CN114905527A - Football robot interception method based on Markov chain and football robot - Google Patents
Football robot interception method based on Markov chain and football robot Download PDFInfo
- Publication number
- CN114905527A CN114905527A CN202210613737.5A CN202210613737A CN114905527A CN 114905527 A CN114905527 A CN 114905527A CN 202210613737 A CN202210613737 A CN 202210613737A CN 114905527 A CN114905527 A CN 114905527A
- Authority
- CN
- China
- Prior art keywords
- football
- information
- robot
- interception
- intercepting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000009471 action Effects 0.000 claims abstract description 47
- 230000000903 blocking effect Effects 0.000 claims description 38
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000007704 transition Effects 0.000 claims description 27
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/08—Programme-controlled manipulators characterised by modular constructions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The application provides a football robot interception method and football robot based on Markov chain, include: obtaining football field information, player information, current football posture information and position information; predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information; generating a predicted intercepting position and an intercepting action of the football robot by using a Markov chain algorithm, a game algorithm and the football running track; the execution football robot predicts the interception action information and generates the interception action information of the football robot through a Markov chain algorithm and a game algorithm, so that the football robot can counterattack according to the interception action information of football players, the intellectualization of the football robot is greatly improved, and the training capacity of the football players is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a football robot intercepting method based on Markov chains and a football robot.
Background
Present football robot all is conventional fixed point interception, and football person is towards football robot batting promptly, and football robot makes and sets for and single interception action in sensor (for example infrared sensor, position sensor etc.) response back, and is relatively poor to football person's training effect this moment, exists a great deal of not enoughly.
Disclosure of Invention
The application provides a football robot interception method and football robot based on Markov chain aims at solving football robot and all is conventional fixed point counterattack, and football person is towards football robot batting promptly, and football robot makes and sets for and single interception action after sensor (for example infrared sensor, position sensor etc.) response, to football person's the relatively poor problem of training effect this moment.
The embodiment of the first aspect of the application provides a markov chain-based football robot intercepting method, which is executed by a football robot and comprises the following steps:
obtaining football field information, player information, current football posture information and position information;
predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information;
generating a predicted intercepting position and an intercepting action of the football robot by using a Markov chain algorithm, a game algorithm and the football running track;
and executing the predicted intercepting action information of the football robot.
In an optional embodiment, the generating of the predicted intercepting position and the intercepting action of the soccer robot by using the markov chain algorithm, the game algorithm and the soccer moving trajectory includes:
generating all possible intercepting positions and corresponding intercepting actions of the football robot and the intercepting probability of each intercepting position according to the game algorithm and the football running track;
generating a state transition matrix of a Markov chain according to all the blocking action information which can be executed by the football robot and the probability of each blocking action information;
and generating the predicted intercepting position and the intercepting action of the football robot according to the state transition matrix.
In an optional embodiment, generating all possible interception positions and corresponding interception actions of the soccer robot and the interception probability of each interception position according to the game algorithm and the soccer running trajectory includes:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
In an alternative embodiment, the generating a state transition matrix of a markov chain according to all the blocking action information that may be executed by the soccer robot and the probability of each blocking action information includes:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the football interception estimated time or not;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming the state transition matrix of the Markov chain by all the probability values.
An embodiment of the second aspect of the present application provides a markov chain-based soccer robot, including:
the acquisition module acquires football field information, player information, current football posture information and position information;
the running track generation module is used for predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information;
the intercepting information generating module generates a predicted intercepting position and an intercepting action of the football robot by utilizing a Markov chain algorithm, a game algorithm and the football running track;
and the moving module executes the predicted intercepting action information of the football robot.
In an optional embodiment, the interception information generating module includes:
the game prediction unit generates all blocking positions and corresponding blocking actions which can be executed by the football robot and the blocking probability of each blocking position according to the game algorithm and the football running track;
the state transition matrix generating unit is used for generating a state transition matrix of a Markov chain according to all the blocking action information which can be executed by the football robot and the probability of each piece of blocking action information;
and the foot prediction action unit generates a predicted intercepting position and an intercepting action of the football robot according to the state transition matrix.
In an optional embodiment, the game prediction unit is specifically configured to:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
In an optional embodiment, the state transition matrix generating unit is specifically configured to:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the estimated time of the football interception;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming a state transition matrix of the Markov chain by all the probability values.
According to the technical scheme, the football robot interception method based on the Markov chain and the football robot generate the interception action information of the football robot through the Markov chain algorithm and the game algorithm, so that counterattack can be performed according to the shooting action and the position of football players, the intellectualization of the football robot is greatly improved, and the training capacity of the football players is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are 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 schematic flowchart of a markov chain-based soccer robot interception method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a soccer robot in an embodiment of the present application.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise. It should be noted that the markov chain-based soccer robot interception method and the soccer robot disclosed in the present application can be used in the field of artificial intelligence, and can also be used in any field other than the field of artificial intelligence.
In a first aspect, an embodiment of the present application provides a markov chain-based soccer robot interception method, as shown in fig. 1, performed by a soccer robot, including:
s1: obtaining football field information, player information, current football posture information and position information;
s2: predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information;
s3: generating a predicted intercepting position and an intercepting action of the football robot by using a Markov chain algorithm, a game algorithm and the football running track;
s4: and executing the predicted intercepting action information of the football robot.
The application provides a football robot interception method based on Markov chain through Markov chain algorithm and game algorithm, generates football robot's interception action information to can be according to football player's interception action information and counterattack, improved football robot's intellectuality greatly, improved football player's training ability.
In principle, the Game algorithm can be Bash Game (Bash Game), Weizhou Game (Wythoff Game) and the like, the Game algorithm can determine Game points according to the interception action information of football players, possible action probabilities are generated by matching with a Markov chain, and the maximum probability value can be selected as the best corresponding mode.
In an optional embodiment, the generating of the predicted intercepting position and the intercepting action of the soccer robot by using the markov chain algorithm, the game algorithm and the soccer moving trajectory includes:
generating all possible interception positions and corresponding interception actions of the football robot and the interception probability of each interception position according to the game algorithm and the football running track;
generating a state transition matrix of a Markov chain according to all the blocking action information which can be executed by the football robot and the probability of each blocking action information;
and generating the predicted intercepting position and the intercepting action of the football robot according to the state transition matrix.
In an optional embodiment, generating all possible interception positions and corresponding interception actions of the soccer robot and the interception probability of each interception position according to the game algorithm and the soccer running trajectory includes:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
In an alternative embodiment, the generating a state transition matrix of a markov chain according to all the blocking action information that may be executed by the soccer robot and the probability of each blocking action information includes:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the estimated time of the football interception;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming the state transition matrix of the Markov chain by all the probability values.
An embodiment of the second aspect of the present application provides a markov chain-based soccer robot, as shown in fig. 2, including:
the acquisition module 11 is used for acquiring football field information, player information, current football posture information and position information;
the running track generation module 12 is used for predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information;
the interception information generation module 13 generates a predicted interception position and an interception action of the football robot by using a Markov chain algorithm, a game algorithm and the football running track;
and a moving module 14 for executing the predicted intercepting action information of the football robot.
The application provides a pair of football robot based on Markov chain through Markov chain algorithm and game algorithm, generates football robot's interception action information to can be according to football player's interception action information and counterattack, improved football robot's intellectuality greatly, improved football player's training ability.
In an optional embodiment, the interception information generating module includes:
the game prediction unit generates all blocking positions and corresponding blocking actions which can be executed by the football robot and the blocking probability of each blocking position according to the game algorithm and the football running track;
the state transition matrix generating unit is used for generating a state transition matrix of a Markov chain according to all the blocking action information which can be executed by the football robot and the probability of each piece of blocking action information;
and the foot prediction action unit generates a predicted intercepting position and an intercepting action of the football robot according to the state transition matrix.
In an optional embodiment, the game prediction unit is specifically configured to:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
In an optional embodiment, the state transition matrix generating unit is specifically configured to:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the estimated time of the football interception;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming the state transition matrix of the Markov chain by all the probability values.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (8)
1. A football robot interception method based on Markov chain is characterized by being executed by a football robot and comprising the following steps:
obtaining football field information, player information, current football posture information and position information;
predicting the running track of the football according to the football field information, the player information, the current football posture information and the position information;
generating a predicted intercepting position and an intercepting action of the football robot by using a Markov chain algorithm, a game algorithm and the football running track;
and executing the predicted intercepting action information of the football robot.
2. The soccer robot intercepting method of claim 1, wherein the generating of the predicted intercepting position and the intercepting action of the soccer robot using the markov chain algorithm, the game algorithm, and the soccer ball running trajectory comprises:
generating all possible intercepting positions and corresponding intercepting actions of the football robot and the intercepting probability of each intercepting position according to the game algorithm and the football running track;
generating a state transition matrix of a Markov chain according to all possible interception positions and corresponding interception actions of the football robot and the interception probability of each interception position;
and generating the predicted intercepting position and the intercepting action of the football robot according to the state transition matrix.
3. The soccer robot intercepting method of claim 2, wherein generating all possible intercepting positions and corresponding intercepting actions of the soccer robot and the intercepting probability of each intercepting position according to the game algorithm and the soccer motion trajectory comprises:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
4. The soccer robot interception method according to claim 2, wherein generating a Markov chain state transition matrix according to all possible interception action information of the soccer robot and the probability of each interception action information comprises:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the estimated time of the football interception;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming the state transition matrix of the Markov chain by all the probability values.
5. A markov chain-based soccer robot, comprising:
the acquisition module acquires football field information, player information, current football posture information and position information;
the running track generation module predicts a football running track according to football field information, player information, current football posture information and position information;
the intercepting information generating module generates a predicted intercepting position and an intercepting action of the football robot by utilizing a Markov chain algorithm, a game algorithm and the football running track;
and the moving module executes the predicted intercepting action information of the football robot.
6. The soccer robot of claim 5, wherein the interception information generating module comprises:
the game prediction unit generates all blocking positions and corresponding blocking actions which can be executed by the football robot and the blocking probability of each blocking position according to the game algorithm and the football running track;
the state transition matrix generating unit is used for generating a state transition matrix of a Markov chain according to all the blocking action information which can be executed by the football robot and the probability of each piece of blocking action information;
and the foot prediction action unit generates a predicted intercepting position and an intercepting action of the football robot according to the state transition matrix.
7. The soccer robot of claim 6, wherein the game prediction unit is specifically configured to:
blocking posture information and ball catching results of football players on the football field when the football players catch the football opponents to generate possible position information and blocking posture information of the football players;
and generating the ball catching probability of each piece of position information and interception posture information by combining a game algorithm, and further obtaining all possible executed position information, interception posture information and corresponding interception probability of the football robot.
8. The soccer robot of claim 6, wherein the state transition matrix generation unit is specifically configured to:
generating time for reaching all possible executed position information of the football robot according to all possible position information, interception posture information and corresponding probability of the football robot and by combining the current position information of the football robot;
judging whether the time is higher than the estimated time of the football interception;
the current position information and the interception attitude information of the football robot are combined, and a probability value is given to the position information and the interception attitude information of which each time is lower than the estimated football interception time according to the time;
and forming the state transition matrix of the Markov chain by all the probability values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613737.5A CN114905527A (en) | 2022-05-31 | 2022-05-31 | Football robot interception method based on Markov chain and football robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613737.5A CN114905527A (en) | 2022-05-31 | 2022-05-31 | Football robot interception method based on Markov chain and football robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114905527A true CN114905527A (en) | 2022-08-16 |
Family
ID=82771647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210613737.5A Pending CN114905527A (en) | 2022-05-31 | 2022-05-31 | Football robot interception method based on Markov chain and football robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114905527A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984479A (en) * | 2017-06-02 | 2018-12-11 | 浙江师范大学 | It is a kind of for improving the new method of crowdsourcing platform operational efficiency |
| CN109492887A (en) * | 2018-10-25 | 2019-03-19 | 浙江工商大学 | Mobile intelligent perception motivational techniques based on gesture theory of games |
| WO2019234700A1 (en) * | 2018-06-08 | 2019-12-12 | Politecnico Di Milano | A predictive control method of a robot and related control system |
| CN110653819A (en) * | 2019-09-25 | 2020-01-07 | 上海大学 | System and method for generating kicking action of humanoid robot |
| EP3742343A1 (en) * | 2019-05-20 | 2020-11-25 | NVIDIA Corporation | Autonomous vehicle simulation using machine learning |
| CN112329348A (en) * | 2020-11-06 | 2021-02-05 | 东北大学 | Intelligent decision-making method for military countermeasure game under incomplete information condition |
| US11340079B1 (en) * | 2018-05-21 | 2022-05-24 | AI Incorporated | Simultaneous collaboration, localization, and mapping |
-
2022
- 2022-05-31 CN CN202210613737.5A patent/CN114905527A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984479A (en) * | 2017-06-02 | 2018-12-11 | 浙江师范大学 | It is a kind of for improving the new method of crowdsourcing platform operational efficiency |
| US11340079B1 (en) * | 2018-05-21 | 2022-05-24 | AI Incorporated | Simultaneous collaboration, localization, and mapping |
| WO2019234700A1 (en) * | 2018-06-08 | 2019-12-12 | Politecnico Di Milano | A predictive control method of a robot and related control system |
| CN109492887A (en) * | 2018-10-25 | 2019-03-19 | 浙江工商大学 | Mobile intelligent perception motivational techniques based on gesture theory of games |
| EP3742343A1 (en) * | 2019-05-20 | 2020-11-25 | NVIDIA Corporation | Autonomous vehicle simulation using machine learning |
| CN110653819A (en) * | 2019-09-25 | 2020-01-07 | 上海大学 | System and method for generating kicking action of humanoid robot |
| CN112329348A (en) * | 2020-11-06 | 2021-02-05 | 东北大学 | Intelligent decision-making method for military countermeasure game under incomplete information condition |
Non-Patent Citations (3)
| Title |
|---|
| QINGYU ZHANG ETC.: "Addressing Mandatory Lane Change Problem with Game Theoretic Model Predictive Control and Fuzzy Markov Chain", 《 2018 ANNUAL AMERICAN CONTROL CONFERENCE》 * |
| 黄媛媛: "机器人协作博弈的建模与仿真", 《中国优秀硕士学位论文全文 电子期刊网 信息科技辑》 * |
| 黎继巧: "有限群体博弈Nash平衡的存在性及随机稳定性", 《中国优秀硕士学位论文全文 电子期刊网 基础科学辑 》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10748376B2 (en) | Real-time game tracking with a mobile device using artificial intelligence | |
| CN109107161B (en) | Game object control method, device, medium and equipment | |
| Gray | “Markov at the bat”: A model of cognitive processing in baseball batters | |
| Pfau et al. | Towards deep player behavior models in mmorpgs | |
| KR102143906B1 (en) | Method and system for performing environment adapting stategy based on ai | |
| Hanke et al. | A recommender system for hero line-ups in MOBA games | |
| Galli et al. | A cheating detection framework for unreal tournament iii: A machine learning approach | |
| Yang et al. | TennisMaster: An IMU-based online serve performance evaluation system | |
| Young et al. | Evolutionary learning of goal priorities in a real-time strategy game | |
| Ghosh et al. | Sports analytics review: Artificial intelligence applications, emerging technologies, and algorithmic perspective | |
| KR20190127196A (en) | Method and apparatus for real - time monitoring of baseball game using artificial neural network | |
| CN114905527A (en) | Football robot interception method based on Markov chain and football robot | |
| JP6432523B2 (en) | Analysis device, recording medium, and analysis method | |
| Brault et al. | Detecting deceptive movement in 1 vs. 1 based on global body displacement of a rugby player | |
| CN114904247A (en) | Tennis robot slapping method based on Markov chain and tennis robot | |
| Rusydi et al. | Pattern recognition of overhead forehand and backhand in badminton based on the sign of local euler angle | |
| Sestini et al. | Efficient Inverse Reinforcement Learning in Procedurally Generated Environments | |
| CN112870727B (en) | Training and control method for intelligent agent in game | |
| CN114986503A (en) | Multi-robot cooperative motion method and football robot | |
| Röfer et al. | B-Human 2019–complex team play under natural lighting conditions | |
| Wang et al. | Refining co-operative competition of robocup soccer with reinforcement learning | |
| Raza et al. | On learning coordination among soccer agents | |
| Simard et al. | Bounding an optimal search path with a game of cop and robber on graphs | |
| Rajesh et al. | Predict the Game Analysis of Cricket Match Winning Using K-Nearest Neighbor and Compare Prediction Accuracy Over Support Vector Machine | |
| Ferguson et al. | Imitating playstyle with dynamic time warping imitation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220816 |
|
| WD01 | Invention patent application deemed withdrawn after publication |