CN110974425B - Method for training surgical instrument clamping force sensing model - Google Patents
Method for training surgical instrument clamping force sensing model Download PDFInfo
- Publication number
- CN110974425B CN110974425B CN201911327800.3A CN201911327800A CN110974425B CN 110974425 B CN110974425 B CN 110974425B CN 201911327800 A CN201911327800 A CN 201911327800A CN 110974425 B CN110974425 B CN 110974425B
- Authority
- CN
- China
- Prior art keywords
- surgical instrument
- driving
- clamping force
- load
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000033001 locomotion Effects 0.000 claims abstract description 63
- 230000008447 perception Effects 0.000 claims description 21
- 238000010276 construction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000002324 minimally invasive surgery Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/30—Surgical robots
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/70—Manipulators specially adapted for use in surgery
- A61B34/76—Manipulators having means for providing feel, e.g. force or tactile feedback
Landscapes
- Health & Medical Sciences (AREA)
- Surgery (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Robotics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Manipulator (AREA)
Abstract
A method for training a clamping force sensing model of a surgical instrument belongs to the field of medical robots. The problems of low clamping force sensing precision, inconvenience in use and poor adaptability of the existing minimally invasive surgery robot system are solved. The method comprises the steps of firstly collecting an idle load motion sample set and a loaded motion sample set of all surgical instruments of the same class in an idle load state, training a clamping force sensing model in the prior art by utilizing a deep learning mode, and obtaining the trained clamping force sensing model. The invention is mainly used for sensing the clamping force of the surgical instrument of the minimally invasive surgical robot.
Description
Technical Field
The invention belongs to the field of medical robots.
Background
The advent of minimally invasive surgical robots has reduced the burden on patients and doctors. The doctor controls the surgical instruments entering the body of the patient to perform the operation by operating the master hand. The existing minimally invasive surgery robot system mainly depends on visual feedback, and most of the existing minimally invasive surgery robot systems cannot provide intraoperative clamping force perception for doctors. The lack of clamping force greatly reduces the on-site feeling of the operation, increases the training cost of doctors and the possibility of misoperation in the operation, and even can endanger the life of patients, so the requirement of intuition of the minimally invasive operation cannot be effectively met.
The existing scheme for sensing the clamping force of the surgical instrument mainly comprises the following types: the method comprises the steps of designing a clamping force sensor specially, designing a steel wire rope tension sensor to indirectly calculate the clamping force, calculating the clamping force based on a dynamic model modeling, and obtaining the clamping force based on a learning algorithm. The specially designed clamping force sensor is still in the research and development stage due to the defects of high cost, large occupied space, influence on high-temperature disinfection and the like; the clamping force is indirectly calculated by utilizing the steel wire rope tension sensor, and due to the fact that the modeling accuracy of the nonlinear rope pulley transmission system is limited, the sensing precision of the clamping force is reduced, and the defects that the high cost affects high-temperature disinfection still exist; the modeling based on the dynamic model does not need extra hardware cost and does not influence high-temperature disinfection, but the sensing accuracy is lower because the nonlinearity of the dynamic model is stronger and the accurate modeling is difficult; the clamping force is acquired based on the learning algorithm, the non-linear rope wheel dynamic model is automatically learned by the learning algorithm by utilizing the pre-acquired data of the drive end sensor and the data of the tail end clamping force, the additional hardware cost is not needed, the accuracy is greatly improved compared with that of a dynamic modeling method, and the accuracy of an untrained surgical instrument and a clamped object is reduced. In a word, the existing scheme does not meet the requirements of low cost, high precision, convenient use and strong adaptability of clamping force perception. Therefore, the above problems need to be solved.
Disclosure of Invention
The invention provides a method for training a clamping force sensing model of a surgical instrument, aiming at solving the problems of low clamping force sensing precision, inconvenience in use and poor adaptability of the existing minimally invasive surgery robot system.
The method for training the surgical instrument clamping force sensing model is realized based on a driving motor, and the driving motor is used for driving N surgical instruments of the same kind respectively; n is an integer greater than 5;
the training method comprises the following steps:
the method comprises the following steps that firstly, no-load driving is carried out on each surgical instrument through a driving motor, motion characteristics of all the surgical instruments are extracted in a no-load state, and a no-load motion sample set is constructed;
secondly, carrying out on-load driving on each surgical instrument through a driving motor, enabling a hand grip of each surgical instrument to respectively press M objects to be clamped, and collecting the current, the angular position, the angular speed and the pressure of M groups of objects to be clamped of M groups of driving motors of each surgical instrument in an on-load motion state, so as to obtain an on-load motion sample set of all surgical instruments; m is an integer greater than 10;
and step three, taking the no-load motion sample set and the loaded motion sample set as training samples of the clamping force perception model, training the clamping force perception model, taking data corresponding to each surgical instrument in the no-load motion sample set and data corresponding to the loaded motion sample set as a group of training data to train the clamping force perception model during training, and finally obtaining the trained clamping force perception model so as to finish the training of the clamping force perception model.
Preferably, in the step one, the no-load driving is performed on each surgical instrument through the driving motor, the motion characteristic extraction is performed on all the surgical instruments in the no-load state, and the specific process of constructing the no-load motion sample set is as follows:
step one, carrying out no-load driving on each surgical instrument through a driving motor to obtain the current, the angular position and the angular speed of the driving motor of each surgical instrument under the condition of no-load driving;
step two, training the feature extractor by using the current, the angular position and the angular speed of a driving motor of all surgical instruments under the condition of no-load driving to obtain the trained feature extractor;
and step three, performing feature extraction on the current, the angular position and the angular speed of the driving motor of all the surgical instruments under the condition of no-load driving by using the trained feature extractor to obtain the motion features of each surgical instrument under the condition of no-load driving, and taking the motion features of all the surgical instruments under the condition of no-load driving as a no-load motion sample set so as to complete the construction of the no-load motion sample set.
Preferably, in the step two, the driving motor drives each surgical instrument in an on-load manner, so that the gripper of each surgical instrument presses M objects to be clamped respectively, and the current, the angular position, the angular velocity and the pressure of M groups of objects to be clamped of M groups of driving motors of each surgical instrument in an on-load movement state are acquired, so as to obtain an on-load movement sample set of all surgical instruments, which specifically comprises the following steps:
secondly, carrying out loading driving on each surgical instrument through a driving motor, enabling a gripper of the surgical instrument to press each object to be clamped, collecting the current, the angular position, the angular speed and the pressure of the object to be clamped of the driving motor of the corresponding surgical instrument in a loading motion state under the condition of pressing each operation object, and obtaining the current, the angular position, the angular speed and the pressure of M groups of driving motors of each surgical instrument in the loading motion state;
and secondly, taking the current, the angular position and the angular speed of the driving motor of all the surgical instruments in a carrying state and the pressure of the corresponding object to be clamped as a carrying motion sample set of all the surgical instruments, thereby completing the construction of the carrying motion sample set of all the surgical instruments.
Preferably, the M objects to be held differ in size and elasticity.
The invention has the advantages that the defects of high cost, poor precision, inconvenient use and poor adaptability of the clamping force sensing scheme of the existing minimally invasive surgery robot system are overcome, the high-precision clamping force sensing can be realized at low hardware cost, the use is convenient, the high-temperature disinfection is not influenced, the independent training of each surgical instrument is not required, and the adaptability to different clamped objects is strong. Specifically, the characteristics are extracted through a learning algorithm, and a dynamic model is learned by using data acquired offline, so that modeling errors are avoided, and the clamping force sensing precision can be improved. Any clamping force sensing model trained by the invention can sense the clamping force by only acquiring the current of the motor, the angular position of the driving motor and the angular speed of the driving motor in actual use, has no extra hardware cost, and does not influence high-temperature disinfection.
In order to ensure high adaptability of the clamping force perception model to different instruments, the invention introduces the idea of 'parameter identification' and utilizes a learning algorithm to autonomously extract the motion characteristics of the instruments. In addition, the training set contains articles with different physical parameters such as size and elasticity, the expected dynamic model can be guided to learn by a learning algorithm, the sensing precision of the clamping force is improved, and meanwhile, the high adaptability to different clamped articles can be guaranteed.
Drawings
FIG. 1 is a diagram showing the relative positions of a driving motor, an instrument to be operated, an object to be clamped, and a force sensor; wherein reference numeral 2 denotes an object to be clamped and reference numeral 3 denotes a force sensor.
Fig. 2 is a schematic diagram illustrating a method for training a clamping force sensing model of a surgical instrument according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
Referring to fig. 1, the method for training the clamping force sensing model of the surgical instrument according to the embodiment is implemented based on driving motors, and the driving motors are used for driving N surgical instruments 1 of the same type respectively; n is an integer greater than 5;
the training method comprises the following steps:
firstly, carrying out no-load driving on each surgical instrument 1 through a driving motor, carrying out motion characteristic extraction on all surgical instruments 1 in a no-load state, and constructing a no-load motion sample set;
secondly, carrying out loading driving on each surgical instrument 1 through a driving motor, enabling a gripper 1-1 of each surgical instrument 1 to respectively press M objects to be clamped, and collecting the current, the angular position and the angular speed of M groups of driving motors and the pressure of M groups of objects to be clamped of each surgical instrument 1 in a loading driving state, so as to obtain loading motion sample sets of all the surgical instruments 1; m is an integer greater than 10;
and step three, taking the no-load motion sample set and the loaded motion sample set as training samples of the clamping force perception model, training the clamping force perception model, taking data corresponding to each surgical instrument 1 in the no-load motion sample set and data corresponding to the loaded motion sample set as a group of training data to train the clamping force perception model during training, and finally obtaining a trained clamping force perception model so as to finish training the clamping force perception model.
In the embodiment, when each surgical instrument 1 is driven to be loaded through the driving motor in the training process, the object to be measured 2 is arranged above the force sensor 3, and the force applied to the object to be measured 2 by the hand grip 1-1 of the surgical instrument 1 is collected through the force sensor 3.
In the present embodiment, the clamping force perception model is a model for obtaining perception force, and this model is a conventional model.
The method comprises the steps of firstly collecting an idle load motion sample set and a loaded motion sample set of all surgical instruments 1 in the same class in an idle load state, training a clamping force sensing model in the prior art by utilizing a deep learning mode, and obtaining the trained clamping force sensing model.
When the clamping force sensing model is applied specifically, the trained clamping force sensing model is used for receiving the current, the angular position and the angular speed of the driving motor of the to-be-operated instrument in the actual operation process, the trained clamping force sensing model can directly output the sensing force, and the acting force of the to-be-operated instrument on the to-be-operated object can be sensed with high precision.
Further, in the step one, each surgical instrument 1 is driven in an idle-load manner by a driving motor, and motion characteristics of all the surgical instruments 1 are extracted in an idle-load state, wherein a specific process of constructing an idle-load motion sample set is as follows:
step one, carrying out no-load driving on each surgical instrument 1 through a driving motor to obtain the current, the angular position and the angular speed of the driving motor of each surgical instrument 1 under the condition of no-load driving;
step two, training the feature extractor by using the current, the angular position and the angular speed of the driving motor of all the surgical instruments 1 under the condition of no-load driving to obtain the trained feature extractor;
and step three, performing feature extraction on the current, the angular position and the angular speed of the driving motors of all the surgical instruments 1 under the condition of no-load driving by using the trained feature extractor to obtain the motion features of each surgical instrument 1 under the condition of no-load driving, and taking the motion features of all the surgical instruments 1 under the condition of no-load driving as a no-load motion sample set, thereby completing the construction of the no-load motion sample set.
Furthermore, in the step two, each surgical instrument 1 is driven in a loading manner by the driving motor, so that the gripper 1-1 of each surgical instrument 1 presses M objects to be clamped respectively, and the current, the angular position, the angular velocity and the pressure of M groups of objects to be clamped of M groups of driving motors of each surgical instrument 1 in a loading state are acquired, so that the specific process of obtaining a loading motion sample set of all surgical instruments 1 is as follows:
secondly, carrying out loading driving on each surgical instrument 1 through a driving motor, enabling a gripper 1-1 of each surgical instrument 1 to press each object to be clamped, and acquiring the current, the angular position, the angular speed and the pressure of the object to be clamped of the driving motor in a loading motion state of the corresponding surgical instrument 1 under the condition of pressing each operation object to obtain the current, the angular position, the angular speed and the pressure of M groups of driving motors of each surgical instrument 1 in a loading motion state;
and step two, taking the current, the angular position and the angular speed of the driving motor of all the surgical instruments 1 in the carrying state and the corresponding pressure of the object to be clamped as the carrying motion sample set of all the surgical instruments 1, thereby completing the construction of the carrying motion sample set of all the surgical instruments 1.
In the present preferred embodiment, what is obtained in the first step is the current of the M sets of driving motors, the angular position of the M sets of driving motors, the angular velocity of the M sets of driving motors, and the pressure of the M sets of objects to be clamped of each surgical instrument 1 in the carrying state. Each object to be clamped corresponds to one group of data.
Further, the size and elasticity of the M objects to be held are different.
In the preferred embodiment, high adaptability to different operating objects is ensured just because of the diversity of the objects to be clamped.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that features described in different dependent claims and herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (4)
1. The method for training the surgical instrument clamping force sensing model is realized based on a driving motor, and the driving motor is used for driving N surgical instruments (1) of the same kind respectively; n is an integer greater than 5;
the training method is characterized by comprising the following steps:
the method comprises the following steps that firstly, no-load driving is carried out on each surgical instrument (1) through a driving motor, motion characteristic extraction is carried out on all the surgical instruments (1) in a no-load state, and a no-load motion sample set composed of the motion characteristics of all the surgical instruments (1) in the no-load state is constructed;
secondly, carrying out loading driving on each surgical instrument (1) through a driving motor, enabling a gripper (1-1) of each surgical instrument (1) to respectively press M objects to be clamped, and acquiring the current, the angular position, the angular speed and the pressure of M groups of objects to be clamped of M groups of driving motors of each surgical instrument (1) in a loading driving state, so as to obtain a loading motion sample set consisting of the current, the angular position, the angular speed and the corresponding pressure of the objects to be clamped of all the surgical instruments (1) in the loading driving state; m is an integer greater than 10;
and step three, taking the no-load motion sample set and the loaded motion sample set as training samples of the clamping force perception model, training the clamping force perception model, taking data corresponding to each surgical instrument (1) in the no-load motion sample set and data corresponding to the loaded motion sample set as a group of training data to train the clamping force perception model during training, and finally obtaining the trained clamping force perception model so as to finish the training of the clamping force perception model.
2. The method for training the clamping force sensing model of the surgical instrument according to claim 1, wherein in the step one, each surgical instrument (1) is driven in an idle state by a driving motor, and the motion characteristics of all the surgical instruments (1) in the idle state are extracted, and a specific process for constructing the idle motion sample set composed of the motion characteristics of all the surgical instruments (1) in the idle state is as follows:
step one, carrying out no-load driving on each surgical instrument (1) through a driving motor to obtain the current, the angular position and the angular speed of the driving motor of each surgical instrument (1) under the condition of no-load driving;
step two, training the feature extractor by using the current, the angular position and the angular speed of a driving motor of all the surgical instruments (1) under the condition of no-load driving to obtain the trained feature extractor;
and step three, performing feature extraction on the current, the angular position and the angular speed of the driving motor of all the surgical instruments (1) under the condition of no-load driving by using the trained feature extractor to obtain the motion features of each surgical instrument (1) under the condition of no-load driving, and taking the motion features of all the surgical instruments (1) under the condition of no-load driving as a no-load motion sample set so as to complete the construction of the no-load motion sample set.
3. The method for training the surgical instrument clamping force sensing model according to claim 1 or 2, wherein in the step two, each surgical instrument (1) is driven with a load by a driving motor, so that the grippers (1-1) of each surgical instrument (1) respectively press M objects to be clamped, and the current, the angular position, the angular velocity and the pressure of M groups of driving motors of each surgical instrument (1) in a carrying state are collected, so as to obtain a carrying motion sample set consisting of the current, the angular position, the angular velocity and the corresponding pressure of the objects to be clamped of the driving motors of all the surgical instruments (1) in the carrying state:
secondly, carrying out loading driving on each surgical instrument (1) through a driving motor, enabling a gripper (1-1) of each surgical instrument (1) to press each object to be clamped, and acquiring the current, the angular position, the angular speed and the pressure of the object to be clamped of the driving motor of the corresponding surgical instrument (1) in a loading motion state under the condition of pressing each operation object to obtain the current, the angular position, the angular speed and the pressure of M groups of driving motors of each surgical instrument (1) in the loading motion state;
and secondly, taking the current, the angular position and the angular speed of the driving motor of all the surgical instruments (1) in a carrying state and the corresponding pressure of the object to be clamped as a carrying motion sample set of all the surgical instruments (1), thereby completing the construction of the carrying motion sample set of all the surgical instruments (1).
4. The method of training a surgical instrument clamping force perception model according to claim 1, wherein the size and elasticity of the M objects to be clamped are different.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911327800.3A CN110974425B (en) | 2019-12-20 | 2019-12-20 | Method for training surgical instrument clamping force sensing model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911327800.3A CN110974425B (en) | 2019-12-20 | 2019-12-20 | Method for training surgical instrument clamping force sensing model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110974425A CN110974425A (en) | 2020-04-10 |
| CN110974425B true CN110974425B (en) | 2020-10-30 |
Family
ID=70073647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911327800.3A Active CN110974425B (en) | 2019-12-20 | 2019-12-20 | Method for training surgical instrument clamping force sensing model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110974425B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308026B (en) * | 2020-11-23 | 2022-10-14 | 哈尔滨工业大学 | Surgical instrument clamping force sensing method based on deep learning |
| CN112545652B (en) * | 2020-12-02 | 2022-07-19 | 哈尔滨工业大学 | High-precision off-line control method for flexible wire transmission surgical instrument of minimally invasive surgical robot |
| CN113925612B (en) * | 2021-12-17 | 2022-03-15 | 极限人工智能有限公司 | Instrument control method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110170994A (en) * | 2019-04-29 | 2019-08-27 | 清华大学 | A kind of tactile method of servo-controlling for manipulator crawl task |
| CN110188794A (en) * | 2019-04-23 | 2019-08-30 | 深圳大学 | A kind of training method, device, equipment and the storage medium of deep learning model |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102207997B (en) * | 2011-06-07 | 2013-10-16 | 哈尔滨工业大学 | Force-feedback-based robot micro-wound operation simulating system |
| CN106056135B (en) * | 2016-05-20 | 2019-04-12 | 北京九艺同兴科技有限公司 | A kind of compressed sensing based human action classification method |
| CN106938470B (en) * | 2017-03-22 | 2017-10-31 | 华中科技大学 | A kind of device and method of Robot Force control teaching learning by imitation |
| EP3743901A4 (en) * | 2018-01-25 | 2021-03-31 | Facebook Technologies, Inc. | Real-time processing of handstate representation model estimates |
-
2019
- 2019-12-20 CN CN201911327800.3A patent/CN110974425B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188794A (en) * | 2019-04-23 | 2019-08-30 | 深圳大学 | A kind of training method, device, equipment and the storage medium of deep learning model |
| CN110170994A (en) * | 2019-04-29 | 2019-08-27 | 清华大学 | A kind of tactile method of servo-controlling for manipulator crawl task |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110974425A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110974425B (en) | Method for training surgical instrument clamping force sensing model | |
| US11666331B2 (en) | Systems for detecting proximity of surgical end effector to cancerous tissue | |
| CN103079491B (en) | Manipulator system control device, manipulator system, and manipulator system control method | |
| Nagyné Elek et al. | Robot-assisted minimally invasive surgical skill assessment—Manual and automated platforms | |
| CN109115380B (en) | Three-dimensional force sensor for minimally invasive medical instrument | |
| CN109875850A (en) | A kind of cerebral apoplexy hand convalescence device | |
| CN104546235A (en) | Hybrid prosthetic hand | |
| CN112826458B (en) | Pulse diagnosis system and pulse diagnosis method | |
| CN108786015A (en) | A kind of wearable finger function initiative rehabilitation training system | |
| IL170338A (en) | Automated method for discriminating the cardiac beat | |
| CN104856707A (en) | Pressure sensing data glove based on machine vision and gripping process judgment method thereof | |
| CN109602415B (en) | Electrocardio equipment lead inversion identification method based on machine learning | |
| CN112308026B (en) | Surgical instrument clamping force sensing method based on deep learning | |
| CN102813507A (en) | Device and method for measuring blood pressure value of human body when human body is in stable state | |
| CN201239143Y (en) | Instrument for monitoring physiological signal of laboratory animal | |
| CN104545882A (en) | Electrocardiogram measuring apparatus and synthesized electrocardiogram generating method | |
| CN109620414B (en) | Mechanical gripper force feedback method and system for surgical operation | |
| CN203609515U (en) | Surgical robot slave manipulator clamping hand loaded with force sensing device | |
| CN112603262B (en) | Human body state identification method, system and medium | |
| CN113616239A (en) | Automatic ultrasonic detection method and system | |
| Kim et al. | Asynchronous classification of error-related potentials in human-robot interaction | |
| CN203195702U (en) | Continuous changeable stress test system | |
| Li et al. | Vascular Intervention Surgical Robot Master-Slave Force Sensing Technology | |
| CN115153849A (en) | Force feedback sensing device based on disposable instrument of laparoscopic surgery robot and laparoscopic surgery robot | |
| CN109009075A (en) | A kind of electrocardiogram monitor system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240617 Address after: 311119, 1st Floor, Building 1, and 1-4 Floors, Building 2, No. 39 Science and Technology Avenue, Yuhang Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Weijing medical robot Co.,Ltd. Country or region after: China Address before: 150001 No. 92 West straight street, Nangang District, Heilongjiang, Harbin Patentee before: HARBIN INSTITUTE OF TECHNOLOGY Country or region before: China |