Movatterモバイル変換


[0]ホーム

URL:


CN117558406A - Active training method and system based on upper limb rehabilitation - Google Patents

Active training method and system based on upper limb rehabilitation
Download PDF

Info

Publication number
CN117558406A
CN117558406ACN202311441901.XACN202311441901ACN117558406ACN 117558406 ACN117558406 ACN 117558406ACN 202311441901 ACN202311441901 ACN 202311441901ACN 117558406 ACN117558406 ACN 117558406A
Authority
CN
China
Prior art keywords
training
path
time
paths
operator
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.)
Granted
Application number
CN202311441901.XA
Other languages
Chinese (zh)
Other versions
CN117558406B (en
Inventor
何永正
孟令珂
马登伟
信焕玲
李亚飞
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.)
Xiangyu Medical Co ltd
Original Assignee
Xiangyu Medical Co ltd
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 Xiangyu Medical Co ltdfiledCriticalXiangyu Medical Co ltd
Priority to CN202311441901.XApriorityCriticalpatent/CN117558406B/en
Publication of CN117558406ApublicationCriticalpatent/CN117558406A/en
Application grantedgrantedCritical
Publication of CN117558406BpublicationCriticalpatent/CN117558406B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

The invention relates to the technical field of rehabilitation training, in particular to an active training method and system based on upper limb rehabilitation, comprising the steps of constructing a training path, wherein the training path comprises in training points, i1, i2 and i3 … … in sequence; the patient moves the first operation object according to the training path; the line segment between one training point and the next training point is a path, and the path comprises an inclined path and a non-inclined path; detecting the moving time of a first operator in each section of the training path; returning the first operator to the training point i1 in response to the first operator not moving from the training point i1 to the training point i2 within a predetermined time of the corresponding path; the invention can generate multiple sections of identical paths in the next training scheme aiming at the paths of abnormal training of the patient, so that the patient trains for multiple times aiming at the paths of abnormal training, and the rehabilitation training effect of the patient is quickened.

Description

Active training method and system based on upper limb rehabilitation
Technical Field
The invention relates to the technical field of rehabilitation training, in particular to an active training method and system based on upper limb rehabilitation.
Background
At present, the rehabilitation training for the upper limbs is to control the movement of the upper limbs by a patient, so as to achieve the capability of training the movement and balance of the upper limbs of cerebellum, promote the brain nerve structure to generate new connection and recombination, and simultaneously perform the movement rehabilitation training for the 3 joints of the shoulder, elbow and wrist of the patient, thereby improving the flexibility and coordination capability of the upper limbs of the patient.
The existing upper limb rehabilitation training method can only perform single-double-side training along a middle track, cannot perform self-learning and guide the next training according to the real-time state of the upper limb lifting capability of a patient, cannot automatically generate the next training scheme according to the current upper limb lifting training of the patient, enables the patient to adopt the same training path each time when performing rehabilitation training, cannot increase or decrease the training path according to the rehabilitation condition of the patient, and causes poor effect of the existing active training method on the rehabilitation treatment of the upper limb of the patient.
Disclosure of Invention
Aiming at the defects of the prior art in the background art, the invention aims to provide an active training method and system based on upper limb rehabilitation, so as to solve the problem that the current active training method has poor effect on upper limb rehabilitation treatment of a patient because the training path cannot be increased or decreased according to the rehabilitation condition of the patient in the background art.
In a first aspect, the present invention provides an active training method based on upper limb rehabilitation, comprising: constructing a training path, wherein the training path comprises in training points, i1, i2 and i3 … … in sequence; the patient moves the first operation object according to the training path; the line segment between one training point and the next training point is a path, and the path comprises an inclined path and a non-inclined path; detecting the moving time of a first operator in each section of the training path; returning the first operator to the training point i1 in response to the first operator not moving from the training point i1 to the training point i2 within a predetermined time of the corresponding path; training according to the training path in response to the first operation object moving from the training point position i1 to the training point position i2 in the preset time of the corresponding path; sequentially circulating to finish all training paths; counting time consumption time T1, T1= { T1, T2, t3..} of the first operator for completing each section of the non-inclined path, wherein T1 refers to time consumption time for completing a certain section of the non-inclined path; calculating the slope of each section of the inclined path; counting time T2 for the first operator to finish each inclined path; and generating a next training scheme in response to at least one of the time consumption time T1 and the time consumption time T2 being greater than a preset condition.
In one embodiment, the predetermined time is 2.3s; for the non-inclined path, the predetermined time is 2s.
In an embodiment, the preset condition includes: a first threshold corresponding to the time consumption time T1; and a second threshold corresponding to the time consumption time T2.
In one embodiment, responding to the first operator moving from training point i1 to training point i2 within a predetermined time of the corresponding path comprises: responding to the fact that the first operation object finishes moving for 2 seconds in a section of the non-inclined path, and normally finishing training; and responding to the fact that the time for the first operator to complete moving in a section of the inclined path is within 2.3s, and then training is normally completed.
In an embodiment, the generating the next training scheme includes: judging whether the time consumption time T1 of a section of the non-inclined path is greater than a first threshold value or not; in response to the time elapsed T1 to complete the non-inclined path being greater than a first threshold, presetting a plurality of training paths identical to the non-inclined path; judging the time consuming time T2 for the first operator to finish a section of the inclined path; and in response to the time consumption time T2 for completing the inclined path is greater than a second threshold value, presetting a plurality of inclined paths with the same slope as the corresponding inclined paths.
In an embodiment, the number of next identical training paths is generated according to the time-consuming time for completing the training paths, the number of preset identical training paths is proportional to the time-consuming time corresponding to the same training paths, and the calculation formula is as follows: q=tn×k, K > 0; the method comprises the steps of obtaining a final value of Q after rounding and rounding a calculated value of Q, wherein Q refers to the number of training paths which are required to be preset and correspond to the next training scheme, and Tn refers to time consuming time for completing different training paths.
In an embodiment, the first threshold is 6s.
In an embodiment, the second threshold is 7s.
In an embodiment, further comprising: and responding to the fact that the first operation object normally completes training in each path, stopping generating a next training scheme, wherein the fact that the first operation object normally completes training means that the moving time of the first operation object in each path is smaller than or equal to the corresponding preset time.
In a second aspect, the present invention provides an active training system based on rehabilitation of the upper limbs, comprising a processor and a memory, said memory storing a computer program, characterized in that said processor executes said computer program to carry out the steps of any of the methods described above.
The invention has the beneficial effects that:
according to the upper limb capability of the patient, the patient automatically learns and guides the next training, and after the training, the next training scheme is automatically generated until the patient is recovered, and the whole course guidance of a doctor is not needed.
Furthermore, multiple sections of identical paths can be generated in the next training scheme aiming at the paths of abnormal training of the patient, so that the patient trains for multiple times aiming at the paths of abnormal training, and the rehabilitation training effect of the patient is quickened.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart schematically illustrating the generation of a next training scenario in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart schematically illustrating the generation of non-inclined path training of an embodiment of the present invention;
FIG. 3 is a flow chart schematically illustrating the generation of a diagonal path training scenario in accordance with an embodiment of the present invention;
fig. 4 is a system structural diagram schematically showing an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The existing upper limb rehabilitation training method can only perform single-double-side training along a middle track, cannot perform self-learning and guide the next training according to the real-time state of the upper limb lifting capability of a patient, cannot automatically generate the next training scheme according to the current upper limb lifting training of the patient, enables the patient to adopt the same training path each time when performing rehabilitation training, cannot increase or decrease the training path according to the rehabilitation condition of the patient, and causes poor effect of the existing active training method on the rehabilitation treatment of the upper limb of the patient.
In this embodiment, the first operator and the second operator are electric telescopic handles, and electric telescopic handles can stretch out and draw back from top to bottom and change length to adapt to the patient that needs not co-altitude, and electric telescopic handles rotatable setting is on trainer, and has great resistance between electric telescopic handles and the trainer, makes patient's upper limbs can promote electric telescopic handles and carry out rehabilitation training, and it is to be noted that, electric telescopic handles can return the normal position through mechanical structure control, all belong to prior art above, do not have in the detailed description.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Fig. 1 schematically illustrates an active training method based on upper limb rehabilitation according to this embodiment, which specifically includes the following steps:
step S11: a training path is constructed.
Constructing training paths on the chessboard according to the chessboard distribution, wherein the training paths comprise i on the chessboardn Training points are i in turn1、 i2、 i3…… in The method comprises the steps of carrying out a first treatment on the surface of the It should be noted that, the line segment between one training point and the next training point is a path, and the path includes an inclined path and a non-inclined path, and the patient moves the operator according to the training path.
It should be noted that the number of the operators is two, and the operators are divided into a first operator and a second operator; the first operation object and the second operation object are arranged in bilateral symmetry. When rehabilitation training is carried out, a patient selects a corresponding operation object according to the self condition, for example, when the patient carries out single-limb training, the patient can select a first operation object to carry out training and can select a second operation object to carry out training; when the patient needs to perform the double-limb training, the first operation object and the second operation object can be selected for training at the same time. When the patient selects the first operator for training, the first operator needs to be moved according to the training path.
Step S12: and detecting the moving time of the first operator in each section of the training path.
The training path of the first operator is exemplified by the training point i1 Move to training point position i2 Then detecting the first operation object from the training point position i1 Move to training point position i2 The moving time of the path is sequentially circulated, and the moving time of the training path is detected:
step S121: and judging whether the first operator moves within a preset time to finish a corresponding path. If the first operator does not follow the training point i within the predetermined time of the corresponding path1 Move to training point position i2 Returning the first operation object to the training point position i1
Specifically, the predetermined time for the inclined path is 2.3s; the predetermined time for the non-inclined path is 2s.
For example when i is detected1 Move to training point position i2 The moving time of the path is longer than 2s, the abnormal training is realized, and the first operation object is required to return to the training point position i1 The first operator is led to be from the training point position i again1 Move to training point position i2
For example i2 Move to training point position i3 When the path belongs to an inclined path, detecting the first operation object from the training point position i2 Move to training point position i3 The moving time of the path is less than or equal to 2.3s, and the training is normally completed; when i is detected2 Move to training point position i3 The moving time of the path is longer than 2.3s, the abnormal training is realized, and the first operation object is required to return to the training point position i2 The first operator is led to be from the training point position i again2 Move to training point position i3
If the first operator is from training point i within a predetermined time of the corresponding path1 Move to training point position i2 And training according to the training paths, and sequentially cycling to finish all the training paths.
For example i1 Move to training point position i2 When the path belongs to a non-inclined path, detecting the first operation object from the training point position i1 Move to training point position i2 The moving time of the path is less than or equal to 2s, and the training is normally completed. At this time, the patient can control the first operation object from the training point position i2 Training point position i3 Moving;
step S13: counting time T for the first operator to complete each section of the non-inclined path1 ,T1 = { t1, t2, t3.. }; wherein t1 is the time elapsed for completing a certain section of the non-inclined path, as shown in the following figure;
for example i1~ i2 And i3~ i4 All belong to non-inclined paths and detect that the first operator has moved to completion i1~ i2 The total time consumption of the path is t1, and the first operation object is detected to complete moving i3~ i4 The time taken for this path is t2.
The time consuming time for both inclined and non-inclined paths refers to the total time taken to complete a certain training path, e.g. the patient manipulates the first operator from training point i1 Move to training point position i2 The first operation consumes 2.4s from training point i when moving for the first time1 Move to training point position i2 At this time, the first operator returns to training point i1 Then the patient continues to control the first operation material consumption for 2.2s from the training point position i1 Move to training point position i2 The first operator returns to the training point position i again1 Until the patient continues to control the first operation object for 2s from the training point position i1 Move to training point position i2 At this time, the training point position i is completed1 Move to training point position i2 Training the path to calculate the training point position i1 Move to training point position i2 The time taken for this path t1=2.4s+2.2s+2s=6.4 s.
Step S14: calculating the slope of each section of inclined path, and counting the time T for the first operator to complete each section of inclined path2 ,T2 = { x1, x2, x3.. }; where x1 refers to the time taken to complete a certain segment of the non-inclined path, as shown in the above figures.
For example i2~ i3 And i4~ i5 All belong to the inclined path and detect the completion of the movement of the first operator i2~ i3 The time consuming time of the path is x1, and the first operation object is detected to complete moving i4~ i5 The time taken for this path is x2.
For example, the patient manipulates the first operator from the training point i2 Move to training point position i3 The first operator takes 2 times when moving for the first time.7s from training point i2 Move to training point position i3 At this time, the first operator returns to training point i2 Then the patient continues to control the first operation material consumption for 2.5s from the training point position i2 Move to training point position i3 The first operator returns to the training point position i again2 Until the patient continues to control the first operation material consumption for 2.2s from the training point position i2 Move to training point position i3 At this time, the training point position i is completed2 Move to training point position i3 Training the path to calculate the training point position i2 Move to training point position i3 The time taken for this path t1=2.7s+2.5s+2.2s=7.4 s.
Step S15: in response to time consumption T1 And time consuming T2 When at least one of the training schemes is larger than a preset condition, generating the next training scheme.
Wherein the preset condition comprises a first threshold value and a second threshold value, the first threshold value corresponds to the time consuming time T1 And setting the first threshold to 6s; the second threshold corresponds to a time period T2 And the second threshold is set to 7s.
The next training regimen is generated as follows:
as shown in fig. 2, step S251: judging time consuming time T of the non-inclined path1 Whether greater than a first threshold.
Step S252: time T in response to completion of the non-inclined path1 And if the training path is larger than the first threshold value, presetting a plurality of training paths which are the same as the non-inclined path.
Exemplary, time T is elapsed when the non-sloped path is completed1 And when the training time is greater than 6s, presetting a plurality of training paths which are the same as the non-inclined path in the next training scheme.
As shown in fig. 3, step S351: judging the time consuming time T for the first operator to finish the inclined path2 Whether greater than a second threshold.
Step S352: time T in response to completion of the inclined path2 If the road is larger than the second threshold value, presetting a plurality of inclined roads corresponding to the inclined roadsOblique paths having the same diameter slope.
Time elapsed T when the non-inclined path is completed1 If the slope of the inclined path is larger than 7s, presetting a plurality of inclined paths with the same slope as the corresponding inclined paths in the next training scheme.
In this embodiment, the number of next identical training paths needs to be generated according to the time-consuming time for completing the training paths, and the number of identical training paths is preset to be proportional to the time-consuming time corresponding to the identical training paths, where the calculation formula is as follows:
Q=Tn *K,K>0。
wherein Q refers to the number of training paths required to be preset in the next training scheme, the calculated value of Q is rounded to obtain the final value of Q, Tn Refers to the time taken to complete the different training paths, with k defined as a constant of 0.5.
Exemplary, for non-inclined paths, training Point i is completed1 Move to training point position i2 Time consuming T of the path1 6.4s, T1 Greater than 6s, calculate q=t1 * K=6.4×0.5=3.2, and the final value of Q obtained by rounding off is 3, then 3 training paths identical to the non-inclined path need to be generated in the next scheme.
For inclined paths, training point position i is completed2 Move to training point position i3 Time consuming T of the path2 7.4s, T2 Greater than 6s, calculate q=t2 * K=7.4×0.5=3.7, and the final value of Q obtained by rounding is 4, then 4 inclined paths with the same slope as the corresponding inclined paths need to be generated in the next training scheme.
Responding to the fact that the first operation object normally completes training in each path, stopping generating a next training scheme, wherein the fact that the first operation object normally completes training means that the moving time of the first operation object in each path is smaller than or equal to corresponding preset time; that is, when the patient controls the first operation object to move and complete the movement time of each section of non-inclined slope to be less than or equal to 2s, and when the patient controls the first operation object to move and complete the movement time of each section of inclined slope to be less than or equal to 2.3s, the patient is informed that the patient controls the first operation object to normally train all training paths, and the upper limb rehabilitation training of the patient is completed, and then the next training scheme is not needed to be generated.
In the second embodiment, the patient may be allowed to operate the second manipulator to perform rehabilitation training according to the steps in the first embodiment until all training points are completed normally.
In the third embodiment, the patient may be allowed to simultaneously manipulate the steps of the first embodiment of the first and second operators to perform symmetrical movements until all training points are completed normally.
In the above embodiment, the next training is automatically generated after the present training according to the real-time status of the upper limb ability of the patient, until the patient is recovered, without the need of a doctor to conduct the whole course, and multiple identical paths can be generated in the next training scheme for the path of the patient abnormal training, so that the patient trains for multiple times for the path of the abnormal training, and the rehabilitation training effect of the patient is accelerated.
As shown in fig. 4, according to a second aspect of the present application, the present application further provides an active training system based on upper limb rehabilitation, including a display, a processor and a memory, where the processor is connected to the display and the memory, and the computer executable instructions, when executed by the processor, implement an active training method based on upper limb rehabilitation according to the first aspect of the present application. The memory stores computer program instructions that when executed by the processor implement an active training method based on upper limb rehabilitation according to the first aspect of the present application. The device also includes other components, such as a communication bus and a communication interface, which are well known to those skilled in the art, and the arrangement and function of which are known in the art and therefore not described in detail herein. The system further comprises other components known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and are therefore not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.

Claims (10)

CN202311441901.XA2023-11-012023-11-01Active training method and system based on upper limb rehabilitationActiveCN117558406B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202311441901.XACN117558406B (en)2023-11-012023-11-01Active training method and system based on upper limb rehabilitation

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202311441901.XACN117558406B (en)2023-11-012023-11-01Active training method and system based on upper limb rehabilitation

Publications (2)

Publication NumberPublication Date
CN117558406Atrue CN117558406A (en)2024-02-13
CN117558406B CN117558406B (en)2024-08-13

Family

ID=89813752

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202311441901.XAActiveCN117558406B (en)2023-11-012023-11-01Active training method and system based on upper limb rehabilitation

Country Status (1)

CountryLink
CN (1)CN117558406B (en)

Citations (17)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20110165996A1 (en)*2008-08-222011-07-07David PaulusComputer controlled exercise equipment apparatus and method of use thereof
US20140135873A1 (en)*2012-11-132014-05-15Daegu Gyeongbuk Institute Of Science & TechnologyRehabilitation training system and method
CN104317196A (en)*2014-09-292015-01-28华南理工大学Virtual reality-based upper limb rehabilitation training robot control method
US20160184634A1 (en)*2014-12-312016-06-30EZ as a Drink Productions, Inc.Exercise systems, methods, and apparatuses configured for evaluating muscular activity of users during physical exercise and/or providing feedback to users
US20160199246A1 (en)*2015-01-142016-07-14Yeung Ki KimUpper limb rehabilitation training apparatus
CN109124985A (en)*2018-08-202019-01-04中国科学院苏州生物医学工程技术研究所Personalized upper-limbs rehabilitation training robot system based on path planning
CN109847269A (en)*2019-01-102019-06-07山东中医药大学附属医院 A hemiplegia rehabilitation device
CN110465065A (en)*2019-08-162019-11-19吉林师范大学A kind of supplemental training method based on table tennis track analysis
CN111863188A (en)*2020-07-242020-10-30阚绍龙Targeted upper limb rehabilitation training system and training method thereof
CN111888729A (en)*2020-07-302020-11-06同济大学 A cognitive and upper limb comprehensive training device based on directional movement
CN111956452A (en)*2020-08-292020-11-20上海电气集团股份有限公司Control method and device for upper limb rehabilitation robot
CN113426068A (en)*2021-08-272021-09-24上海卓道医疗科技有限公司Rehabilitation training device and working method thereof
CN113974612A (en)*2021-12-022022-01-28上海大学 A method and system for automatic assessment of upper limb motor function in stroke patients
US20220105390A1 (en)*2020-10-022022-04-07Toyota Jidosha Kabushiki KaishaRehabilitation assistance system, rehabilitation assistance method, and program
CN116440453A (en)*2023-04-212023-07-18郑州大学第一附属医院Cervical vertebra auxiliary exercise equipment and method
CN116604532A (en)*2023-05-092023-08-18山东大学Intelligent control method for upper limb rehabilitation robot
CN116869777A (en)*2023-07-252023-10-13哈尔滨工业大学Upper limb full-period rehabilitation training device for cerebral apoplexy patient

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20110165996A1 (en)*2008-08-222011-07-07David PaulusComputer controlled exercise equipment apparatus and method of use thereof
US20140135873A1 (en)*2012-11-132014-05-15Daegu Gyeongbuk Institute Of Science & TechnologyRehabilitation training system and method
CN104317196A (en)*2014-09-292015-01-28华南理工大学Virtual reality-based upper limb rehabilitation training robot control method
US20160184634A1 (en)*2014-12-312016-06-30EZ as a Drink Productions, Inc.Exercise systems, methods, and apparatuses configured for evaluating muscular activity of users during physical exercise and/or providing feedback to users
US20160199246A1 (en)*2015-01-142016-07-14Yeung Ki KimUpper limb rehabilitation training apparatus
CN109124985A (en)*2018-08-202019-01-04中国科学院苏州生物医学工程技术研究所Personalized upper-limbs rehabilitation training robot system based on path planning
CN109847269A (en)*2019-01-102019-06-07山东中医药大学附属医院 A hemiplegia rehabilitation device
CN110465065A (en)*2019-08-162019-11-19吉林师范大学A kind of supplemental training method based on table tennis track analysis
CN111863188A (en)*2020-07-242020-10-30阚绍龙Targeted upper limb rehabilitation training system and training method thereof
CN111888729A (en)*2020-07-302020-11-06同济大学 A cognitive and upper limb comprehensive training device based on directional movement
CN111956452A (en)*2020-08-292020-11-20上海电气集团股份有限公司Control method and device for upper limb rehabilitation robot
US20220105390A1 (en)*2020-10-022022-04-07Toyota Jidosha Kabushiki KaishaRehabilitation assistance system, rehabilitation assistance method, and program
CN113426068A (en)*2021-08-272021-09-24上海卓道医疗科技有限公司Rehabilitation training device and working method thereof
CN113974612A (en)*2021-12-022022-01-28上海大学 A method and system for automatic assessment of upper limb motor function in stroke patients
CN116440453A (en)*2023-04-212023-07-18郑州大学第一附属医院Cervical vertebra auxiliary exercise equipment and method
CN116604532A (en)*2023-05-092023-08-18山东大学Intelligent control method for upper limb rehabilitation robot
CN116869777A (en)*2023-07-252023-10-13哈尔滨工业大学Upper limb full-period rehabilitation training device for cerebral apoplexy patient

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
KENDRA A. NORBAKA ET AL: "DynoBrace: Stability Control of Ankle Joint Using a Mobile App Controlled Smart Brace Device", IEEE, 31 December 2018 (2018-12-31), pages 1 - 4*
尹相国 等: "基于多模感知的上肢康复训练轨迹跟踪研究", 《仪器仪表学报》, vol. 44, no. 2, 28 February 2023 (2023-02-28), pages 154 - 163*

Also Published As

Publication numberPublication date
CN117558406B (en)2024-08-13

Similar Documents

PublicationPublication DateTitle
CN114460943B (en)Self-adaptive target navigation method and system for service robot
Lin et al.Explore, exploit or listen: Combining human feedback and policy model to speed up deep reinforcement learning in 3d worlds
Frazier et al.Improving deep reinforcement learning in minecraft with action advice
CN109550254A (en)A kind of method and device of game adjustment, electronic equipment, storage medium
CN117558406B (en)Active training method and system based on upper limb rehabilitation
CN112330488A (en)Power grid frequency situation prediction method based on transfer learning
Tang et al.Classroom evaluation of a gamified adaptive tutoring system
Kaliappan et al.Flexible power consumption management using Q learning techniques in a smart home
Cai et al.An algorithm of micromouse maze solving
Whitehead et al.A role for anticipation in reactive systems that learn
CN116673968B (en)Mechanical arm track planning element selection method and system based on reinforcement learning
Altaf et al.Extended case-based behavior control for multi-humanoid robots
Say et al.A model for cognitively valid lifelong learning
CN113238757B (en)Method and device for identifying programming instruction
Rakhman et al.Fully automatic data collection for neuro-symbolic task planning for mobile robot navigation
Mo et al.MoChat: Joints-Grouped Spatio-Temporal Grounding LLM for Multi-Turn Motion Comprehension and Description
Dai et al.Application of advanced Petri net in personalized learning
SauseCoordinated reinforcement learning agents in a multi-agent virtual environment
CN115202339B (en) DQN-based Adaptive Planning Method for Multiple Rover Sampling Fixed Targets
Arul et al.Solving combined economic emission dispatch problems using self-adaptive differential harmony search algorithm
Guan et al.A new subsampling deep Q network method
Ierache et al.Learning life cycle in autonomous intelligent systems
CN115933694A (en) A Formation Control Method of Multiple Robots Under Mine
Khademian et al.Experimental performance evaluation of a haptic training simulation system
Iwanaga et al.FUT-K team description paper 2017

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp