CN109213175A - A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network - Google Patents

A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network Download PDF

Info

Publication number
CN109213175A
CN109213175A CN201811286883.1A CN201811286883A CN109213175A CN 109213175 A CN109213175 A CN 109213175A CN 201811286883 A CN201811286883 A CN 201811286883A CN 109213175 A CN109213175 A CN 109213175A
Authority
CN
China
Prior art keywords
mobile robot
neural network
primal
camera
pdnn
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
Application number
CN201811286883.1A
Other languages
Chinese (zh)
Inventor
俞立
吴锦辉
陈旭
刘安东
滕游
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201811286883.1A priority Critical patent/CN109213175A/en
Publication of CN109213175A publication Critical patent/CN109213175A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Manipulator (AREA)
  • Feedback Control In General (AREA)

Abstract

A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network, comprising the following steps: 1) establish moveable robot movement model；2) camera is fixed on the ceiling, enable camera to obtain overall Vision information, establishes Visual Servoing Mobile Robot error model；3) it according to error model, obtains predictive equation and defines PREDICTIVE CONTROL performance indicator；4) performance indicator minimization problem is established as the minimization problem based on primal-dual neural network, in conjunction with the primal-dual neural network module in Matlab-Simulink, solves controller gain, completes track following task.Problem is converted to multiple constraint linear quadratic planning problem by the present invention, rapidly finds out optimal solution using PDNN.

Description

Mobile robot visual servo trajectory tracking and predicting control method based on primal-dual neural network
Technical Field
The invention relates to the technical field of trajectory tracking of mobile robots, in particular to a visual servo trajectory tracking and predicting control method of a mobile robot based on a primal-dual neural network.
Background
With the development of science and technology, people not only need to complete specific tasks, but also need to perceive the environment. The visual information is the most important information for sensing the environment, so that many researchers put the research focus in the field of visual servo control. The tracking control problem of the visual servo track of the mobile robot is one of three basic problems of the visual servo control, and is also one of the basic problems of the intelligent robot. Therefore, the research result of the visual servo track tracking control of the mobile robot not only adds a theoretical result to the motion control of the mobile robot, but also lays a solid foundation for the field of intelligent robot perception.
However, in actual operation, the robot has constraints of linear velocity and angular velocity, which increases the difficulty of designing the controller. The predictive control method is a control method for real-time correction through a predictive equation, can explicitly process constraints, and can convert the problem solved by the controller into an optimization problem. However, it has the major disadvantage of being computationally expensive, and the requirement for rapidity is high for practical motion control systems. Therefore, how to accelerate the solution speed of the predictive control optimization problem with multiple constraints becomes a hot problem in recent years.
Disclosure of Invention
In order to solve the problem that the prior art cannot solve the problem that the solving speed of a multi-constraint optimization problem in the tracking and predicting control of the visual servo track of the mobile robot is low, the invention provides a tracking and predicting control method of the visual servo track of the mobile robot based on a Primary Dual Neural Network (PDNN), which converts the problem into the problem of multi-constraint linear quadratic programming and rapidly solves the optimal solution by utilizing the PDNN.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a mobile robot visual servo track tracking prediction control method based on a primal-dual neural network comprises the following steps:
1) establishing a mobile robot kinematics model;
definition [ x y θ ]]TThe linear velocity of the robot is v, the angular velocity of the robot is omega, and the kinematic model of the non-integral mobile robot is
2) Fixing the camera on the ceiling, enabling the camera to obtain global visual information, and establishing an error model of the visual servo mobile robot as
Wherein (x)m,ym)TFor robot coordinate (x, y)TAt the coordinates of the pixel coordinate system,is a positive definite matrix, d1And d2Is a constant, θ, dependent on camera depth information0Is a camera axis YrAnd the axis X of the world coordinate systemwAngle between, rotation matrixProjection coordinates of the optical center of the camera on a motion plane;
definition ofWherein,the derivation is carried out on the formula (2) and the error model is obtained by combining the formula (1)
Discretizing the system (3) by a period T to obtain an error model of the visual servo mobile robot based on the image
z(k+1)＝z(k)+Tf(z(k))u (4)
Wherein,
3) obtaining a prediction equation according to the error model;
rewriting equation (4) to the nonlinear form:
z(k+1)＝f1(z(k))+f2(z(k))u (5)
wherein f is1(z(k))＝z(k)，f2(z(k))＝Tf(z(k))；
Defining the trajectory tracking prediction control performance index as
Where r (k + j | k) is a reference vector, z (k + j | k) is a prediction vector, Δ u (k + j | k) is a control increment and Δ u (k + j | k) is u (k + j | k) -u (k-1+ j | k), N, and NuRespectively representing a prediction time domain and a control time domain, N > Nu> 0, Q and R denote weight matrices, and | represents the corresponding directionThe euclidean norm of the quantity; considering that the mobile robot has constraints in actual motion, the prediction equation with the constraints and the performance index minimization problem are as follows:
wherein I represents an identity matrix, RkThe dimension of the representation matrix is k,
4) establishing a minimization problem based on a primal-dual neural network, and rewriting a performance index minimization problem (8) into:
the performance index minimization problem (8) is changed into:
wherein,
the PDNN dynamic equation is:
wherein gamma is an inductance in the neural network circuit for controlling the convergence rate of the neural network,the optimization vector representing PDNN, η is a dual vector,defining a PDNN constraint vector according to the constraintsThen
The vision servo track tracking and predicting control process of the mobile robot based on the primal-dual neural network obtained by the analysis comprises the following steps:
s1: inputting H, p and the constraint into a PDNN module of Matlab-Simulink, and calculating an optimal control increment Δ u (k) at the current time, where u (k) is Δ u (k) plus u (k-1);
s2: substituting u (k) into equation of state (5) to obtain the state quantity of the next momentAnd updating the matrices H and p;
s3: let k be k +1, and end if Δ u (k) is 0; otherwise, step S1 is repeated.
The technical conception of the invention is as follows: first, the visual servo mobile robot is built into a nonlinear model in consideration of input and state quantity change constraints. And then, combining a prediction control idea, giving a prediction equation and a prediction control performance index, and converting the solving controller into a control increment minimization problem. Finally, the PDNN is used to solve the minimization problem until the control increment is 0.
The invention has the following beneficial effects: the problem of solving the controller is converted into a minimization problem through a predictive control method, so that the optimization theory is favorably utilized for solving; by combining the PDNN method, the optimization problem of multiple constraints can be rapidly and accurately calculated on line, and the problem of tracking the track of the visual servo mobile robot with input and state change constraints is effectively solved.
Drawings
FIG. 1 is a coordinate relation diagram of a visual servo mobile robot;
FIG. 2 is a diagram of model construction of PDNN under Matlab-Simulink.
FIG. 3 is a simulation diagram of prediction control trajectory tracking based on a primal-dual neural network
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1, a method for controlling visual servo trajectory tracking and prediction of a mobile robot based on a primal-dual neural network includes the following steps:
1) establishing a mobile robot kinematics model;
definition [ x y θ ]]TThe linear velocity of the robot is v, the angular velocity of the robot is omega, and the kinematic model of the non-integral mobile robot is
2) Fixing the camera on the ceiling, enabling the camera to obtain global visual information, and establishing an error model of the visual servo mobile robot as
Wherein (x)m,ym)TFor robot coordinate (x, y)TAt the coordinates of the pixel coordinate system,is a positive definite matrix, d1And d2Is a constant, θ, dependent on camera depth information0Is a camera axis YrAnd the axis X of the world coordinate systemwAngle between, rotation matrixProjection coordinates of the optical center of the camera on a motion plane;
definition ofWherein,the derivation is carried out on the formula (2) and the error model is obtained by combining the formula (1)
Discretizing the system (3) by a period T to obtain an error model of the visual servo mobile robot based on the image
z(k+1)＝z(k)+Tf(z(k))u (4)
Wherein,
3) obtaining a prediction equation according to the error model;
rewriting equation (4) to the nonlinear form:
z(k+1)＝f1(z(k))+f2(z(k))u (5)
wherein f is1(z(k))＝z(k)，f2(z(k))＝Tf(z(k))；
Defining the trajectory tracking prediction control performance index as
Where r (k + j | k) is a reference vector, z (k + j | k) is a prediction vector, Δ u (k + j | k) is a control increment and Δ u (k + j | k) is u (k + j | k) -u (k-1+ j | k), N, and NuRespectively representing a prediction time domain and a control time domain, N > NuGreater than 0, Q and R represent weight matrixes, and | il. | | represents the Euclidean norm of the corresponding vector; considering that the mobile robot has constraints in actual motion, the prediction equation with the constraints and the performance index minimization problem are as follows:
wherein I represents an identity matrix, RkThe dimension of the representation matrix is k,
4) establishing a minimization problem based on a primal-dual neural network, and rewriting a performance index minimization problem (8) into:
the performance index minimization problem (8) is changed into:
wherein,
the PDNN dynamic equation is:
wherein gamma is an inductance in the neural network circuit for controlling the convergence rate of the neural network,the optimization vector representing PDNN, η is a dual vector,from the constraints, a PDNN constraint vector may be definedThen
The process of the mobile robot visual servo track tracking prediction control based on the primal-dual neural network obtained by the analysis comprises the following steps:
s1: h, p and the constraint are input into the PDNN module of Matlab-Simulink in fig. 2, and when the optimal control increment Δ u (k) at the current time is calculated, the optimal control amount u (k) ═ Δ u (k) + u (k-1) at the current time;
s2: substituting u (k) into equation of state (5) to obtain the state quantity of the next momentAnd updating the matrices H and p;
s3: let k be k +1, and end if Δ u (k) is 0; otherwise, step S1 is repeated.
Setting the regulation factor gamma of the neural network as 1000 in conjunction with fig. 3, the simulation experiment is from the initial position x as [ 0.145-0.0075-0.5 ═ 0.145-0.0075]Initially, the vision servo neural network prediction controller is used for finally enabling the mobile robot to track to a specified track xr＝3kT，yr＝sinxr。

Claims (1)

1. A mobile robot visual servo track tracking and predicting control method based on a primal-dual neural network is characterized by comprising the following steps:
1) establishing a mobile robot kinematics model;
definition [ x y θ ]]TThe linear velocity of the robot is v, the angular velocity of the robot is omega, and the kinematic model of the non-integral mobile robot is
2) Fixing the camera on the ceiling, enabling the camera to obtain global visual information, and establishing an error model of the visual servo mobile robot as
Wherein (x)m,ym)TFor robot coordinate (x, y)TAt the coordinates of the pixel coordinate system,is a positive definite matrix, d1And d2Is a constant, θ, dependent on camera depth information0Is a camera axis YrAnd the axis X of the world coordinate systemwAngle between, rotation matrix Projection coordinates of the optical center of the camera on a motion plane;
definition ofWherein,the derivation is carried out on the formula (2) and the error model is obtained by combining the formula (1)
Discretizing the system (3) by a period T to obtain an error model of the visual servo mobile robot based on the image
z(k+1)＝z(k)+Tf(z(k))u(4)
Wherein,
3) obtaining a prediction equation according to the error model;
rewriting equation (4) to the nonlinear form:
z(k+1)＝f1(z(k))+f2(z(k))u (5)
wherein f is1(z(k))＝z(k)，f2(z(k))＝Tf(z(k))；
Defining the trajectory tracking prediction control performance index as
Where r (k + j | k) is a reference vector, z (k + j | k) is a prediction vector, Δ u (k + j | k) is a control increment and Δ u (k + j | k) is u (k + j | k) -u (k-1+ j | k), N, and NuRespectively representing a prediction time domain and a control time domain, N > NuGreater than 0, Q and R represent weight matrixes, and | il. | | represents the Euclidean norm of the corresponding vector; considering that the mobile robot has constraints in actual motion, the prediction equation with the constraints and the performance index minimization problem are as follows:
wherein I represents an identity matrix, RkThe dimension of the representation matrix is k,
4) establishing a minimization problem based on a primal-dual neural network, and rewriting a performance index minimization problem (8) into:
the performance index minimization problem (8) is changed into:
wherein,
W＝2(GTQG+R)，
the PDNN dynamic equation is:
wherein gamma is an inductance in the neural network circuit for controlling the convergence rate of the neural network,
the optimization vector representing PDNN, η is a dual vector,defining a PDNN constraint vector according to the constraintsThen
The vision servo track tracking and predicting control process of the mobile robot based on the primal-dual neural network obtained by the analysis comprises the following steps:
s1: inputting H, p and the constraint into a PDNN module of Matlab-Simulink, and calculating an optimal control increment Δ u (k) at the current time, where u (k) is Δ u (k) plus u (k-1);
s2: substituting u (k) into the state equation (5) to obtain the state quantity z (k +1) of the next moment and updating the matrixes H and p;
s3: let k be k +1, and end if Δ u (k) is 0; otherwise, step S1 is repeated.
CN201811286883.1A 2018-10-31 2018-10-31 A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network Pending CN109213175A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811286883.1A CN109213175A (en) 2018-10-31 2018-10-31 A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811286883.1A CN109213175A (en) 2018-10-31 2018-10-31 A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network

Publications (1)

Publication Number Publication Date
CN109213175A true CN109213175A (en) 2019-01-15

Family

ID=64998323

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811286883.1A Pending CN109213175A (en) 2018-10-31 2018-10-31 A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network

Country Status (1)

Country Link
CN (1) CN109213175A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109866255A (en) * 2019-04-11 2019-06-11 吉林大学 A kind of recognition methods of robot motion's direction and device
CN110095983A (en) * 2019-04-22 2019-08-06 浙江工业大学 A kind of mobile robot predicting tracing control method based on path parameter
CN110244703A (en) * 2019-03-28 2019-09-17 浙江工业大学 A kind of mobile robot forecast Control Algorithm with external disturbance and data exception
CN110470298A (en) * 2019-07-04 2019-11-19 浙江工业大学 A kind of Robot Visual Servoing position and orientation estimation method based on rolling time horizon
CN111283683A (en) * 2020-03-04 2020-06-16 湖南师范大学 Servo tracking accelerated convergence method for robot visual feature planning track
CN111309002A (en) * 2019-11-26 2020-06-19 华南理工大学 Wheel type mobile robot obstacle avoidance method and system based on vector
CN112894812A (en) * 2021-01-21 2021-06-04 中山大学 Visual servo trajectory tracking control method and system for mechanical arm
CN114418159A (en) * 2021-10-29 2022-04-29 中国科学院宁波材料技术与工程研究所 Method and system for predicting limb movement locus and prediction error thereof and electronic device
CN115344047A (en) * 2022-08-22 2022-11-15 吉林大学 Robot switching type predictive control trajectory tracking method based on neural network model
CN118502250A (en) * 2024-07-16 2024-08-16 广东工业大学 Data processing system, method and device for unmanned aerial vehicle and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103558856A (en) * 2013-11-21 2014-02-05 东南大学 Service mobile robot navigation method in dynamic environment
CN106292290A (en) * 2016-09-28 2017-01-04 浙江工业大学 A kind of wheeled mobile robot point is calmed rolling optimization control method
US20170302218A1 (en) * 2014-12-02 2017-10-19 Electronic Power Design System and Method for HYBRID POWER GENERATION

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103558856A (en) * 2013-11-21 2014-02-05 东南大学 Service mobile robot navigation method in dynamic environment
US20170302218A1 (en) * 2014-12-02 2017-10-19 Electronic Power Design System and Method for HYBRID POWER GENERATION
CN106292290A (en) * 2016-09-28 2017-01-04 浙江工业大学 A kind of wheeled mobile robot point is calmed rolling optimization control method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
曾志文 等: ""基于模型预测控制的移动机器人轨迹跟踪"", 《控制工程》 *
邓骏: ""基于预测控制的非完整移动机器人视觉伺服"", 《优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110244703A (en) * 2019-03-28 2019-09-17 浙江工业大学 A kind of mobile robot forecast Control Algorithm with external disturbance and data exception
CN110244703B (en) * 2019-03-28 2022-05-03 浙江工业大学 Mobile robot prediction control method with external interference and data abnormity
CN109866255A (en) * 2019-04-11 2019-06-11 吉林大学 A kind of recognition methods of robot motion's direction and device
CN109866255B (en) * 2019-04-11 2021-10-01 吉林大学 Robot motion orientation identification method and device
CN110095983B (en) * 2019-04-22 2021-11-23 浙江工业大学 Mobile robot prediction tracking control method based on path parameterization
CN110095983A (en) * 2019-04-22 2019-08-06 浙江工业大学 A kind of mobile robot predicting tracing control method based on path parameter
CN110470298A (en) * 2019-07-04 2019-11-19 浙江工业大学 A kind of Robot Visual Servoing position and orientation estimation method based on rolling time horizon
CN110470298B (en) * 2019-07-04 2021-02-26 浙江工业大学 Robot vision servo pose estimation method based on rolling time domain
CN111309002A (en) * 2019-11-26 2020-06-19 华南理工大学 Wheel type mobile robot obstacle avoidance method and system based on vector
CN111283683A (en) * 2020-03-04 2020-06-16 湖南师范大学 Servo tracking accelerated convergence method for robot visual feature planning track
CN112894812A (en) * 2021-01-21 2021-06-04 中山大学 Visual servo trajectory tracking control method and system for mechanical arm
CN114418159A (en) * 2021-10-29 2022-04-29 中国科学院宁波材料技术与工程研究所 Method and system for predicting limb movement locus and prediction error thereof and electronic device
CN114418159B (en) * 2021-10-29 2023-01-03 中国科学院宁波材料技术与工程研究所 Method and system for predicting limb movement locus and prediction error thereof and electronic device
CN115344047A (en) * 2022-08-22 2022-11-15 吉林大学 Robot switching type predictive control trajectory tracking method based on neural network model
CN118502250A (en) * 2024-07-16 2024-08-16 广东工业大学 Data processing system, method and device for unmanned aerial vehicle and storage medium
CN118502250B (en) * 2024-07-16 2024-10-15 广东工业大学 Data processing system, method and device for unmanned aerial vehicle and storage medium

Similar Documents

Publication Publication Date Title
CN109213175A (en) A kind of mobile robot visual servo track tracking prediction control method based on primal-dual neural network
CN108839026B (en) Visual servo tracking prediction control method for mobile robot
CN109102525B (en) Mobile robot following control method based on self-adaptive posture estimation
CN110095983B (en) Mobile robot prediction tracking control method based on path parameterization
CN109760047B (en) Stage robot prediction control method based on vision sensor
CN110703692B (en) Multi-mobile-robot distributed predictive control method based on virtual structure method
Wang et al. Design of robotic visual servo control based on neural network and genetic algorithm
CN114721275B (en) Visual servo robot self-adaptive tracking control method based on preset performance
Mousavi et al. Robust adaptive fractional-order nonsingular terminal sliding mode stabilization of three-axis gimbal platforms
CN104298244A (en) Industrial robot three-dimensional real-time and high-precision positioning device and method
CN113910218B (en) Robot calibration method and device based on kinematic and deep neural network fusion
CN114942593A (en) Mechanical arm self-adaptive sliding mode control method based on disturbance observer compensation
CN112650217B (en) Robot trajectory tracking strategy dynamic optimization method based on evaluation function
CN114434441A (en) Mobile robot visual servo tracking control method based on self-adaptive dynamic programming
CN114986498B (en) Cooperative control method for mobile operation arm
CN113199481B (en) Robot motion control method, device, electronic apparatus, and medium
Burlacu et al. Reference trajectory-based visual predictive control
CN113580146A (en) Mechanical arm real-time obstacle avoidance method integrating dynamic system and model predictive control
CN107894709A (en) Controlled based on Adaptive critic network redundancy Robot Visual Servoing
Morel et al. Robust visual servoing: Bounding the task function tracking errors
Ghasemi et al. Adaptive image-based visual servoing of 6 DOF robots using switch approach
Chen et al. Adaptive Stiffness Visual Servoing for Unmanned Aerial Manipulators With Prescribed Performance
CN110488608B (en) Intelligent kinetic parameter identification method and module for driving and controlling integrated control system
CN118456447B (en) Data processing system, method and device based on visual positioning and formation prediction
CN114083545B (en) Moving object robot grabbing method and device based on visual perception

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190115