the aircraft simulation trajectory to achieve path planning; The method of determining the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory by using the locust algorithm based on the preset dynamic window evaluation function includes: Acquire a preset number of current speed combinations, and use the current speed combinations as a current population; wherein any current speed combination in the current population represents a simulated trajectory of an aircraft; Based on a preset dynamic window evaluation function, obtaining an initial evaluation function value of each current speed combination in the current population; Iterative update: keeping the position of the current speed combination corresponding to the best evaluation function value in the initial evaluation function value unchanged, updating the positions of the remaining current speed combinations using the force function, and re-obtaining the updated evaluation function values ​​of the remaining current speed combinations; Comparing the evaluation function value with the updated evaluation function value, and determining an updated optimal evaluation function value according to the comparison result; The iterative update is repeated until a preset condition is met, a target speed combination corresponding to the optimal evaluation function value is obtained, and the aircraft simulation trajectory corresponding to the target speed combination is determined as the target aircraft simulation trajectory.

2. The method according to claim 1, characterized in that The method of determining the speed sampling window based on the physical structure of the aircraft and obstacle information includes: Determining a kinematic velocity space achieved by the aircraft under kinematic performance constraints according to constraints on linear velocity and angular velocity in the physical structure of the aircraft; Determining the dynamic speed space achieved by the aircraft under the constraints of dynamic performance according to the constraints of active force and steering torque in the physical structure of the aircraft; Determining a safe speed space that the aircraft can reach under safety conditions according to the constraint of the collision distance between the aircraft and the obstacle information; The speed sampling window is determined based on the kinematic speed space, the dynamic speed space and the safety speed space.

3. The method according to claim 1, characterized in that The method of using the speed sampling window to obtain a speed combination of the aircraft within a sampling time and generating a simulated trajectory of the aircraft corresponding to the speed combination includes: In the speed sampling window, sampling is performed according to the sampling time to obtain the speed combination; The trajectory of the speed combination is simulated using the aircraft kinematic model to obtain the simulated trajectory of the aircraft.

4. The method according to claim 1, characterized in that: The preset dynamic window evaluation function is: Among them, heading(v,w) is the azimuth evaluation function; α is the weight of the azimuth evaluation function; velocity(v,w) is the speed evaluation function; β is the weight of the speed evaluation function; dist(v,w) is the distance evaluation function; γ is the weight of the distance evaluation function; traj_dist(v,w) is the trajectory point distance evaluation function; δ is the weight of the trajectory point distance evaluation function; lead_dist(v,w) is the guide point distance evaluation function; ε is the weight of the guide point distance evaluation function; σ is a smoothing function, which normalizes each evaluation function.

5. The method according to claim 4, characterized in that The trajectory point distance evaluation function and the guide point distance evaluation function include the predicted characteristic states corresponding to the obstacles; The method for obtaining the predicted characteristic state corresponding to the obstacle includes: Acquire the current characteristic state of the obstacle based on the AIS system; According to the current characteristic state, a Kalman wave filter is used to generate a predicted characteristic state corresponding to the obstacle.

6. The method according to claim 5, characterized in that The step of using a Kalman wave filter to generate a predicted characteristic state corresponding to the obstacle according to the current characteristic state includes: Construct the state equation X of the obstacle k , measurement equation Z k And the prediction matrix A k : Among them, x k is the state vector at the kth moment; u k is the input vector at the kth moment; f(x k-1 ,u k-1 ) is the nonlinear state equation; WQ k-1 is the process noise at the k-1th moment; long k is the longitude of the obstacle at the kth moment; vt k is the speed of the obstacle at the kth moment; βt k is the direction of the obstacle at the kth moment; k is the latitude of the obstacle at the kth moment; T is the time interval from the k-1th moment to the kth moment; Get the prediction matrix A at the previous moment k-1 , the state equation at the previous moment X k-1 , the state covariance matrix P at the previous moment k-1 , the process noise covariance matrix Q at the previous moment k-1 , the current measurement noise covariance matrix R k , the measurement equation Z at the current moment k ; Predict the feature state at the current moment ,in, ; Predict the predicted state covariance matrix at the current moment ,in, ; Calculate the Kalman gain K at the current moment k ,in, ; Update the current state to obtain the updated predicted feature state ,in, Update the current prediction state covariance matrix to obtain the updated prediction state covariance matrix P k ,in, , I is the identity matrix.

7. An aircraft path planning system, characterized in that: The system comprises: A window determination unit, used to determine a speed sampling window based on the physical structure of the aircraft and obstacle information; A speed determination unit, configured to obtain a speed combination of the aircraft within a sampling time by using the speed sampling window, and generate a simulated trajectory of the aircraft corresponding to the speed combination; A path planning unit, configured to determine a target aircraft simulation trajectory corresponding to an optimal evaluation function value from the aircraft simulation trajectory by using a locust algorithm based on a preset dynamic window evaluation function, so as to implement path planning; The method of determining the target aircraft simulation trajectory corresponding to the best evaluation function value from the aircraft simulation trajectory by using the locust algorithm based on the preset dynamic window evaluation function includes: Acquire a preset number of current speed combinations, and use the current speed combinations as a current population; wherein any current speed combination in the current population represents a simulated trajectory of an aircraft; Based on a preset dynamic window evaluation function, obtaining an initial evaluation function value of each current speed combination in the current population; Iterative update: keeping the position of the current speed combination corresponding to the best evaluation function value in the initial evaluation function value unchanged, updating the positions of the remaining current speed combinations using the force function, and re-obtaining the updated evaluation function values ​​of the remaining current speed combinations; Comparing the evaluation function value with the updated evaluation function value, and determining an updated optimal evaluation function value according to the comparison result; The iterative update is repeated until a preset condition is met, a target speed combination corresponding to the optimal evaluation function value is obtained, and the aircraft simulation trajectory corresponding to the target speed combination is determined as the target aircraft simulation trajectory.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the aircraft path planning method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the aircraft path planning method according to any one of claims 1 to 6.

Images