CN115890749A - Endoscope robot visual servo and optimization control method and system under RCM constraint and robot - Google Patents
Endoscope robot visual servo and optimization control method and system under RCM constraint and robot Download PDFInfo
- Publication number
- CN115890749A CN115890749A CN202211410907.6A CN202211410907A CN115890749A CN 115890749 A CN115890749 A CN 115890749A CN 202211410907 A CN202211410907 A CN 202211410907A CN 115890749 A CN115890749 A CN 115890749A
- Authority
- CN
- China
- Prior art keywords
- robot
- constraint
- rcm
- angle
- endoscope
- 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.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Endoscopes (AREA)
Abstract
The invention discloses a visual servo and optimal control method, a system and a robot of an endoscope robot under RCM constraint, comprising the following steps: step one, completing a target detection task in a surgical field and extracting a current state of a target; step two, establishing a constraint optimization control scheme according to a specific robot model; step three, equivalently converting the constraint optimization problem into a nonlinear equation set based on a projection operator; step four, an error function is built by utilizing the nonlinear equation set obtained in the step three, and a recurrent neural network RNN solver is designed based on the Dini derivative so as to obtain an optimal solution of the constraint optimization problem; and step five, sending the joint angle or the joint speed obtained in the step four to a lower computer, driving the robot to move, and automatically adjusting the surgical field of vision. Compared with other methods, the method has the advantages that iterative computation is not needed, training is not needed, and partial coefficients and elements are continuous but non-conductive.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a method, a system and a robot for controlling visual servo and optimization of an endoscope robot under RCM constraint.
Background
In the traditional minimally invasive surgery, a plurality of unstable factors exist in manual operation. For example, prolonged operation of an endoscope can cause the physician to shake their hands, resulting in an unstable field of view of the endoscope; in addition, there is a disadvantage that the communication and operation between the doctor and the assistant are not coordinated. In recent years, with the development of robotics and the improvement of medical level, medical robots have been successfully applied to the field of minimally invasive surgery. The robot-assisted minimally invasive surgery (RAMIS) system can effectively remove the influence of hand shaking during the operation of a doctor and improve the stability of the operation; the configuration of the operating personnel can be reduced, the fatigue of the operator can be relieved, and the labor cost of the operation can be reduced; the master-slave separation type operation mode can realize remote operation, sharing of medical resources and the like. In the research on the minimally invasive surgical robot, how to move the surgical instrument integrated at the end of the robot reliably around the small body surface incision as a fulcrum without enlarging the incision wound has become one of the research hotspots of the surgical robot.
A mechanism is said to be "telecentric" (RCM) if a part or point of the mechanism passes through a fixed point away from the mechanism itself throughout its movement and the point has no physical constraints in practice. The characteristics of the telecentric mechanism are in accordance with the operation requirements of minimally invasive surgery, so that the telecentric mechanism is widely applied to the minimally invasive surgery robot, and the motion performance and stability of the telecentric mechanism directly influence the operation performance of the whole minimally invasive surgery robot. Mechanical telecentric mechanisms typically have only one fixed center of focus, often requiring setup for a particular surgical procedure, and lack flexibility. In view of this, a software-based telecentric motion generation algorithm is proposed in the existing literature, which can be adjusted at a software level as required, and has higher flexibility and wider application range. During the operation, it is important to provide stable and timely visual information for doctors. The robot vision servo control is a method for capturing images in real time through a vision sensor, extracting characteristic information through an image processing algorithm, and driving a robot to operate by taking the characteristic information as a feedback signal.
The vision servo and the optimization control of the robot can be abstractly represented in mathematics into an optimization problem containing various constraints, such as a Quadratic Programming (QP) problem. Due to the characteristics of parallel computing, adaptivity, hardware realizability and the like, the neural network has become one of effective methods for solving the optimization problem. The existing QP solving algorithm mainly comprises a gradient-based Recurrent Neural Network (RNN), a zero-ized neural network ZNN and the like, wherein the RNN is suitable for solving the problem of invariance, and has the problems of more iteration times, long solving time and the like. While ZNN has the advantage of not requiring iterative computations, it requires that the relevant elements and coefficients be everywhere derivable and that it cannot directly handle the double-ended constraint. Based on the above analysis, we propose a new QP solution algorithm Dini-RNN in which double-ended constraints can be handled directly without iterative computations and in which some coefficients and elements are allowed to be continuous but not conductive.
Disclosure of Invention
The invention mainly aims to overcome the defects and shortcomings of the prior art and provides a visual servo and optimization control method, a system and a robot of an endoscope robot under RCM constraint.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a visual servo and optimization control method for an endoscope robot under RCM constraint, including the following steps:
step one, completing a target detection task in an operation visual field, and extracting a target current state r;
step two, establishing a corresponding constraint optimization control scheme according to the specific endoscope robot, and designing a performance index ofThe equation is constrained to->And &>And double-ended constraint of q - ≤q≤q + And &>Where W denotes a weighting matrix q and +>Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Denotes the RCM point p rcm To the Jacobian matrix, J system Is a Jacobian matrix of the endoscope robot>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof are collated into a double-end constraint->Wherein->And beta > 0, and then by introducing a matrix->n > 5 and-> Uniformly representing a constraint optimization control scheme into a quadratic programming problem with a general form, wherein the performance index isThe constraint condition is->
Step three, by introducing a projection operatorWherein the concrete expression of the projection operator is defined as
Equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0 based on the KKT condition;
step four, inspiring by the design idea of the zero neural network, introducing the Dini derivative to obtain a brand new RNN solverWhere gamma is a convergence parameter, phi (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of the constraint optimization problem, and then the angle change rate (or greater than or equal to) of the driving joint of the endoscope robot is obtained>
Step five, comparing the result obtained in the step fourOr the joint angle q is driven to be sent to a lower computer, the robot is driven to move, and the operation visual field is automatically adjusted.
Preferably, the endoscope robot comprises a fixed platform, an end effector, an endoscope and n driving joints q 1 ~q n N is more than 5, and the kinematic equation of the mechanical arm speed layer of the endoscope robot isWhereinJ denotes the Jacobian matrix->Representing the camera plane feature point velocity and the linear velocity at the RCM point.
As a preferred technical solution, the jacobian matrix is specifically:
wherein, J system =J image J camera ,J image Is a jacobian matrix of the image,
J task is a jacobian matrix of the endoscope tip relative to a base coordinate system, 0 J n and 0 J n+1 are respectively the Jacobian matrix of the nth coordinate system and the (n + 1) th coordinate system to the base coordinate system, 0 R n+1 is the rotation matrix of the (n + 1) th coordinate system with respect to the base coordinate system, λ ∈ (0,1).
As a preferred technical scheme, in the kinematic equation of the robot velocity layer, an optimized performance index is designedConsidering the upper and lower limit constraints of the angle of the driving joint and the change rate thereof, and establishing a constraint optimization control scheme of the endoscope robot;
after equivalent arrangement, the method is represented mathematically as a quadratic programming problem with a general form, wherein the performance index isThe constraint condition is->
Based on the projection operator and the KKT condition, the quadratic programming problem is converted equivalently to a nonlinear equation system g (t, x, μ) =0.
As a preferred technical solution, the projection operator is continuous everywhere.
As an optimal technical scheme, a brand new RNN solver is obtained by being inspired by the design idea of a zero neural networkAmong them are:
z=Cx+μ,
as an optimal technical scheme, the RNN solver does not need training and iterative computation, can efficiently solve and obtain the optimal solution of a quadratic programming problem, and further obtains the angle change rate of the driving joint of the endoscope robotBy varying the rate of change of angle of the drive joint>Or the driving joint angle q obtained by integration is sent to a lower computer to drive the robot to move for operation visionAnd (4) automatically adjusting the field.
In a second aspect, the invention also provides an endoscope robot visual servo and optimization control system under the RCM constraint, which is applied to the endoscope robot visual servo and optimization control method under the RCM constraint and comprises a target detection module, a kinematics control scheme construction module, an equivalence transformation module, an optimization problem solving module and a driving module;
the target detection module is used for restricting a motion track, namely the ideal speed of the characteristic point under the camera plane of the endoscope robotSetting (2);
the kinematic control scheme construction module is used for establishing a corresponding constraint optimization control scheme according to a specific endoscope robot, and the design performance index isThe equation is constrained to->And &>And double-ended constraint of q - ≤q≤q + And &>Wherein W denotes a weighting matrix q and->Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Denotes the RCM point p rcm To form a Jacobian matrix, J system For the endoscopic robot Jacobian matrix, in combination with a camera>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof are collated into a double-end constraint->WhereinAnd beta > 0, and then by introducing a matrixn > 5 and->Uniformly characterizing a constrained optimal control scheme as a quadratic programming problem having a general form in which a performance criterion is ^ based>With a constraint of >>
The equivalence conversion module is used for projecting operator-based
And KKT condition, equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0;
the optimal solving module is used for defining an error monitoring function e (t) = g (t, x, mu), the error monitoring function is a nonlinear equation set obtained in the third step, is inspired by the design idea of a zero neural network, introduces Dini derivatives, and obtains a brand new RNN solverWhere γ is the convergence parameter, Φ (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of a constraint optimization problem, and then the angle change rate->
The drive module is used for transmitting the obtained resultOr the joint angle q is driven to be sent to a lower computer, the robot is driven to move, and the operation visual field is carried outAutomatic adjustment of (2).
In a third aspect, the present invention further provides a computer readable storage medium, in which a program is stored, and when the program is executed by a processor, the method for performing visual servoing and optimal control of an endoscope robot under RCM constraints is implemented.
In a fourth aspect, the present invention also provides an endoscope robot comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the endoscopic robot vision servo and optimization control method under the RCM constraints.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the present invention can effectively overcome the disadvantages of the general technology, and the ZNN solver proposed before this needs all derivative information of the relevant elements and coefficients, so the equality constraint and the inequality constraint need to have differentiable boundaries everywhere. In addition, when the ZNN solver considers double-ended constraints, the double-ended constraints need to be equivalently converted into inequality constraints for processing, and the number of neurons and the computational complexity of the neural network controller are increased in this way. The invention utilizes a projection operator to carry out inequality constraint processing and equivalent transformation of a quadratic programming problem, introduces Dini derivatives, combines an evolution rule and an activation function to obtain a brand new RNN solver, and the RNN solver can solve the optimal solution of the quadratic programming problem. After the optimal solution of the quadratic programming problem is obtained, the endoscope robot can be driven to move under the RCM constraint, and the automatic target tracking task is realized. The Dini-RNN solver algorithm of the present invention has the advantages of no need of iteration, direct processing of double-ended constraints, and allowing partial coefficients and elements to be continuous but non-conductive. The invention provides a control method for automatically tracking a target by using a visual servo of an endoscope robot under the constraint of RCM, which is convenient to operate, does not need training and iterative computation, and has standard operation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of visual servo and optimization control of an endoscopic robot under RCM constraints according to an embodiment of the present invention;
FIG. 2 is a model diagram of a simulated Franka Emika Panda mechanical arm according to an embodiment of the present invention.
FIG. 3 is a diagram of an RCM scheme according to an embodiment of the present invention.
Fig. 4 is a motion trajectory of a feature point on a camera plane at the end of the simulated Franka Emika Panda mechanical arm according to the embodiment of the present invention, starting from any 6 initial positions, and finally reaching the center of the camera plane.
FIG. 5 is an RCM error plot of a simulated Franka Emika Panda mechanical arm according to an embodiment of the present invention.
FIG. 6 is a graph showing the variation of joint angles of a Franka Emika Panda robot according to an embodiment of the present invention.
FIG. 7 is a graph of the rate of change of joint angle for a simulated Franka Emika Panda robotic arm in accordance with an embodiment of the present invention.
FIG. 8 is a schematic block diagram of a system for constrained motion planning and control of an endoscopic robot under the constraint of RCM in accordance with an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a robot according to an embodiment of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention and the accompanying drawings, it should be understood that the drawings are for illustrative purposes only and are not to be construed as limiting the patent. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Examples
As shown in fig. 1, the present embodiment is a method for controlling the visual servoing and optimization of an endoscope robot under the constraint of RCM, the method includes the following steps:
step one, completing a target detection task in an operation visual field, and extracting a target current state r;
step two, establishing a corresponding constraint optimization control scheme according to the specific endoscope robot, and finally obtaining a performance index in the constraint optimization control scheme asThe equation is constrained to->Both ends are constrained to be->
In the second step, the constraint is carried out by the equationCan make the characteristic point speed and RCM point speed in the camera planeAnd its joint angular velocity>In connection therewith, automatic tracking of target control under RCM constraints can be achieved. Is bound by an inequality->Joint limit constraints on the joint angles of the endoscopic robot can be addressed.
Step three: projection-based operatorAnd equivalently converting the constraint optimization problem into a nonlinear equation system.
In the third step, corresponding Lagrangian functions are defined for the constraint optimization problem, on the basis, derivation is carried out to obtain the KKT condition, and the obtained KKT condition is used
And (5) processing, and finally equivalently converting the constraint optimization problem into a nonlinear equation system.
Step four: and (4) aiming at the nonlinear equation set in the step three, constructing an error function and designing an RNN solver to obtain the nonlinear equation set and an optimal solution of the constraint optimization problem, so as to obtain the speed of each joint of the endoscope robot.
Constructing an error monitoring function e (t) = g (t, x, mu) based on the nonlinear equation set in the step three, introducing Dini derivatives under the inspiration of the design idea of the zero-ized neural network, and obtaining a brand-new RNN solverWhere γ is the convergence parameter, Φ (-) represents the activation function array,
z=Cx+μ,
is relative to z i The finally obtained RNN solver can simultaneously obtain the optimal solution of the solution and constraint optimization problem of the nonlinear equation set>Can obtain the change rate of the driving angle of the endoscope robot>
Step five: combining the results of step fourOr the joint angle q is driven to be sent to a lower computer, the endoscope robot is driven to move, and the operation visual field is automatically adjusted.
As shown in FIG. 2, in the present embodiment, the endoscope robot includes a fixed platform, an end effector, an endoscope, and 7 rotary joints, O being the 7 rotary joints respectively 1 ,...,O 7 And endoscope O 8 The kinematic relation of the robot velocity layer under the RCM constraint isWherein->Representing the camera plane feature point velocity and the RCM point velocity.
As shown in FIG. 3, the endoscope linkage is passed into the body through the insertion site and cannot be laterally displaced at the RCM site.
As shown in fig. 4, the detected target is initialized randomly to any position on the camera plane for 6 times, and finally the camera controls the mechanical arm to move through the visual servo, so that the detected target can be seen to move to the center of the camera plane, which shows that the method can realize automatic tracking of the target under the RCM constraint and has little deviation.
As shown in fig. 5, in which the solid line e x Shows the error of the RCM point of the simulated Panda mechanical arm in the X direction, and the dotted line e y Shows the error of the RCM point of the simulated Panda mechanical arm in the Y direction, and the dotted line e z The error in the Z-direction of the RCM point of the simulated Panda tandem robot arm is shown. Wherein during the execution of the task, the errors in three directions are all less than or equal to 1.5 multiplied by 10 -5 Meter, high accuracy Yu Yahao meter level accuracy.
As shown in FIG. 6, wherein q is 1 ,q 2 ,q 3 ,q 4 ,q 5 ,q 6 ,q 7 Respectively showing the first rotary joints O of the simulated Panda endoscope robot 1 And a second rotary joint O 2 And a third rotary joint O 3 And a fourth rotary joint O 4 Fifth rotary joint O 5 Sixth rotary joint O 6 And a seventh rotary joint O 7 The angle of (c). During task execution, the angles of the joints are changed continuously, and various motions occur corresponding to the mechanical arms.
As shown in fig. 7, in which,respectively showing the first rotary joints O of the simulated Panda endoscope robot 1 And a second rotary joint O 2 And a third rotary joint O 3 And a fourth rotary joint O 4 Fifth rotary joint O 5 Sixth rotary joint O 6 And a seventh rotary joint O 7 Angle change rate of. As can be seen from fig. 7, in the process of task execution, the angle change rate of each joint angle can be guaranteed to change within a certain range, so that the effectiveness of the invention in double-end constraint processing and joint limit avoidance in the quadratic programming problem can be demonstrated.
As shown in fig. 8, in another embodiment of the present application, there is provided an endoscope robot vision servo and optimization control system 100 under RCM constraint, comprising an object detection module 101, a kinematic control scheme construction module 102, an equivalence transformation module 103, an optimal solution module 104, and a driving module 105;
the target detection module 101 is used for restricting a motion track, namely an ideal speed of a characteristic point under a camera plane of the endoscope robotSetting (2);
the kinematic control scheme building module 102 is configured to build a corresponding constraint optimization control scheme according to a specific endoscope robot, where a performance index is designed to beThe equation is constrained to >>And &>And double-ended constraint of q - ≤q≤q + And &>Wherein W denotes a weighting matrix q and->Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Denotes the RCM point p rcm To form a Jacobian matrix, J system Is a Jacobian matrix of the endoscope robot>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof can be collated into a double-end constraint->WhereinAnd beta > 0, and then by introducing a matrixn > 5 and>uniformly characterizing a constrained optimal control scheme as a quadratic programming problem having a general form in which a performance criterion is ^ based>The constraint condition is->
The equivalence transformation module 103 is configured to transform the projection-based image into an equivalent image
And KKT condition, equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0;
the optimal solution module 104 is configured to define an error monitoring function e (t) = g (t, x, μ), where the error monitoring function is derived by introducing a Dini derivative into an obtained nonlinear equation set, as inspired by a design idea of a zero-valued neural network, to obtain a brand-new RNN solverWhere gamma is a convergence parameter, phi (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of the constraint optimization problem, and then the angle change rate (or greater than or equal to) of the driving joint of the endoscope robot is obtained>
The driving module 105 is used for obtaining the resultOr the integral q is sent to a lower computer to drive the endoscope robot to move.
In addition, in the implementation of the system for motion planning and control of an endoscopic robot under the RCM constraint of the above embodiment, the logical division of each program module is only an example, and in practical applications, the above function allocation may be performed by different program modules according to needs, for example, due to the configuration requirements of corresponding hardware or the convenience of implementation of software, that is, the visual servo of the endoscopic robot under the RCM constraint and the internal structure of the optimization control system are divided into different program modules to perform all or part of the above described functions.
As shown in fig. 9, in one embodiment, a robot 200 is provided, and the robot 200 may include a first processor 201, a first memory 202 and a bus, and may further include a computer program stored in the first memory 202 and executable on the first processor 201, such as a visual servo and optimization control program 203 of an endoscopic robot under the RCM constraint.
The first memory 202 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The first memory 202 may in some embodiments be an internal storage unit of the robot 200, e.g. a mobile hard disk of the robot 200. The first memory 202 may also be an external storage device of the robot 200 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the robot 200. Further, the first memory 202 may also include both an internal storage unit of the robot 200 and an external storage device. The first memory 202 may be used not only to store application software installed in the robot 200 and various types of data, such as codes of a visual servo and optimization control program 203 of the endoscopic robot under the RCM constraint, but also to temporarily store data that has been output or will be output.
The first processor 201 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The first processor 201 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the robot 200 by running or executing programs or modules (e.g., federal learning defense programs and the like) stored in the first memory 202 and calling data stored in the first memory 202.
Fig. 9 shows only a robot with components, and those skilled in the art will appreciate that the structure shown in fig. 8 does not constitute a limitation of the robot 200, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
The endoscopic robot visual servoing and optimization control program 203 under RCM constraints stored in the first memory 202 of the robot 200 is a combination of instructions that, when executed in the first processor 201, can implement:
step one, completing a target detection task in an operation visual field, and extracting a target current state r;
step two, establishing a corresponding constraint optimization control scheme according to the specific endoscope robot, and designing a performance index ofThe equation is constrained to->And &>And double-ended constraint of q - ≤q≤q + Andwhere W denotes a weighting matrix q and +>Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Denotes the RCM point p rcm To the Jacobian matrix, J system Is a Jacobian matrix of the endoscope robot>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof are arranged into a double-end constraint->WhereinAnd beta > 0, and then by introducing a matrixn > 5 and-> Uniformly characterizing a constrained optimal control scheme as a quadratic programming problem having a general form in which a performance criterion is ^ based>The constraint condition is->
Step three, by introducing a projection operatorWherein the concrete expression of the projection operator is defined as
Equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0 based on the KKT condition;
step four, inspiring by the design idea of the zero neural network, introducing the Dini derivative to obtain a brand new RNN solverWhere γ is the convergence parameter, Φ (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of the constraint optimization problem, and then the angle change rate (or greater than or equal to) of the driving joint of the endoscope robot is obtained>
Step five, comparing the result obtained in the step fourOr the joint angle q is driven to be sent to a lower computer, the robot is driven to move, and the operation visual field is automatically adjusted.
Further, the modules/units integrated by the robot 200, if implemented in the form of software functional units and sold or used as independent products, may be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM).
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A visual servo and optimization control method of an endoscope robot under RCM constraint is characterized by comprising the following steps:
step one, completing a target detection task in an operation visual field, and extracting a target current state r;
step two, establishing a corresponding constraint optimization control scheme according to the specific endoscope robot, and designing the performance index asThe equation is constrained to->And &>And double-ended constraint of q - ≤q≤q + And &>Wherein W denotes a weighting matrix q and->Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Represents the RCM point p rcm To form a Jacobian matrix, J system Is a Jacobian matrix of the endoscope robot>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof are arranged into a double-end constraint->Wherein->And beta > 0, and then by introducing a matrix->n > 5 and-> Uniformly characterizing a constrained optimal control scheme as a quadratic programming problem having a general form in which a performance criterion is ^ based>The constraint condition is->
Step three, by introducing a projection operatorWherein the concrete expression of the projection operator is defined as
Based on KKT conditions, equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0;
step four, inspiring by the design idea of the zero neural network, introducing the Dini derivative to obtain a brand new RNN solverWhere γ is the convergence parameter, Φ (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of the constraint optimization problem, and then the angle change rate (or greater than or equal to) of the driving joint of the endoscope robot is obtained>
2. The RCM-constrained visual servo and optimization control method of an endoscopic robot according to claim 1, wherein the endoscopic robot comprises a fixed platform, an end effector, an endoscope, and n driving joints q 1 ~q n N is more than 5, and the kinematic equation of the mechanical arm speed layer of the endoscope robot isWherein->J denotes the Jacobian matrix->Representing the camera plane feature point velocity and the linear velocity at the RCM point.
3. The visual servo and optimization control method of an endoscopic robot under RCM constraint according to claim 2, characterized in that the jacobian matrix is specifically:
wherein, J system =J image J camera ,J image Is a jacobian matrix of the image,
J task is a jacobian matrix of the endoscope tip relative to a base coordinate system, 0 J n and 0 J n+1 are respectively the Jacobian matrix of the nth coordinate system and the (n + 1) th coordinate system to the base coordinate system, 0 R n+1 is the rotation matrix of the (n + 1) th coordinate system with respect to the base coordinate system, λ ∈ (0,1).
4. The RCM-constrained visual servo and optimization control method for endoscope robots according to claim 2, wherein optimization performance indexes are designed in the kinematic equation of the robot velocity layerConsidering the constraint of the driving joint angle and the upper and lower limits of the change rate of the driving joint angle, and establishing a constraint optimization control scheme of the endoscope robot;
through equivalent arrangement, the method is represented as a quadratic programming problem with a general form in mathematics, wherein the performance index isThe constraint condition is->
Based on the projection operator and the KKT condition, the quadratic programming problem is equivalently converted into a nonlinear equation set g (t, x, μ) =0.
5. The RCM-constrained endoscopic robot vision servoing and optimization control method according to claim 4, wherein the projection operator is continuous everywhere.
7. the visual servo and optimization control method for the endoscope robot under the RCM constraint of claim 6, wherein the RNN solver can efficiently solve and obtain the optimal solution of the quadratic programming problem without training and iterative computation, so as to obtain the angle change rate of the driving joint of the endoscope robotBy varying the rate of change of angle of the driving joint->Or the driving joint angle q obtained by integration is sent to a lower computer to drive the robot to move, so that the operation visual field is automatically adjusted.
An endoscope robot visual servo and optimization control system under RCM constraint, which is applied to the endoscope robot visual servo and optimization control method under RCM constraint of any one of claims 1-7, and is characterized by comprising a target detection module, a kinematics control scheme construction module, an equivalent transformation module, an optimization problem solving module and a driving module;
the target detection module is used for restricting a motion track, namely the ideal speed of the characteristic point under the camera plane of the endoscope robotDetermination of (1);
the kinematic control scheme construction module is used for establishing a corresponding constraint optimization control scheme according to a specific endoscope robot, and the design performance index isThe equation is constrained to >>And &>And a double end constraint of q - ≤q≤q + And &>Wherein W denotes a weighting matrix q and->Respectively representing the angle and the rate of change of the angle of the driving joint, q - And q is + Respectively represent the upper and lower limits of the angle of the driving joint>And &>Respectively representing the upper and lower limits of the rate of change of the angle of the driving joint, J rcm Represents the RCM point p rcm To form a Jacobian matrix, J system For the endoscopic robot Jacobian matrix, in combination with a camera>And &>Respectively representing the linear velocity of an RCM point and the characteristic point velocity under a camera plane; two double-end constraints on the angle of the driving joint and the angle change rate thereof are collated into a double-end constraint->WhereinAnd beta > 0, recanalizationOver-introduced matrixn > 5 and->Uniformly characterizing a constrained optimal control scheme as a quadratic programming problem having a general form in which a performance criterion is ^ based>With a constraint of >>
The equivalence conversion module is used for projecting operator based
And KKT condition, equivalently converting the constraint optimization problem into a nonlinear equation set g (t, x, mu) =0;
the optimal solving module is inspired by the design idea of the zero neural network, introduces Dini derivatives and obtains a brand new RNN solverWhere γ is the convergence parameter, Φ (-) represents the activation function array,
z=Cx+μ,
is relative to z i The Dini upper right derivative operator is solved through an RNN solver to obtain an optimal solution of a constraint optimization problem, and then the angle change rate->
9. A computer-readable storage medium storing a program which, when executed by a processor, implements the RCM-constrained visual servoing and optimization control method for an endoscopic robot according to any one of claims 1 to 7.
10. An endoscopic robot, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores computer program instructions executable by the at least one processor to cause the at least one processor to perform the method of visual servoing and optimization control of an endoscopic robot under RCM constraints as defined in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211410907.6A CN115890749A (en) | 2022-11-11 | 2022-11-11 | Endoscope robot visual servo and optimization control method and system under RCM constraint and robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211410907.6A CN115890749A (en) | 2022-11-11 | 2022-11-11 | Endoscope robot visual servo and optimization control method and system under RCM constraint and robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115890749A true CN115890749A (en) | 2023-04-04 |
Family
ID=86470502
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211410907.6A Pending CN115890749A (en) | 2022-11-11 | 2022-11-11 | Endoscope robot visual servo and optimization control method and system under RCM constraint and robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115890749A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116687452A (en) * | 2023-07-28 | 2023-09-05 | 首都医科大学附属北京妇产医院 | Early pregnancy fetus ultrasonic autonomous scanning method, system and equipment |
-
2022
- 2022-11-11 CN CN202211410907.6A patent/CN115890749A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116687452A (en) * | 2023-07-28 | 2023-09-05 | 首都医科大学附属北京妇产医院 | Early pregnancy fetus ultrasonic autonomous scanning method, system and equipment |
CN116687452B (en) * | 2023-07-28 | 2023-11-03 | 首都医科大学附属北京妇产医院 | Early pregnancy fetus ultrasonic autonomous scanning method, system and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220009096A1 (en) | Inverse kinematics solving method for redundant robot and redundant robot and computer readable storage medium using the same | |
CN111438688B (en) | Robot correction method, robot correction device, computer equipment and storage medium | |
CN109048897B (en) | Method for teleoperation of master-slave robot | |
CN114952868B (en) | 7-degree-of-freedom SRS (sounding reference Signal) type mechanical arm control method and device and piano playing robot | |
US10899005B2 (en) | Link-sequence mapping device, link-sequence mapping method, and program | |
CN115890749A (en) | Endoscope robot visual servo and optimization control method and system under RCM constraint and robot | |
WO2023168849A1 (en) | Mechanical arm motion capture method, medium, electronic device, and system | |
CN115213905B (en) | Method and system for controlling position and pose of redundant mechanical arm and robot | |
CN115157262B (en) | Obstacle avoidance and optimal control method and system for joint-limited redundant mechanical arm and robot | |
CN110682293A (en) | Robot arm correction method, robot arm correction device, robot arm controller and storage medium | |
CN115179297A (en) | Method and system for controlling joint limit of joint in combined obstacle avoidance mode through position and posture of surgical robot | |
CN113524201B (en) | Active adjusting method and device for pose of mechanical arm, mechanical arm and readable storage medium | |
CN113084791B (en) | Mechanical arm control method, mechanical arm control device and terminal equipment | |
CN116141330A (en) | Robot motion control method and device, robot equipment and storage medium | |
CN115424701B (en) | Bone surface follow-up technology for optimal path planning | |
CN116175569A (en) | Method for determining relation model of hand-eye matrix, hand-eye calibration method and equipment | |
CN114851168B (en) | Motion planning and control method and system for joint-limited redundant parallel mechanical arm and robot | |
CN114643582B (en) | Model-free joint fault-tolerant control method and device for redundant mechanical arm | |
CN115741666A (en) | Robot hand-eye calibration method, robot and robot operation method | |
CN114407011A (en) | Special-shaped workpiece grabbing planning method, planning device and special-shaped workpiece grabbing method | |
CN117428791B (en) | Inverse kinematics solving method and system for shoulder four-axis rehabilitation robot | |
CN116141341B (en) | Method for realizing pointing action of five-degree-of-freedom mechanical arm meeting Cartesian space constraint | |
CN116787417A (en) | Robot control method, apparatus, device and storage medium | |
CN114274141A (en) | Robot, method and device for controlling robot, and computer-readable storage medium | |
CN116869654A (en) | Surgical robot telecentric motion and man-machine interaction admittance control method and system based on quadratic programming and robot |
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 |