CPG gait generation control method and system of amphibious electric power inspection robot

Abstract

The invention discloses a CPG gait generation control method and system of an amphibious electric power inspection robot, and relates to the technical field of inspection robots. The method comprises the following steps: setting 2N Hopf oscillators as initial oscillation units; a CPG coupling neural network is established, so that the 2N Hopf oscillators are mutually coupled; generating a final periodic oscillation signal by taking the coupled oscillation signal as an input and combining an x-direction signal of an input vector of an external planner; and converting the periodic oscillation signal into a motor control signal through a gait mapping algorithm of the robot. Through an innovative CPG gait generation control algorithm, the input direction vector of an external planner is converted into the action gait of the robot in real time, in each control period, the algorithm can recalculate the oscillation angle frequency and the control signal increment according to the actual motion state of the robot and an external input signal, and the action gait of the robot is obtained. Therefore, the optimal gait meeting the current environment and task requirements is generated, and the robot has the timely and flexible control effect.

Description

Technical Field

[0001] This invention relates to the field of inspection robot technology, specifically to a CPG gait generation and control method and system for an amphibious power inspection robot. Background Technology

[0002] With the increasing demand for inspections in complex water-land mixed areas such as intertidal zones, swamps, narrow rivers, and substations in the power operation and maintenance field, traditional single-scenario dedicated inspection equipment, such as land wheeled robots and underwater propeller robots, suffers from poor terrain adaptability and limited motion modes. This makes continuous operation difficult in various scenarios, including land gravel, water surface, underwater, and water-land transition zones. Furthermore, some amphibious robots, relying on multiple independent drive mechanisms, result in bulky bodies, further restricting their operational capabilities in confined spaces (such as cable trenches and equipment gaps) during power inspections. Therefore, there is an urgent need for integrated inspection equipment with multi-environment mobility. To address this, the 12-DOF amphibious hexapod robot, with its reusable leg mechanism hardware, has become an important platform for adapting to such complex scenarios. This type of amphibious robot, with its targeted design, can theoretically achieve land walking, water surface floating, underwater diving, and underwater obstacle crossing. Gait generation algorithms, as the core of the robot's control algorithm, act as a bridge between the external controller and the robot's actions, and are indispensable in the overall robot design.

[0003] Existing CPG (Central Pattern Generator) control models are mostly developed for single motion modes and cannot take into account gait stability and efficiency in multiple scenarios. Existing CPG models cannot well parse and respond to the direction commands of external planners, especially in complex environments that require frequent turning. This inconsistency will lead to a significant reduction in path tracking accuracy. To address this, this invention proposes a CPG gait generation and control method and system for amphibious power inspection robots. Summary of the Invention

[0004] The purpose of this invention is to provide a CPG gait generation and control method and system for an amphibious power inspection robot, which can dynamically adapt to multiple water and land scenarios and adjust the navigation direction in a timely manner according to an external planner.

[0005] According to a first aspect of the present invention, in order to achieve the above-mentioned objective, the present invention provides the following technical solution: a CPG gait generation and control method for an amphibious power inspection robot, comprising the following steps: 2N Hopf oscillators are set as the initial oscillation units, corresponding to the N values ​​of the multi-legged robot. N leg joint motors are used to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. A CPG coupled neural network is established based on the output oscillation signal, so that 2N Hopf oscillators are coupled to each other, and the coupled oscillation signal is output. The CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector of the external planner to generate the final periodic oscillating signal. The periodic oscillation signal is taken as input and converted into a motor control signal by the robot's gait mapping algorithm, and then input into the motor for control. Using the robot's actual motor state as input, the gait mapping algorithm is used to inversely map it into a CPG periodic oscillation signal, which is then fed back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, the CPG periodic oscillation signal of the current control cycle is adjusted in real time, thereby forming a closed-loop control.

[0006] Furthermore, the 2N Hopf oscillator units are configured as follows: (in i =1,2….,2N), where u i For the first i Oscillator signal x coordinate, v i For the first i Oscillator signal y The coordinates are as follows: the first N coordinates correspond to the oscillation units of the leg and foot drive joints, and the last N+1 to 2N coordinates correspond to the oscillation units of the hip joints.

[0007] Furthermore, a CPG coupled neural network is established based on the output oscillation signal, so that N Hopf oscillators are coupled to each other, and the coupled oscillation signal is output as follows: A CPG coupled neural network is established to couple 2N Hopf oscillators to each other. The coupling method is achieved by setting the expected phase difference between the i-th and j-th oscillator units. To establish coupling factors The coupling factor is: Therefore, the oscillating output signal after coupling is: In the formula, M is the time-dependent differential component of the output oscillation signal, σ is the convergence factor, R is the radius of the limit cycle, ω is the oscillation angular frequency, and λ is the coupling coefficient. In each control cycle, the coefficient of the previous cycle is... Adding M to the base generates the control signal for this cycle.

[0008] Furthermore, the CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector from the external planner to generate the final periodic oscillating signal, as follows: Setting parameters α i Its value is: in Input vectors for the external planner x Directional signals primarily affect the robot's turning direction. α 0 represents the motor center angle corresponding to the initial stride length of a single-leg movement, and the final output signal is... .

[0009] Furthermore, the CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector from the external planner to generate the final periodic oscillating signal, as follows: in, i i1 The control angle of the leg joint drive motor corresponds to the first to the Nth oscillation signal; i i2 The desired angle of the hip joint drive motor corresponds to the (N+1)th to the 2Nth oscillation signal; parameters k This helps to speed up the lifting process; under the same control parameters, k The larger the hip, the faster the hip joint lifts up; i 2max Determines the maximum angle of the hip joint. i 2min The initial angle of the hip joint motor when one leg is in the support phase. oh ω is the oscillation angular frequency.

[0010] Furthermore, taking the robot's actual motor state as input, it is inversely mapped to a CPG periodic oscillation signal through a gait mapping algorithm, and fed back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, the CPG periodic oscillation signal of this control cycle is adjusted in real time, thereby forming a closed-loop control, as follows: First, put all the drive joints i i ( i =1,2…2N) The actual Hopf oscillator unit signal at the end of the current control cycle is calculated by inverse mapping according to the gait mapping algorithm. And input vectors to the external planner y Direction signal Combined with the initial oscillation angular frequency oh0 Generates the current oscillation angular frequency: This regenerates the increment of the current control cycle. M This generates the control signal for the current control cycle.

[0011] According to a second aspect of the present invention, the present invention provides a CPG gait generation and control system for an amphibious power inspection robot, used to implement the CPG gait generation and control method for an amphibious power inspection robot described in the first aspect, comprising: The signal acquisition module is used to set 2N Hopf oscillators as initial oscillation units, which correspond to N hip joint motors and N leg joint motors of the multi-legged robot, respectively, and are used to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. The signal coupling module is used to establish a CPG coupled neural network based on the output oscillation signal, so that N Hopf oscillators are coupled to each other and output the coupled oscillation signal. The signal generation module is used by the CPG neural network to generate the final periodic oscillation signal by taking the coupled oscillation signal as input and combining it with the x-direction signal of the input vector of the external planner. The control module is used to take periodic oscillation signals as input, convert them into motor control signals through the robot's gait mapping algorithm, and input them into the motor for control. The control feedback module takes the robot's actual motor state as input, inversely maps it to a CPG periodic oscillation signal through a gait mapping algorithm, and feeds it back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, it adjusts the CPG periodic oscillation signal of the current control cycle in real time, thereby forming a closed-loop control.

[0012] According to a third aspect of the present invention, the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it employs the CPG gait generation and control method for an amphibious power inspection robot described in the first aspect.

[0013] According to a fourth aspect of the present invention, the present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the CPG gait generation control method for an amphibious power inspection robot described in the first aspect.

[0014] According to a fifth aspect of the present invention, the present invention provides a computer program product comprising a computer program, which, when executed by a processor, is used to load and execute the CPG gait generation control method for an amphibious power inspection robot as described in the first aspect.

[0015] This invention has at least the following beneficial effects: 1. This invention uses an innovative CPG gait generation control algorithm to convert the input direction vector of the external planner into the robot's gait in real time, enabling the robot to have timely and flexible control effects and achieve true multi-environment adaptive motion capability.

[0016] 2. Traditional amphibious robots typically require multiple independent drive mechanisms to adapt to different environments, resulting in complex structures and high costs. This invention, through a unified CPG control algorithm, achieves optimized utilization of a single drive mechanism in different environments, significantly simplifying the robot's mechanical structure. This design makes the robot body more compact, enabling it to easily navigate narrow spaces between electrical equipment.

[0017] 3. By establishing a CPG coupled neural network and a gait mapping algorithm, this invention enables efficient adjustment and optimization of robot gait. Within each control cycle, the algorithm recalculates the oscillation angular frequency and control signal increment based on the robot's actual motion state and external input signals, thereby generating the optimal gait adapted to the current environment and task requirements. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the control method described in this invention; Figure 2 This is a schematic diagram of the overall structure of the 12-DOF amphibious hexapod robot in this invention. Figure 3 This is a simplified kinematic diagram of the single-leg structure of the 12-DOF amphibious hexapod robot in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0020] Example 1: Please see Figure 1-Figure 3 This invention provides a technical solution: a CPG gait generation and control method for an amphibious power inspection robot, comprising the following steps: S1. Set 2N Hopf oscillators as initial oscillation units, corresponding to N hip joint motors and N leg joint motors of the multi-legged robot, respectively, to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. Regarding the technical solution of this embodiment, the robot used in this embodiment has six legs symmetrically distributed on both sides, and each leg has a hip joint drive motor and a leg joint drive motor, for example, attached... Figure 2 The robot shown has two degrees of freedom on each leg: rotational freedom and translational freedom at the hip joint, for a total of 12 degrees of freedom. The end legs adopt a biomimetic design and integrate a water-land interactive motion mechanism, which is used through the same drive mechanism. Its main body is composed of rigid fan-shaped feet and flexible biomimetic fins.

[0021] Regarding the technical solution of this embodiment, the 12 Hopf oscillator oscillation units are configured as follows: (in i =1,2….,12), where u i For the first i Oscillator signal x coordinate, v i For the first i Oscillator signal y The coordinates are as follows: the first six are the oscillation units corresponding to the leg and foot drive joints, and the last six are the oscillation units corresponding to the hip joints. S2. Establish a CPG coupled neural network based on the output oscillation signal, so that 2N Hopf oscillators are coupled to each other, and output the coupled oscillation signal; A CPG coupled neural network is established to couple the 12 Hopf oscillators together. The coupling method is achieved by setting the expected phase difference between the i-th and j-th oscillator units. To establish coupling factors The coupling factor is: Therefore, the oscillating output signal after coupling is: in M To output the time-varying component of the oscillation signal, s The convergence factor is R Let be the radius of the limiting cycle. oh The oscillation angular frequency, l For each control cycle, the coupling coefficient is the coefficient of the previous cycle. Add to the basis MThen the control signal for the cost cycle is generated; The S3.CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector of the external planner to generate the final periodic oscillating signal. CPG neural networks combine external planner input vectors x The direction signal generates the final periodic oscillation signal; parameters are set. α i Its value is: in Input vectors for the external planner x Directional signals primarily affect the robot's turning direction. α 0 represents the motor center angle corresponding to the initial stride length of a single-leg movement. The final output signal is... .

[0022] Next, a kinematic model of the robot is established to serve as the parameter setting basis for the gait mapping algorithm. The rigid body shape of the single leg is simplified, as shown in the attached figure. Figure 3 As shown; The robot's single leg is simplified into a linkage structure, and the rear end of the fan-shaped foot is regarded as the landing point of the toe. P The equivalent length of the hip joint link is... l H The equivalent length of the legs and feet is l L = equal to the equivalent radius of the outer arc of the leg and foot R For ease of study, three coordinate systems are established on the leg and foot mechanism: the base coordinate system {1} which is connected to the torso and is relatively stationary; the hip joint coordinate system {2} which is relatively stationary with respect to the hip joint link; and the leg and foot coordinate system {3} which is relatively stationary with respect to the leg and foot mechanism. There is no rotational transformation between coordinate system {1} and coordinate system {2}, only along... z The axis undergoes a translation transformation, with the origin translated a distance of... k ( i 0+ i 1). Among them, i 0 is defined as the initial mechanical angle of the hip joint drive axis. i 1 represents the rotation angle of the hip joint during movement. k This represents the rotation angle-displacement conversion coefficient, which is a constant and depends only on the equivalent radius of the gear; exist x 3 O 3 z 3. On the projection plane, coordinate system {2} x The axis projection and coordinate system {3} x The included angle of the axis is the leg rotation angle. i 2; Assuming all links are rigid bodies, define the homogeneous transformation matrix between the local coordinate systems. Define the transformation matrix from coordinate system {1} to coordinate system {2}. T 12 And the transformation matrix from coordinate system {2} to coordinate system {3} T 23 The specific definition is as follows: in, R 12 and R 23 It is a three-dimensional rotation matrix. p 12 and p 23 Let be the three-dimensional spatial displacement vector. For ease of calculation, we assume that the coordinate system {3} is along... y 2-axis translation, making O 3 and O 2 overlap, that is p 23 = (0,0,0) T After simplification, we get the point. P Coordinates in coordinate system {3} P 3, and the transformation matrix T 12 and transformation matrix T 23 The results are as follows: The final transformation yields the point. P The coordinates in coordinate system {1} are: P 1: Then, the Jacobian matrix is ​​established using inverse kinematics. J Taking the time derivative of the end coordinates and the rotation angle of the single-leg drive motor, we obtain: in J ij These are the elements of the Jacobian matrix; Now, assuming that the kinetic energy of a single leg remains constant, meaning that the power dissipated by the drive motor in the leg actuator is 0, and all the output power acts as the interaction force with the ground, and since there are only two output torques when the foot contacts the ground during robot walking, the force equation for the i-th leg can be obtained by power conservation: Combining the Jacobian matrix, we obtain the transformation matrix from output torque to ground interaction force: in t i1 The motor outputs torque to the leg and foot joints. t i2 The output torque of the hip joint drive motor is obtained from the output torque when the drive joint interacts with the ground: in, P 0d For the desired position of the end of the leg, P 0f This refers to the actual position of the end of the leg. For the desired end-effector speed, For the actual end-effector speed, each in the matrix... k xp , k yp , k zp , k xd , k yp , k zp These are the proportional control coefficient and the derivative control coefficient, respectively. By establishing the output torque equation, the output torque that each joint drive motor should have at that time can be calculated under the condition of gait control input. S4. Using a periodic oscillation signal as input, the robot's gait mapping algorithm converts it into a motor control signal, which is then input into the motor for control. The periodic oscillation signal is converted into a motor control signal using the robot's gait mapping algorithm and then input into the motor for control. in, i i1 The control angle of the leg joint drive motor corresponds to the 1st to 6th oscillation signals. i i2 This represents the desired angle of the hip joint drive motor, corresponding to the 7th to 12th oscillation signals. Parameters k This helps to speed up the lifting process; under the same control parameters, k The larger the hip, the faster the hip joint lifts up; i 2max Determines the maximum angle of the hip joint. i 2min The initial angle of the hip joint motor when one leg is in the support phase. oh ω is the oscillation angular frequency.

[0023] The obtained control angle can be input into the torque generation matrix to output the motor control torque; S5. Using the robot's actual motor state as input, the gait mapping algorithm is used to inversely map it into a CPG periodic oscillation signal, which is then fed back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, the CPG periodic oscillation signal of this control cycle is adjusted in real time to form a closed-loop control. The robot's actual motor states are inversely mapped to CPG periodic oscillation signals using a gait mapping algorithm, and then fed back to the Hopf oscillator, combined with the input vector from the external planner. y The direction signal adjusts the CPG periodic oscillation signal of the current control cycle in real time, first adjusting all drive joints. i i ( i =1,2…12) Calculate the actual Hopf oscillator unit signal at the end of the current control cycle by inverse mapping using the gait mapping algorithm described above. And input vectors to the external planner y Direction signal Combined with the initial oscillation angular frequency oh 0 Generates the current oscillation angular frequency: This regenerates the increment of the current control cycle. M This generates the control signal for the current control cycle.

[0024] In summary, this invention, through its innovative CPG gait generation and control algorithm, transforms the input direction vector of the external planner into the robot's gait in real time. Within each control cycle, the algorithm recalculates the oscillation angular frequency and control signal increment based on the robot's actual motion state and external input signals, thereby generating the optimal gait that adapts to the current environment and task requirements. This enables the robot to have timely and flexible control effects, achieving true multi-environment adaptive motion capabilities.

[0025] Example 2: This embodiment provides a CPG gait generation and control system for an amphibious power inspection robot, used to implement the CPG gait generation and control method for the amphibious power inspection robot described in Embodiment 1, including: The signal acquisition module is used to set 2N Hopf oscillators as initial oscillation units, which correspond to N hip joint motors and N leg joint motors of the multi-legged robot, respectively, and are used to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. The signal coupling module is used to establish a CPG coupled neural network based on the output oscillation signal, so that N Hopf oscillators are coupled to each other and output the coupled oscillation signal. The signal generation module is used by the CPG neural network to generate the final periodic oscillation signal by taking the coupled oscillation signal as input and combining it with the x-direction signal of the input vector of the external planner. The control module is used to take periodic oscillation signals as input, convert them into motor control signals through the robot's gait mapping algorithm, and input them into the motor for control. The control feedback module takes the robot's actual motor state as input, inversely maps it to a CPG periodic oscillation signal through a gait mapping algorithm, and feeds it back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, it adjusts the CPG periodic oscillation signal of the current control cycle in real time, thereby forming a closed-loop control.

[0026] Example 3: The present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it adopts the CPG gait generation and control method of the amphibious power inspection robot described in Embodiment 1.

[0027] It should be noted that the terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.

[0028] Furthermore, the processor can be a central processing unit (CPU). Of course, depending on the actual use, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be used. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.

[0029] Example 4: The present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the CPG gait generation and control method for the amphibious power inspection robot described in Embodiment 1.

[0030] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0031] Example 5: The present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the CPG gait generation and control method for the amphibious power inspection robot described in Embodiment 1.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0033] For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on," "mounted on," "fixed to," or "set on" another element, it may be directly on the other element or there may be an intermediate element present. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible embodiments.

[0034] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0035] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

Claims

1. A CPG gait generation and control method for an amphibious power inspection robot, applied to an amphibious multi-legged robot, characterized in that, Includes the following steps: 2N Hopf oscillators are set as the initial oscillation units, corresponding to the N hip joint motors and N leg joint motors of the multi-legged robot, respectively, to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. A CPG coupled neural network is established based on the output oscillation signal, so that 2N Hopf oscillators are coupled to each other, and the coupled oscillation signal is output. The CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector of the external planner to generate the final periodic oscillating signal. The periodic oscillation signal is taken as input and converted into a motor control signal through the robot's gait mapping algorithm, and then input into the motor for control. Using the robot's actual motor state as input, the gait mapping algorithm is used to inversely map it into a CPG periodic oscillation signal, which is then fed back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, the CPG periodic oscillation signal of the current control cycle is adjusted in real time, thereby forming a closed-loop control.

2. The CPG gait generation and control method for the amphibious power inspection robot according to claim 1, characterized in that: The 2N Hopf oscillator units are configured as follows: (in i =1,2….,2N), where u i For the first i Oscillator signal x coordinate, v i For the first i Oscillator signal y The coordinates are as follows: the first N coordinates correspond to the oscillation units of the leg and foot drive joints, and the last N+1 to 2N coordinates correspond to the oscillation units of the hip joints.

3. The CPG gait generation and control method for the amphibious power inspection robot according to claim 2, characterized in that: A CPG coupled neural network is established based on the output oscillation signal, so that N Hopf oscillators are coupled to each other, and the coupled oscillation signal is output as follows: A CPG coupled neural network is established to couple 2N Hopf oscillators to each other. The coupling method is achieved by setting the expected phase difference between the i-th and j-th oscillator units. To establish coupling factors The coupling factor is: Therefore, the oscillating output signal after coupling is: In the formula, M is the time-dependent differential component of the output oscillation signal, σ is the convergence factor, R is the radius of the limit cycle, ω is the oscillation angular frequency, and λ is the coupling coefficient. In each control cycle, the coefficient of the previous cycle is... Adding M to the base generates the control signal for this cycle.

4. The CPG gait generation and control method for the amphibious power inspection robot according to claim 3, characterized in that: The CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector from the external planner to generate the final periodic oscillating signal, as follows: Setting parameters α i Its value is: in Input vectors for the external planner x Directional signals primarily affect the robot's turning direction. α 0 represents the motor center angle corresponding to the initial stride length of a single-leg movement, and the final output signal is... .

5. The CPG gait generation and control method for the amphibious power inspection robot according to claim 4, characterized in that: The CPG neural network takes the coupled oscillating signal as input and combines it with the x-direction signal of the input vector from the external planner to generate the final periodic oscillating signal, as follows: in, θ i1 The control angle of the leg joint drive motor corresponds to the first to the Nth oscillation signal; θ i2 The desired angle of the hip joint drive motor corresponds to the (N+1)th to the 2Nth oscillation signal; parameters k This helps to speed up the lifting process; under the same control parameters, k The larger the hip, the faster the hip joint lifts up; θ 2max Determines the maximum angle of the hip joint. θ 2min The initial angle of the hip joint motor when one leg is in the support phase. ω ω is the oscillation angular frequency.

6. The CPG gait generation and control method for the amphibious power inspection robot according to claim 5, characterized in that: Using the robot's actual motor state as input, the gait mapping algorithm inversely maps it to a CPG periodic oscillation signal, which is then fed back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, the CPG periodic oscillation signal for this control cycle is adjusted in real time, thus forming a closed-loop control, as detailed below: First, put all the drive joints θ i ( i =1,2…2N) The actual Hopf oscillator unit signal at the end of the current control cycle is calculated by inverse mapping according to the gait mapping algorithm. And input vectors to the external planner y Direction signal Combined with the initial oscillation angular frequency ω 0 Generates the current oscillation angular frequency: This regenerates the increment of the current control cycle. M This generates the control signal for the current control cycle.

7. A CPG gait generation and control system for an amphibious power inspection robot, used to implement the CPG gait generation and control method for the amphibious power inspection robot as described in any one of claims 1 to 6, characterized in that, include: The signal acquisition module is used to set 2N Hopf oscillators as initial oscillation units, which correspond to N hip joint motors and N leg joint motors of the multi-legged robot, respectively, and are used to output oscillation signals. The multi-legged robot has N legs, and each leg corresponds to one hip joint motor and one leg joint motor. The signal coupling module is used to establish a CPG coupled neural network based on the output oscillation signal, so that N Hopf oscillators are coupled to each other and output the coupled oscillation signal. The signal generation module is used by the CPG neural network to generate the final periodic oscillation signal by taking the coupled oscillation signal as input and combining it with the x-direction signal of the input vector of the external planner. The control module is used to take periodic oscillation signals as input, convert them into motor control signals through the robot's gait mapping algorithm, and input them into the motor for control. The control feedback module takes the robot's actual motor state as input, inversely maps it to a CPG periodic oscillation signal through a gait mapping algorithm, and feeds it back to the Hopf oscillator. Combined with the y-direction signal of the input vector from the external planner, it adjusts the CPG periodic oscillation signal of the current control cycle in real time, thereby forming a closed-loop control.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on the processor. When the processor loads and executes the computer program, it employs the CPG gait generation and control method of the amphibious power inspection robot as described in any one of claims 1 to 6.

9. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the CPG gait generation control method for the amphibious power inspection robot as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, is used to load and execute the CPG gait generation control method for the amphibious power inspection robot as described in any one of claims 1 to 6.

Images