Anti-interference unmanned aerial vehicle intelligent path planning method and system

Abstract

The invention discloses an anti-interference unmanned aerial vehicle intelligent path planning system and method, and belongs to the technical field of artificial intelligence. The system comprises a line-of-sight curvature control network, a first reward function and a second reward function, the unmanned aerial vehicle flies according to an instruction generated by the line-of-sight curvature control network, and the first reward function is used for evaluating the state of the unmanned aerial vehicle relative to a destination at time k and giving a first reward. The second reward function is used for evaluating the state of the obstacle at the time k without the unmanned aerial vehicle and giving a second reward; and the line-of-sight curvature control network updates own parameters according to the first reward and the second reward. According to the method, the problems of unstable GPS signals and unreasonable path planning of the unmanned aerial vehicle under the conditions of complex electromagnetic environment, topographic conditions or blue interference are effectively solved, stable flight and accurate task execution can still be realized, and the safety and stability of the unmanned aerial vehicle are improved.

Description

Technical Field

[0001] The present invention relates to an anti-interference unmanned aerial vehicle intelligent path planning method and system, belonging to the field of artificial intelligence technology. Background Art

[0002] Chinese invention patent application publication number CN118963388A discloses an autonomous flight control system for drones that does not require external navigation. It primarily relies on the Global Positioning System (GPS) for positioning and employs algorithms such as the A* algorithm for path planning. However, in complex environments or with interference, these technologies can suffer from inaccurate positioning and illogical path planning. For example, in urban areas with tall buildings or dense forests, GPS signals may be blocked or reflected, resulting in reduced positioning accuracy. Furthermore, GPS devices may not function properly when encountering electromagnetic interference, such as near high-voltage power lines or in areas with strong magnetic fields, further impacting the drone's positioning capabilities.

[0003] In addition to the localization issue, existing path planning algorithms also have limitations when it comes to obstacle avoidance and optimization in complex environments. While the A* algorithm can find the shortest path from a starting point to a destination, its efficiency decreases significantly when faced with dynamic obstacles. Summary of the Invention

[0004] The purpose of the present invention is to provide an anti-interference UAV intelligent path planning method and system, which ensures that the UAV can effectively solve the problems of unstable GPS signals and unreasonable path planning in complex electromagnetic environments, terrain conditions or blue party interference, and still achieve stable flight and precise mission execution, thereby improving the safety and stability of the UAV.

[0005] To achieve the above-mentioned purpose, the present invention provides an anti-interference UAV intelligent path planning method, which includes: Step 1: The drone controls the network based on the line of sight curvature of the control module The generated flight instructions are used to fly, where is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the UAV to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector to the target at time k, is the distance from the UAV to the destination at time k The estimated distance from the drone to the destination at time k+1 difference; is the state of the UAV relative to the obstacle at time k , is the unit vector of the UAV’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; Step 2: Processor’s First Reward Function Evaluate the distance between the drone and the target to get the first reward. is the parameter of the first reward function; Step 3: Processor’s Second Reward Function Evaluate the distance between the drone and the obstacle to get the second reward. is the parameter of the second reward function; Step 4: Line of sight curvature control network Update its own parameters according to the first reward and the second reward.

[0006] To achieve the above-mentioned purpose, the present invention also provides an anti-interference UAV intelligent path planning system, which includes a processor, the processor includes a line of sight curvature control network , the first reward function and the second reward function , is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the UAV to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector of the UAV relative to the target at time k, is the distance between the UAV and the target at time k The estimated distance between the drone and the target at time k+1 difference; is the state of the UAV relative to the obstacle at time k , is the unit vector of the UAV’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; is the parameter of the first reward function, are the parameters of the second reward function, where the UAV flies according to the flight instructions generated by the line of sight curvature control network. The first reward function is used to evaluate the state of the UAV relative to the target at time k and give a first reward. The second reward function is used to evaluate the state of no UAV relative to the obstacle at time k and give a second reward. The line of sight curvature control network updates its own parameters based on the first and second rewards.

[0007] Compared with the existing technology, the anti-interference UAV intelligent path planning system and method provided by the present invention ensure that the UAV can effectively solve the problems of unstable GPS signals and unreasonable path planning in complex electromagnetic environments, terrain conditions or blue party interference, and can still achieve stable flight and precise mission execution, thereby improving the safety and stability of the UAV. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a block diagram of the anti-interference UAV intelligent path planning system provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0009] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0010] Figure 1 This is a block diagram of the anti-interference UAV intelligent path planning system provided by the first embodiment of the present invention. Figure 1 As shown, the first embodiment of the present invention provides an anti-interference UAV intelligent path planning system, which includes a sensor array, an infrared camera, a rate gyroscope, and an accelerometer. The navigation system identifies the UAV's line of sight unit vector to the target, the UAV's line of sight unit vector to the obstacle, the distance between the UAV and the target, and the distance between the UAV and the obstacle based on data provided by the infrared camera, and outputs these to the processor. The navigation system also monitors the UAV's position, orientation, translation, rotational speed, and acceleration based on data provided by the rate gyroscope and accelerometer, and determines the rotation rate of the UAV's line of sight to the target and the rotation rate of the UAV's line of sight to the obstacle in combination with the data provided by the infrared camera, and then provides the processor.

[0011] In the first embodiment of the present invention, the processor includes a line of sight curvature control network , the first reward function and the second reward function , is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the UAV to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector of the UAV relative to the target at time k, is the distance from the UAV to the destination at time k The estimated distance from the drone to the destination at time k+1 difference; is the state of the UAV relative to the obstacle at time k , is the unit vector of the UAV’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; is the parameter of the first reward function, are the parameters of the second reward function, where the UAV flies according to the flight instructions generated by the line of sight curvature control network. The first reward function is used to evaluate the state of the UAV relative to the target at time k and give a first reward. The second reward function is used to evaluate the state of no UAV relative to the obstacle at time k and give a second reward. The line of sight curvature control network updates its own parameters based on the first and second rewards.

[0012] The anti-interference UAV intelligent path planning system provided in the first embodiment of the present invention also includes a controller and a flight mechanism. The processor provides the flight instructions provided by the line of sight curvature control network to the controller, and the controller generates flight instructions for the flight mechanism based on the flight instructions.

[0013] In the present invention, the unit vector of the drone's line of sight to the target, the unit vector of the drone's line of sight to the obstacle, the rotation rate of the drone's line of sight to the target, the rotation rate of the drone's line of sight to the obstacle, the distance between the drone and the target, and the distance between the drone and the obstacle are all obtained by the drone's onboard sensor array and navigation system, and no GPS positioning system is required to provide any information.

[0014] The anti-interference UAV intelligent path planning system provided in the first embodiment of the present invention further includes a communication unit, and the UAV communicates with the ground terminal through the communication unit.

[0015] In the present invention, and The resultant vector is the velocity vector of the UAV. In the present invention, the obstacles include: high buildings, trees, etc.

[0016] In the first embodiment, the training of the drone includes the following process: S1-1: Make , ; S1-2: , T is the number of training times; ; S1-3: Get the state of the drone relative to the target at time k and the state of obstacles ; S1-4: Get the flight instructions of the drone according to the following formula : ; S1-5: According to flight instructions Estimate the drone's state relative to the target at the next time k+1 and the state of obstacles , and get the first reward and the second reward ; S1-6: , ; S1-7: Judgement, if If it is zero, then execute step S1-8; if not, then return to step S1-4; S1-8: Make the first cumulative return , Otherwise, the first cumulative return , so that the second cumulative return ; S1-9: ; S1-10: If , then execute step S1-12, otherwise execute step S1-11; S1-11: , , , , , Then, make And return to step S1-10, and is the learning rate; S1-12: , , , and judge Is it established? If yes, then end the training. If not, return to step S1-2. The number of training sessions designed.

[0017] In the first embodiment, the distance between the drone and the target at time k is The estimated distance between the drone and the target at time k+1 difference is a positive value, is a positive value, otherwise it is zero; the distance between the drone and the obstacle Greater than or equal to the threshold, is a positive value, otherwise it is zero.

[0018] In the first embodiment, the communication unit includes a transmitting module and a receiving module. The transmitting module is used to transmit information acquired by the drone to the ground terminal. The ground terminal also includes a communication unit, which also includes a transmitting module and a receiving module. The transmitting module of the ground terminal and the drone are identical in composition, and the receiving module of the ground terminal and the drone are identical in composition. Using a drone as an example, the transmitting module includes an encryption module, a modulator, a high-frequency power amplifier, and a transmitting antenna. The encryption module implements the following process: S2-1: Convert the information obtained by the drone into binary numbers to generate a binary string, and divide the binary string into multiple groups, each group includes 2 M bit code, M is a positive integer greater than or equal to 3; S2-2: 2 M The bit codes are arranged according to the self-defined confidentiality rules to obtain the first order digital signal, and the first order digital signal is divided into 2 M-1 Group, and then input to the first level of M-level encryption iteration; the i-th level encryption iteration includes 2 M-i The i-th encrypted butterfly unit, i=1,…,M; the i-th encrypted butterfly unit includes 2 i input terminals and 2 i output terminals; S2-3: The outputs of the two i-1-shaped encryption butterfly units of the i-1-th level encryption iteration are used as the inputs of the i-th shape encryption butterfly unit of the i-th level encryption iteration, wherein the 2 of the second i-1-shaped encryption butterfly unit of the two i-1-shaped encryption butterfly units is used as the input of the i-th shape encryption butterfly unit of the i-th level encryption iteration. i-1 output and rotation factors Multiply and then add 2 of the first i-1 encrypted butterfly unit in the two i-1 encrypted butterfly units. i-1 The output is the 2 of the i-th encrypted butterfly unit i-1outputs, 2 of the second i-1 encrypted butterfly unit in the two i-1 encrypted butterfly units i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1 encrypted butterfly unit is added to obtain the other two i-th encrypted butterfly units. i-1 outputs; S2-4: 2 of 1 M-th encryption butterfly unit of the M-th level encryption iteration M The outputs are used as encryption symbols respectively.

[0019] The modulator will 2 M The encrypted symbols are modulated onto a carrier frequency and amplified by a high frequency power amplifier and then transmitted into space through an antenna. M The encrypted symbols are modulated onto multiple carrier frequencies, amplified by multiple high-frequency power amplifiers, and then provided to multiple antennas for transmission into space.

[0020] When the encryptor of the sending module changes 2 M When an encrypted symbol is modulated onto a carrier frequency and amplified by a high-frequency power amplifier and then transmitted into space through an antenna, the receiving unit includes a receiving antenna, a high-frequency small-signal amplifier, a mixer, a demodulator and a decryption module. The receiving antenna converts the received space electromagnetic waves into high-frequency small signals, which are then amplified by the high-frequency small-signal amplifier and then provided to the mixer; the mixer mixes the amplified high-frequency small signal with the local oscillator signal to generate an intermediate frequency signal; the demodulator extracts the encrypted symbol from the intermediate frequency signal and then decrypts it through the decryption module.

[0021] When the encryptor of the sending module changes 2 M When the encrypted symbols are modulated onto multiple carrier frequencies, amplified by multiple high-frequency power amplifiers, and then provided to multiple antennas for transmission into space, the receiving unit includes multiple receiving antennas, multiple high-frequency small-signal amplifiers, multiple mixers, multiple demodulators, a combiner, and a decryption module. Each receiving antenna receives the electromagnetic wave corresponding to the carrier sent by the transmitting module, which is then amplified by the small-signal amplifier and generated as an intermediate frequency signal by the mixer. The demodulator extracts the encrypted symbols sent by the transmitter, and the combiner combines the encrypted symbols extracted by multiple demodulators and then provides them to the decryption module.

[0022] The decryption module implements the following process: S3-1 will 2 M The encrypted symbols are arranged according to the decryption rules to obtain the second order of encrypted symbols, and the second order of encrypted symbols are divided into 2 M-1 The group is then input to the first level of the M-level decryption iteration; the i-th level decryption iteration includes 2 M-iThe i-th decryption butterfly unit, i=1,…,M; the i-th decryption butterfly unit includes 2 i input terminals and 2 i output terminals; The outputs of the two i-1-shaped decryption butterfly units of the i-1-th level decryption iteration are used as the inputs of the i-th decryption butterfly unit of the i-th level decryption iteration, wherein the 2 of the second i-1-shaped decryption butterfly unit of the two i-1-shaped decryption butterfly units is used as the input of the i-th decryption butterfly unit of the i-th level decryption iteration. i-1 The outputs are respectively related to the rotation factors Multiply and then add the 2 of the first i-1 decryption butterfly unit of the two i-1 decryption butterfly units. i-1 The output is the 2 of the i-th decryption butterfly unit i-1 outputs; 2 i-1 decryption butterfly units of the second i-1 decryption butterfly unit 2 i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1 decryption butterfly unit of the two i-1 decryption butterfly units is added to obtain the other two i-th decryption butterfly units. i-1 outputs; S3-3: 2 of 1 M-th decryption butterfly unit of the M-th level decryption iteration M The output is the plaintext binary bit code sent by the ground station.

[0023] In the present invention, when the ground terminal and the UAV communicate, the code is read according to the customized confidentiality rules and the encrypted symbols are read according to the decryption rules, thus preventing the blue army from stealing and interfering with the information.

[0024] The present invention uses the above technical solution to ensure that the UAV can effectively solve the problems of unstable GPS signals and unreasonable path planning in complex electromagnetic environments, terrain conditions or blue party interference, and can still achieve stable flight and precise mission execution, thereby improving the safety and stability of the UAV.

[0025] Second embodiment

[0026] The second embodiment of the present invention only describes the contents that are different from the first embodiment, and the same contents are not repeated.

[0027] A second embodiment of the present invention provides an anti-interference UAV intelligent path planning method, which includes the following steps: Step 1: The drone controls the network based on the processor's line of sight curvature The generated flight instructions are used to fly, where is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the UAV to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector to the target at time k, is the distance from the UAV to the destination at time k The estimated distance from the drone to the destination at time k+1 difference; is the state of the UAV relative to the obstacle at time k , is the unit vector of the UAV’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; Step 2: Processor’s First Reward Function Evaluate the distance between the drone and the target to get the first reward. is the parameter of the first reward function; Step 3: Processor’s Second Reward Function Evaluate the distance between the drone and the obstacle to get the second reward. is the parameter of the second reward function; Step 4: Line of sight curvature control network Update its own parameters according to the first reward and the second reward.

[0028] The beneficial effects of the anti-interference UAV intelligent path planning method provided by the second embodiment of the present invention are the same as those of the first embodiment and will not be repeated here.

[0029] Third embodiment

[0030] A third embodiment of the present invention provides a computer program product comprising computer program codes, wherein the computer program codes can be invoked by a processor to execute the method of the second embodiment.

[0031] The beneficial effects of the computer program product provided by the third embodiment of the present invention are the same as those of the second embodiment and will not be described again here.

[0032] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined. "Several" means one or more, unless otherwise specifically defined.

[0033] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An anti-interference UAV intelligent path planning method, characterized in that: Follow these steps: Step 1: The drone controls the network based on the line of sight curvature of the processor Generates instructions to fly, where is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the drone to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector to the target at time k, is the distance from the drone to the destination at time k The estimated distance from the drone to the destination at time k+1 difference; is the state of the drone with respect to the obstacle at time k , is the unit vector of the drone’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; Step 2: Processor’s First Reward Function Evaluate the distance between the drone and the target to get the first reward. is the parameter of the first reward function; Step 3: Second Reward Function for Processor Evaluate the distance between the drone and the obstacle to get the second reward. is the parameter of the second reward function; Step 4: Line of sight curvature control network Update its own parameters according to the first reward and the second reward.

2. The anti-interference UAV intelligent path planning method according to claim 1 is characterized in that: The training of drones includes the following process: S1-1: Make , ; S1-2: , T is the number of training times; ; S1-3: Get the state of the drone relative to the target at time k and the state of obstacles ; S1-4: Get the flight instructions of the drone according to the following formula : ； S1-5: According to flight instructions Estimate the state of the drone at the target location at the next time k+1 and the state of obstacles , and get the first reward and the second reward ; S1-6： ， ; S1-7: Judgement, if If it is zero, then execute step S1-8, if not, then return to step S1-4; S1-8: Make the first cumulative return , ; Otherwise, make the first cumulative return , so that the second cumulative return ; S1-9： ; S1-10: If , then execute step S1-12, otherwise execute step S1-11; S1-11： , ， ， , , Then, make And return to step S1-10, and is the learning rate; S1-12: , , , and judge Is it true? If yes, end the training. If not, return to step S1-2. The number of training sessions designed.

3. The anti-interference UAV intelligent path planning method according to claim 2 is characterized in that: The distance between the drone and the target at time k The estimated distance between the drone and the target at time k+1 difference is a positive value, is a positive value, otherwise it is zero; the distance between the drone and the obstacle Greater than or equal to the threshold, is a positive value, otherwise it is zero.

4. The anti-interference UAV intelligent path planning method according to claim 3 is characterized in that: It also includes encrypting the target information obtained by the drone. The encryption process is as follows: S2-1: Convert the information obtained by the drone into binary numbers to generate a binary string, and divide the binary string into multiple groups, each group includes 2 M bit code, M is a positive integer greater than or equal to 3; S2-2: 2 M The bit codes are arranged according to the self-defined confidentiality rules to obtain the first-order digital signal, and the first-order digital signal is divided into 2 M-1 The group is then input into the first level of the M-level encryption iteration; the i-th level encryption iteration includes 2 M-i The i-th encrypted butterfly unit includes 2 i input terminals and 2 i Output terminals; S2-3: The outputs of the two i-1-shaped encryption butterfly units of the i-1-th level encryption iteration are used as the inputs of the i-th-shaped encryption butterfly unit of the i-th level encryption iteration, wherein the 2 of the second i-1-shaped encryption butterfly unit of the two i-1-shaped encryption butterfly units is used as the input of the i-th-shaped encryption butterfly unit of the i-th level encryption iteration. i -1 output and rotation factors Multiply them and then add the 2 of the first i-1 encrypted butterfly unit in the two i-1 encrypted butterfly units. i-1 The output is 2 of the i-th encrypted butterfly unit i-1 output, 2 of the second i-1-shaped encryption butterfly unit in the 2 i-1-shaped encryption butterfly units i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1-shaped encryption butterfly unit in the two i-1-shaped encryption butterfly units is added to obtain the other 2 i-shaped encryption butterfly units. i-1 Outputs; S2-4: 2 of 1 M-th encryption butterfly unit of M-th level encryption iteration M The outputs are used as encryption symbols respectively.

5. The anti-interference UAV intelligent path planning method according to claim 4 is characterized in that: Also includes: The drone decrypts the information sent by the ground station. The decryption process includes: S3-1: will receive 2 M The encrypted symbols are arranged according to the decryption rules to obtain the second order of 2 M Encrypted symbols, the second order of 2 M The encryption symbol is divided into 2 M-1 The group is then input to the first level of the M-level decryption iteration; the i-th level decryption iteration includes 2 M-i The i-th decryption butterfly unit includes 2 i input terminals and 2 i Output terminals; S3-2: The outputs of the two i-1-shaped decryption butterfly units of the i-1-th level decryption iteration are used as the inputs of the i-th decryption butterfly unit of the i-th level decryption iteration, wherein the two i-1-shaped decryption butterfly units of the second i-1-shaped decryption butterfly unit of the two i-1-shaped decryption butterfly units are used as the inputs of the i-th decryption butterfly unit of the i-th level decryption iteration. i-1 The outputs are respectively related to the rotation factors Multiply and then add the 2 of the first i-1 decryption butterfly unit of the two i-1 decryption butterfly units. i-1 The output is 2 of the i-th decrypted butterfly unit i-1 outputs; 2 i-1 decryption butterfly units of the second i-1 decryption butterfly unit 2 i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1 decryption butterfly unit of the two i-1 decryption butterfly units is added to obtain the other two i-th decryption butterfly units. i-1 Outputs; S3-3: 2 of 1 M-th decryption butterfly unit of the M-th decryption iteration M The output is the plaintext binary bit code sent by the ground station. 6.An anti-interference UAV intelligent path planning system, characterized in that: Including a processor, the processor includes a line of sight curvature control network , the first reward function and the second reward function , is the flight instruction of the UAV at time k, is the state of the UAV at the target location at time k, , are the parameters of the line of sight curvature control network, is the sight unit vector of the drone to the target at time k, is the rotation rate of the UAV’s sight line to the target at time k, is the velocity vector of the UAV relative to the target at time k, is the distance from the drone to the destination at time k The estimated distance from the drone to the destination at time k+1 difference; is the state of the drone with respect to the obstacle at time k , is the unit vector of the drone’s line of sight to the obstacle at time k, is the rotation rate of the UAV’s line of sight to the obstacle at time k, The velocity vector of the drone relative to the obstacle at time k, is the distance between the UAV and the obstacle at time k; Parameters of the line of sight curvature control network; is the parameter of the first reward function, is the parameter of the second reward function, wherein the UAV flies according to the instructions generated by the line of sight curvature control network, the first reward function is used to evaluate the state of the UAV relative to the target at time k and give a first reward, and the second reward function is used to evaluate the state of the UAV relative to the obstacle at time k and give a second reward; the line of sight curvature control network updates its own parameters according to the first reward and the second reward.

7. The anti-interference UAV intelligent path planning system according to claim 6 is characterized in that: The training of drones includes the following process: S1-1: Make , ; S1-2: , T is the number of training times; ; S1-3: Get the state of the drone relative to the target at time k and the state of obstacles ; S1-4: Get the flight instructions of the drone according to the following formula : ； S1-5: According to flight instructions Estimate the state of the drone at the target location at the next time k+1 and the state of obstacles , and get the first reward and the second reward ; S1-6： ， ; S1-7: Judgement, if If it is zero, then execute step S1-8, if not, then return to step S1-4; S1-8: Make the first cumulative return , ; Otherwise, make the first cumulative return , so that the second cumulative return ; S1-9： ; S1-10: If , then execute step S1-12, otherwise execute step S1-11; S1-11： , ， ， , , Then, make And return to step S1-10, and is the learning rate; S1-12: , , , and judge Is it true? If yes, end the training. If not, return to step S1-2. The number of training sessions designed.

8. The anti-interference UAV intelligent path planning system according to claim 7 is characterized in that: The distance between the drone and the target at time k The estimated distance between the drone and the target at time k+1 difference is a positive value, is a positive value, otherwise it is zero; the distance between the drone and the obstacle Greater than or equal to the threshold, is a positive value, otherwise it is zero.

9. The anti-interference UAV intelligent path planning system according to claim 8 is characterized in that: It also includes a communication unit, the communication unit includes a signaling module, the signaling module includes an encryption module, and the encryption module implements the following process: S2-1: Convert the information obtained by the drone into binary numbers to generate a binary string, and divide the binary string into multiple groups, each group includes 2 M bit code, M is a positive integer greater than or equal to 3; S2-2: 2 M The bit codes are arranged according to the self-defined confidentiality rules to obtain the first-order digital signal, and the first-order digital signal is divided into 2 M-1 The group is then input into the first level of the M-level encryption iteration; the i-th level encryption iteration includes 2 M-i The i-th encrypted butterfly unit includes 2 i input terminals and 2 i Output terminals; S2-3: The outputs of the two i-1-shaped encryption butterfly units of the i-1-th level encryption iteration are used as the inputs of the i-th-shaped encryption butterfly unit of the i-th level encryption iteration, wherein the 2 of the second i-1-shaped encryption butterfly unit of the two i-1-shaped encryption butterfly units is used as the input of the i-th-shaped encryption butterfly unit of the i-th level encryption iteration. i -1 output and rotation factors Multiply them and then add the 2 of the first i-1 encrypted butterfly unit in the two i-1 encrypted butterfly units. i-1 The output is 2 of the i-th encrypted butterfly unit i-1 output, 2 of the second i-1-shaped encryption butterfly unit in the 2 i-1-shaped encryption butterfly units i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1-shaped encryption butterfly unit in the two i-1-shaped encryption butterfly units is added to obtain the other two i-shaped encryption butterfly units. i-1 Outputs; S2-4: 2 of 1 M-th encryption butterfly unit of M-th level encryption iteration M The outputs are used as encryption symbols respectively.

10. The anti-interference UAV intelligent path planning system according to claim 9 is characterized in that: The communication unit includes a receiving module, the receiving module includes a decryption module, and the decryption module implements the following process: S3-1: will receive 2 M The encrypted symbols are arranged according to the decryption rules to obtain the second order of 2 M Encrypted symbols, the second order of 2 M The encryption symbol is divided into 2 M-1 The group is then input to the first level of the M-level decryption iteration; the i-th level decryption iteration includes 2 M-i The i-th decryption butterfly unit includes 2 i input terminals and 2 i Output terminals; S3-2: The outputs of the two i-1-shaped decryption butterfly units of the i-1-th level decryption iteration are used as the inputs of the i-th decryption butterfly unit of the i-th level decryption iteration, wherein the two i-1-shaped decryption butterfly units of the second i-1-shaped decryption butterfly unit of the two i-1-shaped decryption butterfly units are used as the inputs of the i-th decryption butterfly unit of the i-th level decryption iteration. i-1 The outputs are respectively related to the rotation factors Multiply and then add the 2 of the first i-1 decryption butterfly unit i-1 The output is 2 of the i-th decrypted butterfly unit i-1 outputs; 2 i-1 decryption butterfly units of the second i-1 decryption butterfly unit 2 i-1 The outputs are respectively related to the rotation factors After multiplication and negation, the output of the first i-1 decryption butterfly unit of the two i-1 decryption butterfly units is added to obtain the other two i-th decryption butterfly units. i-1 Outputs; S3-3: 2 of 1 M-th decryption butterfly unit of the M-th decryption iteration M The output is the plaintext binary bit code sent by the ground station.

Images