CN118244805B - Control method, device and equipment for bionic robot dolphin - Google Patents
Control method, device and equipment for bionic robot dolphin Download PDFInfo
- Publication number
- CN118244805B CN118244805B CN202410666955.4A CN202410666955A CN118244805B CN 118244805 B CN118244805 B CN 118244805B CN 202410666955 A CN202410666955 A CN 202410666955A CN 118244805 B CN118244805 B CN 118244805B
- Authority
- CN
- China
- Prior art keywords
- control
- dolphin
- intermediate result
- bionic
- control signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241001481833 Coryphaena hippurus Species 0.000 title claims abstract description 129
- 239000011664 nicotinic acid Substances 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 59
- 210000002569 neuron Anatomy 0.000 claims abstract description 64
- 230000033001 locomotion Effects 0.000 claims abstract description 54
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 37
- 230000003592 biomimetic effect Effects 0.000 claims description 32
- 239000013598 vector Substances 0.000 claims description 20
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 210000000006 pectoral fin Anatomy 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000009975 flexible effect Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241001125840 Coryphaenidae Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D13/00—Control of linear speed; Control of angular speed; Control of acceleration or deceleration, e.g. of a prime mover
- G05D13/62—Control of linear speed; Control of angular speed; Control of acceleration or deceleration, e.g. of a prime mover characterised by the use of electric means, e.g. use of a tachometric dynamo, use of a transducer converting an electric value into a displacement
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Toys (AREA)
Abstract
The invention provides a control method, a control device and control equipment for a bionic robot dolphin, and belongs to the technical field of bionic robot control. The control method of the bionic robot dolphin comprises the following steps: acquiring motion speed information and coordinate information of a bionic robot dolphin; obtaining control parameters of the bionic robotic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle; inputting the control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal; and controlling the running state of the bionic robotic dolphin according to the output signal. According to the technical scheme, the control instruction can be responded in time when the bionic dolphin moves, and the movement performance of the bionic dolphin is improved.
Description
Technical Field
The invention relates to the technical field of bionic robot control, in particular to a control method, a control device and control equipment of a bionic robot dolphin.
Background
Conventional boats and submarines typically employ propellers as propulsion mechanisms that not only emit significant noise, but also consume a portion of the energy of the mechanical work in conducting and overcoming drag and damage aquatic organisms as the conventional paddles rotate. At present, most of bionic underwater robots are based on fishes, and a shell and a propelling structure are designed according to the shapes and propelling modes of different aquatic organisms. The propulsion mode can be divided into a central fin/pair fin propulsion mode and a body/tail fin propulsion mode, wherein the central fin/pair fin propulsion mode has higher sailing stability, the body/tail fin propulsion mode can realize higher sailing speed, propulsion performance and energy utilization efficiency are higher, and meanwhile, the body/tail fin propulsion mode can also eliminate huge noise generated by a propeller and has good hiding effect. The dolphin provides main power by means of tail and tail fin swing, the propulsion mode is a typical body/tail fin propulsion mode, the tail fin is driven to swing through bending motion of the tail, and the track of the dolphin tail fin in the swimming process can be approximately regarded as a curve changing according to a sine rule.
In order to truly restore the motion gesture of the dolphin, most of the existing bionic dolphins adopt a multi-joint module driving mode, a power device is arranged in each joint module, and the power device can timely adjust the motion state of the bionic dolphin according to control instructions and in combination with the current environment. In the process, because a plurality of power devices which are required to control the bionic dolphin simultaneously are matched with each other to work, the traditional control mode can not respond to the control instruction in time, so that the motion performance of the bionic dolphin is not high.
Disclosure of Invention
The invention provides a control method, a control device and control equipment for a bionic robotic dolphin, which improve the motion performance of the bionic robotic dolphin.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a control method of a biomimetic robotic dolphin, comprising:
Acquiring motion speed information and coordinate information of a bionic robot dolphin;
Obtaining control parameters of the bionic robotic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
Inputting the control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
And controlling the running state of the bionic robotic dolphin according to the output signal.
Optionally, according to the movement speed information and the coordinate information, obtaining control parameters of the biomimetic robotic dolphin includes:
According to the movement speed information and the coordinate information, the following formula is adopted:
Obtaining a target speed increment;
Wherein, For the target speed increment, x 2、y2、z2 is the target position coordinate data, x 1、y1、z1 is the current position coordinate data of the bionic robotic dolphin, t is the preset time data,The current movement speed of the bionic robot dolphin is the current movement speed of the bionic robot dolphin;
By the formula:
obtaining a target rotation angle;
Wherein, For the rotation angle of the object to be achieved,For the current motion velocity vector of the biomimetic robotic dolphin,And (3) a target position vector of the bionic robotic dolphin.
Optionally, the control model processes the control parameter through a neuron function to obtain an intermediate result, corrects the intermediate result to obtain an output signal, and includes:
Inputting the control parameters into a control model to carry out weighting treatment through a neuron function to obtain an intermediate result;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move.
Optionally, the control parameters are input into a control model to be weighted through a neuron function, so as to obtain an intermediate result, which comprises the following steps:
the control model is generated by a neuron function:
Processing the control parameters to obtain an intermediate result;
wherein f (n i) is an intermediate result; n i=Ai∙x+d1i, 1.ltoreq.i.ltoreq.j, j being the number of neurons in the first hidden layer; a i = [ ]，The weight value from the input layer to the first hidden layer is given; x= [ x 1,x2 ] is an input vector, x 1 =，x2=; D 1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1.
Optionally, correcting the intermediate result to obtain a current intensity control signal and a power-on time interval control signal, including:
According to the intermediate result, the following formula is adopted:
Determining deviation data, wherein E is the deviation data; Is the expected result;
And correcting the intermediate result according to the deviation data to obtain a current intensity control signal and an energizing time interval control signal.
Optionally, correcting the intermediate result according to the deviation data to obtain a current intensity control signal and a power-on time interval control signal, including:
according to the deviation data, the method comprises the following steps of:
Determining weights of the second hidden layer to the output layer and weights of neuron bias values in the second hidden layer, wherein, For the weight from the second hidden layer to the output layer, m=1, 2; Weights for neuron bias values in the second hidden layer; Is the learning rate;
and obtaining a current intensity control signal and a power-on time interval control signal through the neuron function according to the weight from the second hidden layer to the output layer and the weight of the neuron bias value in the second hidden layer.
Optionally, controlling the running state of the biomimetic robotic dolphin according to the output signal includes:
Generating a control pulse signal according to the current intensity control signal and the power-on time interval control signal;
and controlling the running state of the bionic robot dolphin according to the control pulse signal.
The embodiment of the invention also provides a control device of the bionic robotic dolphin, which comprises:
The acquisition module is used for acquiring motion speed information and coordinate information of the bionic robot dolphin;
The production module is used for obtaining control parameters of the bionic robotic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
the determining module is used for inputting the control parameters into the control model for processing to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
And the control module is used for controlling the running state of the bionic robot dolphin according to the output signal.
Optionally, according to the movement speed information and the coordinate information, obtaining control parameters of the biomimetic robotic dolphin includes:
According to the movement speed information and the coordinate information, the following formula is adopted:
Obtaining a target speed increment;
Wherein, For the target speed increment, x 2、y2、z2 is the target position coordinate data, x 1、y1、z1 is the current position coordinate data of the bionic robotic dolphin, t is the preset time data,The current movement speed of the bionic robot dolphin is the current movement speed of the bionic robot dolphin;
By the formula:
obtaining a target rotation angle;
Wherein, For the rotation angle of the object to be achieved,For the current motion velocity vector of the biomimetic robotic dolphin,And (3) a target position vector of the bionic robotic dolphin.
Optionally, the control model processes the control parameter through a neuron function to obtain an intermediate result, corrects the intermediate result to obtain an output signal, and includes:
Inputting the control parameters into a control model to carry out weighting treatment through a neuron function to obtain an intermediate result;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move.
Optionally, the control parameters are input into a control model to be weighted through a neuron function, so as to obtain an intermediate result, which comprises the following steps:
the control model is generated by a neuron function:
Processing the control parameters to obtain an intermediate result;
wherein f (n i) is an intermediate result; n i=Ai∙x+d1i, 1.ltoreq.i.ltoreq.j, j being the number of neurons in the first hidden layer; a i = [ ]，The weight value from the input layer to the first hidden layer is given; x= [ x 1,x2 ] is an input vector, x 1 =，x2=; D 1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1.
Optionally, correcting the intermediate result to obtain a current intensity control signal and a power-on time interval control signal, including:
According to the intermediate result, the following formula is adopted:
Determining deviation data, wherein E is the deviation data; Is the expected result;
And correcting the intermediate result according to the deviation data to obtain a current intensity control signal and an energizing time interval control signal.
Optionally, correcting the intermediate result according to the deviation data to obtain a current intensity control signal and a power-on time interval control signal, including:
according to the deviation data, the method comprises the following steps of:
Determining weights of the second hidden layer to the output layer and weights of neuron bias values in the second hidden layer, wherein, For the weight from the second hidden layer to the output layer, m=1, 2; Weights for neuron bias values in the second hidden layer; Is the learning rate;
and obtaining a current intensity control signal and a power-on time interval control signal through the neuron function according to the weight from the second hidden layer to the output layer and the weight of the neuron bias value in the second hidden layer.
Optionally, controlling the running state of the biomimetic robotic dolphin according to the output signal includes:
Generating a control pulse signal according to the current intensity control signal and the power-on time interval control signal;
and controlling the running state of the bionic robot dolphin according to the control pulse signal.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method described above.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described method.
The scheme of the invention at least comprises the following beneficial effects:
According to the scheme, the motion speed information and the coordinate information of the bionic robotic dolphin are obtained; obtaining control parameters of the bionic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle; inputting the control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through the neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal; the running state of the bionic robot dolphin is controlled according to the output signals, so that the bionic robot dolphin can respond to the control instructions in time when the bionic robot dolphin moves, the movement performance of the bionic robot dolphin is improved, and the movement of the bionic robot dolphin is more natural, efficient and flexible.
Drawings
Fig. 1 is a flowchart of a control method of a biomimetic robotic dolphin provided by an embodiment of the invention;
Fig. 2 is a schematic diagram of a control model of a biomimetic robotic dolphin according to an embodiment of the present invention;
Fig. 3 is a structural diagram of a biomimetic robotic dolphin provided by an embodiment of the present invention;
Fig. 4 is a block diagram of a control system of a biomimetic robotic dolphin provided by an embodiment of the present invention;
Fig. 5 is a structural diagram of a control device for a biomimetic robotic dolphin provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of a computing device provided by an embodiment of the present invention;
The device comprises a horizontal driving device for a tail fin, wherein the horizontal driving device comprises a horizontal driving device for the tail fin; 2. a tail fin vertical drive; 3. a pectoral fin driving device; 50. a control device; 51. an acquisition module; 52. a production module; 53. a determining module; 54. a control module; 60. a computing device; 61. a processor; 62. a memory.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a control method of a biomimetic robotic dolphin, including:
Step 11, obtaining motion speed information and coordinate information of the bionic robot dolphin;
In specific implementation, the obtaining the motion speed information and the coordinate information of the bionic robotic dolphin includes: acquiring the movement speed information of the bionic robot dolphin through a sensor arranged at the head position of the bionic robot dolphin; the coordinate information of the bionic robot dolphin is obtained through a GPS (global positioning system) locator arranged at the head position of the bionic robot dolphin;
Step 12, obtaining control parameters of the bionic robot dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
In specific implementation, the method is realized by the following formula:
Obtaining a target speed increment;
By the formula:
obtaining a target rotation angle;
Wherein, For the target speed increment, x 2、y2、z2 is the target position coordinate data, x 1、y1、z1 is the current position coordinate data of the bionic robotic dolphin, t is the preset time data,For the current movement speed of the biomimetic robotic dolphin,For the rotation angle of the object to be achieved,For the current motion velocity vector of the biomimetic robotic dolphin,And (3) a target position vector of the bionic robotic dolphin.
Step 13, inputting control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through the neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
and 14, controlling the running state of the bionic robot dolphin according to the output signal.
In the embodiment, the motion speed information and the coordinate information of the bionic robot dolphin are obtained through the localizer and the sensor, and the control parameters of the bionic robot dolphin are obtained according to the motion speed information and the coordinate information of the bionic robot dolphin, wherein the control parameters comprise target speed incrementAnd target rotation angleIncrement the target speedAnd target rotation angleInputting a control model to increase the target speed by a neuron functionAnd target rotation angleThe method and the device have the advantages that the control instruction can be responded in time when the bionic dolphin moves, the movement performance of the bionic dolphin is improved, and the bionic dolphin moves more naturally, efficiently and flexibly.
In an alternative embodiment of the present invention, step 13 includes:
Step 131, inputting the control parameters into a control model for weighting treatment through a neuron function to obtain an intermediate result;
Step 132, correcting the intermediate result to obtain a current intensity control signal and an energizing time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move.
In the embodiment, the control parameters are input into a control model to be weighted through a neuron function, so that an intermediate result is obtained; in particular, the control model is implemented by a neuron function:
Processing the control parameters to obtain an intermediate result;
wherein f (n i) is an intermediate result; n i=Ai∙x+d1i, 1.ltoreq.i.ltoreq.j, j being the number of neurons in the first hidden layer; a i = [ ]，The weight value from the input layer to the first hidden layer is given; x= [ x 1,x2 ] is an input vector, x 1 =，x2=; D 1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move; in specific implementation, according to the intermediate result, the following formula is adopted:
Determining deviation data, wherein E is the deviation data; Is the expected result;
By the formula:
Determining weights of the second hidden layer to the output layer and weights of neuron bias values in the second hidden layer, wherein, For the weight from the second hidden layer to the output layer, m=1, 2; Weights for neuron bias values in the second hidden layer; Is the learning rate; and obtaining a current intensity control signal and a power-on time interval control signal through the neuron function according to the weight from the second hidden layer to the output layer and the weight of the neuron bias value in the second hidden layer.
As shown in fig. 2, a target control model comprising 2 input vectors, 2 hidden layers and 2 output vectors, the training process comprises:
Step 31, obtaining training set data comprising running state parameters of a historical bionic robotic dolphin;
step 32, performing feature extraction processing on the training set data to obtain a plurality of input vectors;
step 33, inputting the input vector into an input layer of a control model, and outputting a first intermediate result by the input layer;
Step 34, the first intermediate result output by the input layer is input into the first hidden layer of the control model to be subjected to local response processing, and the second intermediate result is output;
step 35, inputting the second intermediate result into a second hidden layer of the control model for correction processing, and outputting a third intermediate result;
step 36, inputting the third intermediate result into an output layer of the control model, and outputting a network result by the output layer;
Step 37, obtaining the error between the network result and each sample in the training set;
And step 37, weighting the neural network function in the hidden layer according to the error, and performing input and output calculation again until the error is controlled within an allowable precision range, so as to obtain the control model.
In an alternative embodiment of the present invention, step 14 includes:
Step 141, generating a control pulse signal according to the current intensity control signal and the power-on time interval control signal;
And step 142, controlling the running state of the bionic robotic dolphin according to the control pulse signal.
In this embodiment, the target speed of the biomimetic robotic dolphin is incrementedAnd target rotation angleAs input parameters of a target control model, current intensity and a power-on time interval are obtained; taking the obtained current intensity and the energizing time interval as input parameters of a pulse width modulation circuit to obtain a pulse square wave signal for controlling the operation of the bionic dolphin; the obtained pulse square wave signal is used as an input parameter of power amplification equipment to control a plurality of driving devices of the bionic robot dolphin to operate, so that high-precision speed control of the bionic robot dolphin is realized, and the motion performance of the bionic robot dolphin is improved.
The embodiment of the invention provides a control method of a bionic robotic dolphin, which comprises the following steps:
As shown in fig. 3 and 4, the driving device of the bionic robot dolphin comprises a pectoral fin driving device 3, a pectoral fin horizontal driving device 1 and a pectoral fin vertical driving device 2, wherein the pectoral fin driving device 3 is used for balancing the gesture of the bionic robot dolphin and is beneficial to the completion of various flexible actions of the bionic robot dolphin; the tail fin horizontal driving device 1 is used for adjusting the movement direction of the bionic robot dolphin; the tail fin vertical driving device 2 is formed by connecting a plurality of sub driving devices in series, and can generate sine wave-like swing to drive the bionic robot dolphin to advance; the current motion state information of the bionic robot dolphin, including motion speed information and coordinate information, is acquired through a sensor arranged at the head of the bionic robot dolphin, and the controller calculates and obtains the target speed increment according to the target position And target rotation angleIncrement the target speedAnd target rotation angleThe method comprises the steps that as control parameters, the control parameters are input into a controller, the controller generates output signals containing current intensity and a power-on time interval through a neural network function, the obtained current intensity and the power-on time interval are used as input parameters of a pulse width modulation circuit, and a pulse square wave signal for controlling a bionic mechanical dolphin driving device to operate is obtained; and taking the obtained pulse square wave signal as an input parameter of power amplification equipment, and controlling a plurality of driving devices of the bionic robot dolphin to move so as to enable the bionic robot dolphin to move towards a target position.
As shown in fig. 5, an embodiment of the present invention provides a control device 50 for a biomimetic robotic dolphin, where the control device 50 includes:
an acquisition module 51, configured to acquire motion speed information and coordinate information of a biomimetic robotic dolphin;
the production module 52 is configured to obtain control parameters of the biomimetic robotic dolphin according to the motion speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
A determining module 53, configured to input the control parameter into a control model for processing, so as to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
the control module 54 is configured to control an operation state of the biomimetic robotic dolphin according to the output signal.
Optionally, according to the movement speed information and the coordinate information, obtaining control parameters of the biomimetic robotic dolphin includes:
According to the movement speed information and the coordinate information, the following formula is adopted:
Obtaining a target speed increment;
Wherein, For the target speed increment, x 2、y2、z2 is the target position coordinate data, x 1、y1、z1 is the current position coordinate data of the bionic robotic dolphin, t is the preset time data,The current movement speed of the bionic robot dolphin is the current movement speed of the bionic robot dolphin;
By the formula:
obtaining a target rotation angle;
Wherein, For the rotation angle of the object to be achieved,For the current motion velocity vector of the biomimetic robotic dolphin,And (3) a target position vector of the bionic robotic dolphin.
Optionally, the control model processes the control parameter through a neuron function to obtain an intermediate result, corrects the intermediate result to obtain an output signal, and includes:
Inputting the control parameters into a control model to carry out weighting treatment through a neuron function to obtain an intermediate result;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move.
Optionally, the control parameters are input into a control model to be weighted through a neuron function, so as to obtain an intermediate result, which comprises the following steps:
the control model is generated by a neuron function:
Processing the control parameters to obtain an intermediate result;
wherein f (n i) is an intermediate result; n i=Ai∙x+d1i, 1.ltoreq.i.ltoreq.j, j being the number of neurons in the first hidden layer; a i = [ ]，The weight value from the input layer to the first hidden layer is given; x= [ x 1,x2 ] is an input vector, x 1 =，x2=; D 1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1.
Optionally, correcting the intermediate result to obtain a current intensity control signal and a power-on time interval control signal, including:
According to the intermediate result, the following formula is adopted:
Determining deviation data, wherein E is the deviation data; Is the expected result;
And correcting the intermediate result according to the deviation data to obtain a current intensity control signal and an energizing time interval control signal.
Optionally, correcting the intermediate result according to the deviation data to obtain a current intensity control signal and a power-on time interval control signal, including:
according to the deviation data, the method comprises the following steps of:
Determining weights of the second hidden layer to the output layer and weights of neuron bias values in the second hidden layer, wherein, For the weight from the second hidden layer to the output layer, m=1, 2; Weights for neuron bias values in the second hidden layer; Is the learning rate;
and obtaining a current intensity control signal and a power-on time interval control signal through the neuron function according to the weight from the second hidden layer to the output layer and the weight of the neuron bias value in the second hidden layer.
Optionally, controlling the running state of the biomimetic robotic dolphin according to the output signal includes:
Generating a control pulse signal according to the current intensity control signal and the power-on time interval control signal;
and controlling the running state of the bionic robot dolphin according to the control pulse signal.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
As shown in fig. 6, the embodiment of the present invention further provides a computing device 60, which includes a processor 61, a memory 62, and a program or an instruction stored in the memory 62 and capable of running on the processor 61, where the program or the instruction implements each process of the above embodiment of the method for processing synchronization information of a virtual object when executed by the processor 61, and the same technical effects can be achieved, and for avoiding repetition, a detailed description is omitted herein. It should be noted that, the computing device in the embodiment of the present invention includes the mobile electronic device and the non-mobile electronic device described above.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
Stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing the method or the apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
The foregoing is a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention and are intended to be comprehended within the scope of the present invention.
Claims (8)
1. A control method of a biomimetic robotic dolphin, comprising:
Acquiring motion speed information and coordinate information of a bionic robot dolphin;
Obtaining control parameters of the bionic robotic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
Inputting the control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
controlling the running state of the bionic robotic dolphin according to the output signal;
the control model processes control parameters through a neuron function to obtain an intermediate result, corrects the intermediate result to obtain an output signal, and comprises the following steps:
Inputting the control parameters into a control model to carry out weighting treatment through a neuron function to obtain an intermediate result;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move;
The control parameters are input into a control model to be weighted through a neuron function, and an intermediate result is obtained, wherein the method comprises the following steps:
the control model is generated by a neuron function:
Processing the control parameters to obtain an intermediate result;
Wherein f (n i) is an intermediate result; I is more than or equal to 1 and less than or equal to j, wherein j is the number of neurons in the first hidden layer; a i=[ai1,ai2],ai1、ai2 is the weight from the input layer to the first hidden layer; x= [ x 1,x2 ] is an input vector, and x 1=ΔvT,x2=θT;d1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1.
2. The control method of a biomimetic robotic dolphin according to claim 1, wherein obtaining control parameters of the biomimetic robotic dolphin according to the movement speed information and the coordinate information comprises:
According to the movement speed information and the coordinate information, the following formula is adopted:
Obtaining a target speed increment;
Wherein Deltav T is a target speed increment, x 2、y2、z2 is target position coordinate data, x 1、y1、z1 is current position coordinate data of the bionic robot dolphin, t is preset time data, and v 0 is current movement speed of the bionic robot dolphin;
By the formula:
obtaining a target rotation angle;
Wherein, theta T is the target rotation angle, For the current motion velocity vector of the biomimetic robotic dolphin,And (3) a target position vector of the bionic robotic dolphin.
3. The control method of a biomimetic robotic dolphin according to claim 1, wherein correcting the intermediate result to obtain a current intensity control signal and an energizing time interval control signal comprises:
According to the intermediate result, the following formula is adopted:
Determining deviation data, wherein E is the deviation data; Is the expected result;
And correcting the intermediate result according to the deviation data to obtain a current intensity control signal and an energizing time interval control signal.
4. The control method of a biomimetic robotic dolphin according to claim 3, wherein correcting the intermediate result according to the deviation data, a current intensity control signal and an energizing time interval control signal are obtained, comprising:
according to the deviation data, the method comprises the following steps of:
determining weights from the second hidden layer to the output layer and weights of neuron bias values in the second hidden layer, wherein u im is the weight from the second hidden layer to the output layer, and m=1, 2; d 2i is the weight of the neuron bias value in the second hidden layer; η is the learning rate;
and obtaining a current intensity control signal and a power-on time interval control signal through the neuron function according to the weight from the second hidden layer to the output layer and the weight of the neuron bias value in the second hidden layer.
5. The control method of a biomimetic robotic dolphin according to any one of claims 1 to 4, wherein controlling the operational state of the biomimetic robotic dolphin according to the output signal comprises:
Generating a control pulse signal according to the current intensity control signal and the power-on time interval control signal;
and controlling the running state of the bionic robot dolphin according to the control pulse signal.
6. A control device for a biomimetic robotic dolphin, the device comprising:
The acquisition module is used for acquiring motion speed information and coordinate information of the bionic robot dolphin;
The production module is used for obtaining control parameters of the bionic robotic dolphin according to the movement speed information and the coordinate information; the control parameters include: target speed increment and target rotation angle;
The determining module is used for inputting the control parameters into a control model for processing to obtain an output signal; the control model processes the control parameters through a neuron function to obtain an intermediate result, and corrects the intermediate result to obtain an output signal;
the control module is used for controlling the running state of the bionic robot dolphin according to the output signal;
the control model processes control parameters through a neuron function to obtain an intermediate result, corrects the intermediate result to obtain an output signal, and comprises the following steps:
Inputting the control parameters into a control model to carry out weighting treatment through a neuron function to obtain an intermediate result;
Correcting the intermediate result to obtain a current intensity control signal and an electrifying time interval control signal; the current intensity control signal and the power-on time interval control signal are used for controlling the gesture adjusting device and the driving device of the bionic robot dolphin to move;
The control parameters are input into a control model to be weighted through a neuron function, and an intermediate result is obtained, wherein the method comprises the following steps:
the control model is generated by a neuron function:
Processing the control parameters to obtain an intermediate result;
Wherein f (n i) is an intermediate result; I is more than or equal to 1 and less than or equal to j, wherein j is the number of neurons in the first hidden layer; a i=[ai1,ai2],ai1、ai2 is the weight from the input layer to the first hidden layer; x= [ x 1,x2 ] is an input vector, and x 1=ΔvT,x2=θT;d1i is the weight of the neuron bias value in the first hidden layer; a is a parameter, 0< a <1.
7. A computing device, comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method of any one of claims 1 to 5.
8. A computer readable storage medium storing instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410666955.4A CN118244805B (en) | 2024-05-28 | 2024-05-28 | Control method, device and equipment for bionic robot dolphin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410666955.4A CN118244805B (en) | 2024-05-28 | 2024-05-28 | Control method, device and equipment for bionic robot dolphin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118244805A CN118244805A (en) | 2024-06-25 |
| CN118244805B true CN118244805B (en) | 2024-07-30 |
Family
ID=91559176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410666955.4A Active CN118244805B (en) | 2024-05-28 | 2024-05-28 | Control method, device and equipment for bionic robot dolphin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118244805B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113867156A (en) * | 2021-12-02 | 2021-12-31 | 湖南工商大学 | Method and device for tracking robotic fish path by fusing BP-RBF neural network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909859B (en) * | 2019-11-29 | 2023-03-24 | 中国科学院自动化研究所 | Bionic robot fish motion control method and system based on antagonistic structured control |
| CN111158385B (en) * | 2020-01-10 | 2023-06-30 | 南京工程学院 | Motion control method, device and equipment of bionic robot fish and readable storage medium |
| CN113311705B (en) * | 2021-05-19 | 2022-03-25 | 广州大学 | High-order iterative self-learning control method and device for robotic fish and storage medium |
-
2024
- 2024-05-28 CN CN202410666955.4A patent/CN118244805B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113867156A (en) * | 2021-12-02 | 2021-12-31 | 湖南工商大学 | Method and device for tracking robotic fish path by fusing BP-RBF neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118244805A (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Target tracking control of a biomimetic underwater vehicle through deep reinforcement learning | |
| Yu et al. | A framework for biomimetic robot fish's design and its realization | |
| CN1718378A (en) | S face control method of flotation under water robot motion | |
| Wang et al. | Vision-based autonomous hovering for the biomimetic underwater robot—RobCutt-II | |
| Zhang et al. | Design and locomotion control of a dactylopteridae-inspired biomimetic underwater vehicle with hybrid propulsion | |
| Cao et al. | Hydrodynamic modeling and parameter identification of a bionic underwater vehicle: RobDact | |
| Gu et al. | Communication and cooperation for spherical underwater robots by using acoustic transmission | |
| Mohammed et al. | Design optimal PID controller for quad rotor system | |
| Bai et al. | Hydrodynamics of a flexible flipper for an underwater vehicle-manipulator system | |
| Qiu et al. | Locomotion optimization of a tendon-driven robotic fish with variable passive tail fin | |
| Chocron et al. | Dynamic reconfiguration of autonomous underwater vehicles propulsion system using genetic optimization | |
| CN116736709B (en) | Dynamic compensation type active disturbance rejection heading control method for marine robot | |
| CN115657689A (en) | Autonomous underwater vehicle target tracking control method based on track prediction | |
| CN115903820A (en) | Multi-unmanned-boat pursuit and escape game control method | |
| Wang et al. | A modified ALOS method of path tracking for AUVs with reinforcement learning accelerated by dynamic data-driven AUV model | |
| CN118244805B (en) | Control method, device and equipment for bionic robot dolphin | |
| Wang et al. | Data-driven path-following control of underactuated ships based on antenna mutation beetle swarm predictive reinforcement learning | |
| Lu et al. | Toward swimming speed optimization of a multi-flexible robotic fish with low cost of transport | |
| Praczyk | Using hill climb modular assembler encoding and differential evolution to evolve modular neuro-controllers of an autonomous underwater vehicle acting as a magnetic anomaly detector | |
| Zhang et al. | Locomotion control of a hybrid propulsion biomimetic underwater vehicle via deep reinforcement learning | |
| Wu et al. | Deep reinforcement learning with intrinsic curiosity module based trajectory tracking control for USV | |
| CN114545953A (en) | Bionic fish path control method and device and bionic fish | |
| Priandana et al. | SOM-based direct inverse trajectory control system for double-propeller boat maneuvers | |
| CN115808931B (en) | Underwater robot motion control method, device, system, equipment and storage medium | |
| Meng et al. | Trajectory‐tracking control of an unmanned surface vehicle based on characteristic modelling approach: Implementation and field testing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |