CN113689498B - Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system - Google Patents
Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system Download PDFInfo
- Publication number
- CN113689498B CN113689498B CN202110939672.9A CN202110939672A CN113689498B CN 113689498 B CN113689498 B CN 113689498B CN 202110939672 A CN202110939672 A CN 202110939672A CN 113689498 B CN113689498 B CN 113689498B
- Authority
- CN
- China
- Prior art keywords
- historical
- human body
- acquiring
- seat
- inclination angle
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10821—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum further details of bar or optical code scanning devices
- G06K7/10861—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum further details of bar or optical code scanning devices sensing of data fields affixed to objects or articles, e.g. coded labels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to an auxiliary control method and system of an electric stair climbing vehicle based on artificial intelligence. The method comprises the steps of obtaining identity information of a patient to obtain a diseased part of the patient, and obtaining posture information of the patient on a seat by a sensor on an electric stair climbing vehicle; obtaining a first range of a track inclination angle and a track speed according to the step height and the step width of the stair, and obtaining a second range of a seat inclination angle according to the track angle and the height of an operator; fitting a polynomial function of the comfort level of the human body part, the track speed and the seat inclination angle according to historical data, and constructing an objective function by combining the polynomial function and the attention of the human body part; and in the first range and the second range, acquiring the track speed and the seat inclination angle respectively corresponding to the minimum objective function. Self-adaptive control caterpillar band speed and seat inclination to realize the automatic adjustment of seat, and under the prerequisite of guaranteeing operating personnel's security and comfort level, improved patient's comfort level and security.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an auxiliary control method and system of an electric stair climbing vehicle based on artificial intelligence.
Background
In the scenes of hospitals, emergency centers, emergency rescues and the like, the condition of transferring patients up and down stairs often occurs, and the electric stair climbing vehicle can solve the requirement. The existing electric stair climbing vehicle can be divided into two categories: planet wheel type and crawler type, and the patient can go upstairs and downstairs only by one person. But the operation process of the electric stair climbing vehicle is not automatically controlled in the prior art, and the operation process is controlled only by operating the stair climbing vehicle, so that the comfort of a patient cannot be guaranteed, and the user experience is low.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an auxiliary control method and system of an electric stair climbing vehicle based on artificial intelligence, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides an auxiliary control method for an electric stair climbing vehicle based on artificial intelligence, the method includes the following specific steps:
acquiring identity information of a patient by using an RFID device to obtain a diseased part of the patient; acquiring the posture information of the patient on a seat by a plurality of sensors on the electric stair climbing vehicle;
collecting an RGB image and a corresponding depth image of a staircase under an orthographic view, acquiring the step height and the step width of the staircase by combining the RGB image and the depth image, and obtaining a first range of a track inclination angle and a track speed according to the step height and the step width; acquiring a second range of the inclination angle of the seat by utilizing the inclination angle of the crawler and the height of an operator; the operator refers to a person who operates the electric stair climbing vehicle to help the patient;
classifying a plurality of groups of historical data according to historical attitude information, wherein the historical data comprises the historical attitude information, historical track speed, historical seat inclination angle and fluctuation vectors obtained by historical readings of a plurality of sensors under the historical attitude information; based on each classified type of historical data, acquiring a polynomial function which is fitted by the comfort level of a human body part, the historical crawler speed and the historical seat inclination angle under the corresponding historical posture information, wherein the human body part comprises the diseased part and the normal part; acquiring the attention of the human body part, wherein the attention refers to the attention of the human body part, the attention of the diseased part is greater than that of the normal part, and a target function is constructed based on the polynomial function and the attention; and in the first range and the second range, acquiring the crawler speed and the seat inclination angle which respectively correspond to the minimum objective function in the attitude information.
Preferably, the method for acquiring the posture information of the patient on the seat by a plurality of sensors on the electric stair climbing vehicle comprises the following steps:
and acquiring readings of the plurality of sensors, forming a pressure distribution vector by the readings, and confirming the attitude information according to the pressure distribution vector.
Preferably, after obtaining the pressure distribution vector, the pressure distribution vector is optimized by using a decentralized operation, and the optimization method includes:
and obtaining the mean value of the nonzero readings in the pressure distribution vector, subtracting the mean value from each nonzero reading to obtain a new reading, and forming a new pressure distribution vector by the new reading and the zero reading.
Preferably, the method for acquiring the step height and the step width of the staircase by combining the RGB image and the depth image comprises the following steps:
sending the RGB image into a semantic segmentation network to obtain a mask image of a human body, and obtaining a first depth map of the stair according to the mask image and the depth image;
and performing linear detection on the first depth map, acquiring the step height according to the distance between two parallel edge lines, and acquiring the step width according to the depth information of the edge lines.
Preferably, the method for obtaining the second range of the seat inclination angle by using the track inclination angle and the height of the operator comprises the following steps:
acquiring the optimal height range of the operator when the operator operates the electric stair climbing vehicle according to the height of the operator;
and combining the optimal height range, the height information of the seat and the track inclination angle to obtain the second range of the seat inclination angle.
Preferably, the method of generating a fluctuation vector from historical readings of a plurality of said sensors comprises:
acquiring the variance of the time sequence data according to the time sequence data formed by the historical readings of each sensor at different moments;
and forming the fluctuation vector by the variances corresponding to the plurality of sensors.
Preferably, the method for obtaining the comfort level of the human body part includes:
based on the fluctuation vector in each type of historical data, acquiring the corresponding variance of each human body part in the fluctuation vector according to the sensor corresponding to each human body part;
calculating an average of the variances, the average being the comfort level of each of the human body parts.
Preferably, the calculation formula of the objective function includes:
wherein R is the objective function; n is the number of the human body parts; gnThe attention degree of the nth human body part is obtained; v is the historical track speed; θ is the historical seat tilt angle;
is shown at the k-th*And the polynomial function of the nth human body part under the posture information.
Preferably, the method for acquiring the attention includes:
setting the sum of attention degrees of the diseased part and the normal part to be 1, and distributing the attention degrees to the diseased part and the normal part according to the total number of the human body parts and the number of the diseased part; the degree of attention of the diseased site is greater than the degree of attention of the normal site.
Further, an electric stair climbing vehicle auxiliary control system based on artificial intelligence comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements any one of the steps of the method when executing the computer program.
The embodiment of the invention at least has the following beneficial effects: by the posture information of patient, sick position, stair characteristic and operating personnel's height information adaptive control track speed and seat inclination to realize the automatic adjustment of seat, and under the prerequisite of guaranteeing operating personnel's security and comfort level, also improved patient's comfort level and security.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic view of an electric stair climbing vehicle according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of an electric stair climbing vehicle auxiliary control method based on artificial intelligence according to an embodiment of the present invention;
fig. 3 is a schematic view of a staircase according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined object, the following detailed description, the structure, the features and the functions of an auxiliary control method and system for an electric stair climbing vehicle based on artificial intelligence according to the present invention are provided with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of an electric stair climbing vehicle auxiliary control method and system based on artificial intelligence in detail with reference to the accompanying drawings.
The embodiment of the invention aims at the following specific scenes: in the scenes of hospitals, rehabilitation centers and the like, an operator finishes the operation of going upstairs and downstairs of a patient by means of electric stair climbing, wherein an electric stair climbing vehicle is shown in figure 1.
Referring to fig. 2, a flowchart illustrating steps of an artificial intelligence-based electric stair climbing vehicle auxiliary control method according to an embodiment of the present invention is shown, where the method includes the following steps:
s001, acquiring identity information of a patient by using RFID equipment to obtain a diseased part of the patient; a plurality of sensors on the electric stair climbing vehicle acquire the posture information of a patient on a seat.
Specifically, the patient that need go upstairs and downstairs with the help of electronic stair climbing car generally is too old or sick the action inconvenience that arouses, because the different gestures of patient on electronic stair climbing car's seat directly influence health barycentric position, and then influence the comfortable degree of each human body part of health, consequently provides reference information for follow-up patient's comfort level analysis through the gesture information that acquires the patient on the seat.
Dispose RFID equipment on the handle of electronic stair climbing car, the intelligent bracelet can be worn on its hand to the convenience of patient's treatment and management in the hospital, and each patient can correspond an exclusive bracelet. The identity information of the bracelet wearer can be obtained through the RFID equipment, and the affected parts of the patient, such as the left and right legs, the left and right shoulders and other human body parts, can be obtained through the identity information.
Meanwhile, the pressure is uniformly deployed in the equal intervals of the seat, the backrest and the handrail of the electric stair climbing vehicleThe sensor is used for obtaining the readings of each pressure sensor in the space, numbering each pressure sensor according to the position of each pressure sensor, forming the readings of each pressure sensor into a pressure distribution vector y according to the size of the number, and recording the reading of the ith pressure sensor as yi。
In order to eliminate the influence of the patient's own weight on the readings of the pressure sensor and ensure the accuracy of the subsequent data analysis, after obtaining the pressure distribution vector, the pressure distribution vector is optimized by using the decentralized operation, and the optimization method comprises the following steps: obtaining the mean value of the nonzero readings in the pressure distribution vector, subtracting the mean value from each nonzero reading to obtain a new reading, and forming a new pressure distribution vector by the new reading and the zero reading, namely:
wherein, YiA new reading for the ith pressure sensor after decentralization; n is the number of non-zero readings; y isjIs a non-zero indication of the jth pressure sensor.
Along with different postures of patients, the readings of each pressure sensor in the pressure distribution vector also change correspondingly, for example, when the posture of the patient is sitting, the reading of the pressure sensor at the backrest is 0, and the reading of the pressure sensor at the seat is relatively large; when the posture of the patient is that of the backrest chair, the reading of the pressure sensor at the backrest is larger than that of the pressure sensors at other positions, so that the posture information of the patient is confirmed according to the pressure distribution vector.
S002, collecting RGB images and corresponding depth images of the stairs in the front view, obtaining the step height and the step width of the stairs by combining the RGB images and the depth images, and obtaining a first range of a track inclination angle and a track speed according to the step height and the step width; acquiring a second range of the inclination angle of the seat by utilizing the inclination angle of the crawler and the height of an operator; the operator refers to a person who operates the electric stair climbing vehicle to help a patient.
Specifically, an RGB-D camera is arranged on the outer side of a backrest of the electric stair climbing vehicle, and an RGB image and a corresponding depth image of a stair to be climbed are acquired by the camera.
It should be noted that, the electric stair climbing vehicle runs on a horizontal ground when climbing, the camera pose is fixed, and the RGB image and the corresponding depth image are collected at the front view angle.
Considering that the height of the operator directly affects the most comfortable working height of the operator: when the inclination angle of the seat is too large, the arm of an operator is lifted too high in the stair climbing process, so that the force is not convenient to apply and the comfort level of the operator is reduced; when the inclination of the seat is too small, an operator needs to bend over to operate the electric stair climbing vehicle, and the comfort of the operator is also reduced. In order to ensure the comfort of the operator during operation, the operator needs to manually input own height information H for determining the subsequent seat inclination angle value range.
Further, analyzing the collected RGB image, sending the RGB image into a semantic segmentation network to obtain a mask image of a human body, wherein the pixel value of a pixel point of the human body in the mask image is 1, and other pixel points are 0, and an implementer can realize semantic segmentation by adopting the existing Unet network; and acquiring a first depth map of the staircase from the mask image and the depth image, namely performing negation operation on the mask image, namely setting a pixel value of 1 as 0 and setting a pixel value of 0 as 1, and multiplying the mask image subjected to the negation operation and the depth image to obtain the first depth map of the staircase, so that the depth information of personnel in the depth image is shielded, and only the depth information of the staircase area is concerned.
And performing linear detection on the first depth map, and acquiring the step height according to the distance between two parallel edge lines and the step width according to the depth information of the edge lines.
As an example, obtaining all linear equations in the first depth map by using a hough linear detection algorithm, and recording the slope of a straight line as k; setting the slope k of the edge line of the staircase00.2, satisfies k<k0The straight line of (2) is the edge line of the staircase. Because the edge lines of the stairs are distributed equidistantly and parallelly, two adjacent and parallel edge lines are obtained, and the distance D between the two edge lines is calculated, wherein the distance D isThe step height of the stairs; the average depth of all the pixel points of the two edge lines is counted, and the difference W of the average depths of the two edge lines is calculated, wherein the difference W is the step width of the staircase, such as the staircase schematic diagram shown in fig. 3. The step width is obtained from the depth information of the edge line.
Further, according to the step height D, the step width W and the height information H of the operator, determining a first range of the track speed and a second range of the seat inclination angle when the electric stair climbing vehicle operates, the determining method is as follows:
(1) because electronic stairs-mover is when the climbing, the track inclination is confirmed by the stair of required climbing, consequently utilizes step height D and step width W to obtain the track inclination, and then the computational formula at track inclination alpha is:
(2) obtaining the optimal height range when the operator operates the most comfortable according to the height information H of the operator1H,γ2H]Wherein γ is1,γ2Respectively, the minimum height adjustment coefficient and the maximum height adjustment coefficient are respectively valued as
The two adjusting coefficients are artificially set empirical values; according to the optimal height range and the height information H of the seat0The value range of the seat inclination angle can be obtained, but the height of an operator is higher than the height of the seat when climbing stairs, and a specific higher value is related to the track inclination angle alpha, so that the second range of the seat inclination angle is obtained by combining the optimal height range, the height information of the seat and the track inclination angle, namely:
wherein, thetaminIs the minimum value of the seat inclination angle; thetamaxIs the maximum value of the seat inclination angle; gamma ray3Is the height correction coefficient of an operator during climbing, the coefficient is related to the design of the electric stair climbing vehicle, and the height correction coefficient gamma of the electric stair climbing vehicle with the same style3The same is true.
(3) The step height of the stairs influences the speed of the operator going upstairs, and in order to ensure the safety of the operator, the embodiment of the invention determines the maximum speed v of the crawler according to the step height D of the stairsmax＝4D, wherein γ1The adjustment coefficient gamma in the embodiment of the invention is set for the human being through experience4The first range for obtaining the track speed is 0.8, so [0, v [ ]max]。
It should be noted that the determination of the track speed and the range of the inclination angle of the seat by the characteristics of the operator and the stairs ensures the operation safety and comfort of the operator while the electric stair climbing vehicle runs normally.
Step S003, classifying a plurality of groups of historical data according to the historical attitude information, wherein the historical data comprises historical attitude information, historical track speed, historical seat inclination angle and fluctuation vectors obtained by historical readings of a plurality of sensors under the historical attitude information; based on each type of classified historical data, acquiring a polynomial function which is fitted by the comfort level of the human body part, the historical track speed and the historical seat inclination angle under the corresponding historical posture information, wherein the human body part comprises a diseased part and a normal part; acquiring attention of a human body part, and constructing a target function based on a polynomial function and the attention; and in the first range and the second range, acquiring the track speed and the seat inclination angle respectively corresponding to the minimum target function under the attitude information.
Specifically, historical data are collected, historical track speed v, historical seat inclination angle theta and historical posture information Y of a patient when the electric stair climbing vehicle climbs are obtained, and historical readings of the pressure sensors at different moments in the climbing process are obtained. Forming time sequence data of each pressure sensor according to the historical readings of each pressure sensor at different moments, and acquiring the variance sigma of the historical readings in the time sequence data, wherein the variance reflects the fluctuation of the readings of each pressure sensor, and the larger the fluctuation is, the more serious the bump is, and the lower the comfort level of a patient at the current position of the pressure sensor is; and acquiring the variance corresponding to each pressure sensor according to the same method, forming a fluctuation vector A by the variances corresponding to the plurality of pressure sensors, and forming a group of historical data { Y, A, v, theta } by the historical attitude information and the historical track speed, the historical seat inclination angle and the fluctuation vector under the historical attitude information.
Clustering multiple groups of historical data according to historical posture information of a patient, classifying the historical data with the same historical posture information into the same cluster, then enabling one cluster to represent one type of historical data, and further acquiring a polynomial function which is fitted by the comfort degree of a human body part, the historical crawler speed and the historical seat inclination angle under the corresponding historical posture information based on each type of historical data, wherein the posture information k is taken as an example in the embodiment of the invention, the acquisition method of the polynomial function is as follows:
(1) the number of the pressure sensors deployed on the electric stair climbing vehicle can reflect position information, the number of the sensors where different human body parts of patients with the same posture are located should be the same, that is, the number of the pressure sensors covered by any region where the human body parts are located should be the same for the patients with the same posture, for example, the number of the pressure sensors covered by the regions where the arms of the patients with the same posture are located is the same, and the number of the covered pressure sensors may be one or more. And acquiring the number information of the pressure sensor corresponding to each human body part.
It should be noted that the human body parts include a diseased part and a normal part, and the total number of the human body parts is N, and the specific number N is set by a professional in the medical industry.
(2) Determining the comfort levels of different human body parts according to the serial number information and the fluctuation vector A, and detailing the calculation method of the comfort level c of the left arm by taking the left arm area as an example: obtaining the variance σ of the corresponding position in the fluctuation vector A according to the number information corresponding to the left-hand arm area, wherein the calculation formula of the comfort level c of the left-hand arm is as follows:
wherein σuVariance of the pressure sensor with number u; m is the number of pressure sensors covered by the left arm area.
(3) Comfort level of each human body part can be obtained by utilizing the steps (1) and (2), and then a plurality of groups of sample data (v, theta → c) are formed according to the historical track speed v and the historical seat inclination angle theta under the historical attitude information kn) Performing polynomial fitting on multiple groups of sample data to obtain polynomial function
Further, N polynomial functions corresponding to N human body parts can be obtained.
It should be noted that the highest power of the polynomial function in the embodiment of the present invention is 3.
(4) And (4) obtaining polynomial functions of different human body parts under different posture information by utilizing the steps (1) to (3), and storing the polynomial functions in a database.
Distributing attention to N human body parts of a body according to the total number of the human body parts of a patient and the number of the diseased parts, assuming that the diseased parts of the patient are e, and e is less than or equal to N, and in order to enable the diseased parts to have higher attention, the attention of the diseased parts is set as
The normal part has a focus of
And ensuring that the sum of attention degrees of the diseased part and the normal part is 1. Constructing an objective function from the attention of the human body part and the corresponding polynomial function, wherein the objective function can represent the comfort of the patient, and the objective function R is as follows:
wherein, gnAttention of the nth person body part;
is shown at the k*The polynomial function of the nth person's body part under the seed pose information.
The track speed and the seat inclination angle corresponding to the polynomial function when the objective function R is minimum are acquired based on the posture information of the patient and the affected part confirmed in step S001 within the first range of the track speed and the second range of the seat inclination angle.
It should be noted that the optimal solution, that is, the optimal crawler speed and the optimal seat inclination, when the objective function is the minimum can be obtained by using the hill climbing algorithm, the simulated annealing algorithm, the genetic algorithm and other optimal algorithms. The optimal track speed and the optimal seat inclination angle also improve the comfort and safety of patients on the premise of ensuring the safety and comfort of operators.
In summary, the embodiment of the present invention provides an auxiliary control method for an electric stair climbing vehicle based on artificial intelligence, in which identity information of a patient is obtained to obtain a diseased part of the patient, and a sensor on the electric stair climbing vehicle obtains posture information of the patient on a seat; obtaining a first range of a track inclination angle and a track speed according to the step height and the step width of the stair, and obtaining a second range of a seat inclination angle according to the track angle and the height of an operator; fitting a polynomial function of the comfort level of the human body part, the track speed and the seat inclination angle according to historical data, and constructing an objective function by combining the polynomial function and the attention of the human body part; and acquiring the track speed and the seat inclination angle respectively corresponding to the minimum target function of the attitude information in the first range and the second range. Self-adaptive control caterpillar band speed and seat inclination to realize the automatic adjustment of seat, and under the prerequisite of guaranteeing operating personnel's security and comfort level, also improved patient's comfort level and security.
Further, an embodiment of the present invention provides an artificial intelligence-based electric stair climbing vehicle auxiliary control system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the artificial intelligence-based electric stair climbing vehicle auxiliary control method when executing the computer program.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. An electric stair climbing vehicle auxiliary control method based on artificial intelligence is characterized by comprising the following steps:
acquiring identity information of a patient by using an RFID device to obtain a diseased part of the patient; acquiring the posture information of the patient on a seat by a plurality of sensors on the electric stair climbing vehicle;
collecting an RGB image and a corresponding depth image of a stair at an orthographic view angle, acquiring the step height and the step width of the stair by combining the RGB image and the depth image, and obtaining a track inclination angle and a first range of track speed according to the step height and the step width; acquiring a second range of the inclination angle of the seat by utilizing the inclination angle of the crawler and the height of an operator; the operator refers to a person who operates the electric stair climbing vehicle to help the patient;
classifying a plurality of groups of historical data according to historical attitude information, wherein the historical data comprises the historical attitude information, historical track speed, historical seat inclination angle and fluctuation vectors obtained by historical readings of a plurality of sensors under the historical attitude information; based on each classified type of historical data, acquiring a polynomial function fitted by the comfort level of human body parts, the historical crawler speed and the historical seat inclination angle under the corresponding historical posture information, wherein the human body parts comprise the diseased part and the normal part; acquiring the attention of the human body part, wherein the attention refers to the attention of the human body part, the attention of the diseased part is larger than that of the normal part, and an objective function is constructed on the basis of the polynomial function and the attention; in the first range and the second range, acquiring the track speed and the seat inclination angle respectively corresponding to the minimum objective function of the attitude information;
the calculation formula of the objective function comprises:
wherein R is the objective function; n is the number of the human body parts; gnThe attention degree of the nth human body part is obtained; v is the historical track speed; θ is the historical seat tilt angle;
is shown at the k-th*And the polynomial function of the nth human body part under the posture information.
2. The method of claim 1, wherein the method of obtaining the posture information of the patient on a chair from a plurality of sensors on the stair cart comprises:
and acquiring readings of the plurality of sensors, forming a pressure distribution vector by the readings, and confirming the attitude information according to the pressure distribution vector.
3. The method of claim 2, wherein after obtaining the pressure distribution vector, optimizing the pressure distribution vector using a de-centering operation comprises:
and obtaining the mean value of the nonzero readings in the pressure distribution vector, subtracting the mean value from each nonzero reading to obtain a new reading, and forming a new pressure distribution vector by the new reading and the zero reading.
4. The method of claim 1, wherein the method of obtaining the step height and step width of the staircase in combination with the RGB image and the depth image comprises:
sending the RGB image into a semantic segmentation network to obtain a mask image of a human body, and obtaining a first depth map of the stair according to the mask image and the depth image;
and performing linear detection on the first depth map, acquiring the step height according to the distance between two parallel edge lines, and acquiring the step width according to the depth information of the edge lines.
5. The method of claim 1, wherein the method of using the track inclination and the height of the operator to obtain the second range of seat inclinations comprises:
acquiring the optimal height range of the operator when the operator operates the electric stair climbing vehicle according to the height of the operator;
and combining the optimal height range, the height information of the seat and the track inclination angle to obtain the second range of the seat inclination angle.
6. The method of claim 1, wherein said method of obtaining a fluctuation vector from historical readings of a plurality of said sensors comprises:
acquiring the variance of the time sequence data according to the time sequence data formed by the historical readings of each sensor at different moments;
and the variance corresponding to a plurality of the sensors forms the fluctuation vector.
7. The method of claim 6, wherein the obtaining of the comfort level of the human body part comprises:
based on the fluctuation vector in each type of the historical data, acquiring the corresponding variance in the fluctuation vector according to the sensor corresponding to each human body part;
calculating an average of the variances, the average being the comfort level of each of the human body parts.
8. The method of claim 1, wherein the method of obtaining the attention comprises:
setting the sum of attention degrees of the diseased part and the normal part to be 1, and distributing the attention degrees to the diseased part and the normal part according to the total number of the human body parts and the number of the diseased part; the degree of attention of the diseased site is greater than the degree of attention of the normal site.
9. An artificial intelligence-based electric stair climbing vehicle auxiliary control system, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110939672.9A CN113689498B (en) | 2021-08-16 | 2021-08-16 | Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110939672.9A CN113689498B (en) | 2021-08-16 | 2021-08-16 | Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113689498A CN113689498A (en) | 2021-11-23 |
| CN113689498B true CN113689498B (en) | 2022-06-07 |
Family
ID=78580135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110939672.9A Active CN113689498B (en) | 2021-08-16 | 2021-08-16 | Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689498B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842035A (en) * | 2022-04-24 | 2022-08-02 | 平安国际融资租赁有限公司 | License plate desensitization method, device and equipment based on deep learning and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101486360A (en) * | 2009-01-05 | 2009-07-22 | 东南大学 | Stairs climbing control method for crawler moving robot with guide arm |
| KR20120067474A (en) * | 2010-12-16 | 2012-06-26 | 주식회사 만도 | Automatic stability control system for electric seat and method thereof |
| CN104814842A (en) * | 2015-04-21 | 2015-08-05 | 东华大学 | Intelligent horizontal-attitude stair-climbing wheelchair and rotary stair-climbing method |
| CN106038106A (en) * | 2016-06-24 | 2016-10-26 | 张学海 | Laser ranging based stair climbing wheelchair control system and method |
| CN107088128A (en) * | 2017-05-03 | 2017-08-25 | 河北工业大学 | It is a kind of to move the behavior safety control method for multiplying nursing robot |
| CN107361934A (en) * | 2017-07-24 | 2017-11-21 | 北京动力京工科技有限公司 | A kind of novel six freedom automatic stari creeping ladder wheelchair |
| CN107671872A (en) * | 2017-11-03 | 2018-02-09 | 长安大学 | A kind of attitude-adaptive is helped the elderly disabled aiding robot |
| CN109172177A (en) * | 2018-09-04 | 2019-01-11 | 东莞理工学院 | A kind of wheel-track combined climbing stairs wheelchair of steady comfort type |
| CN110496002A (en) * | 2019-10-12 | 2019-11-26 | 常州兰迪科技有限公司 | A kind of intelligent wheel chair of image-recognizing method control |
| CN111127497A (en) * | 2019-12-11 | 2020-05-08 | 深圳市优必选科技股份有限公司 | Robot and stair climbing control method and device thereof |
| CN112529903A (en) * | 2021-02-03 | 2021-03-19 | 德鲁动力科技(成都)有限公司 | Stair height and width visual detection method and device and robot dog |
| CN112537713A (en) * | 2020-12-04 | 2021-03-23 | 程学智 | Intelligent movement staircase control system based on stairs |
| CN112568899A (en) * | 2019-09-30 | 2021-03-30 | 深圳市荣盛智能装备有限公司 | Personnel posture judgment method and system |
| CN112741739A (en) * | 2019-10-31 | 2021-05-04 | 张效琪 | Electric stair-climbing wheelchair with main wheel driven by elastic bearing and provided with crawler-type front guide wheel and rear auxiliary wheel |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9377784B2 (en) * | 2014-07-25 | 2016-06-28 | The Boeing Company | Adaptable automatic nacelle conversion for tilt rotor aircraft |
| CN104331884B (en) * | 2014-10-29 | 2017-03-29 | 上海大学 | The stair climbing parameter acquiring system of four feeler caterpillar robots |
| CN111881886A (en) * | 2020-08-21 | 2020-11-03 | 董秀园 | Intelligent seat control method and device based on posture recognition |
-
2021
- 2021-08-16 CN CN202110939672.9A patent/CN113689498B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101486360A (en) * | 2009-01-05 | 2009-07-22 | 东南大学 | Stairs climbing control method for crawler moving robot with guide arm |
| KR20120067474A (en) * | 2010-12-16 | 2012-06-26 | 주식회사 만도 | Automatic stability control system for electric seat and method thereof |
| CN104814842A (en) * | 2015-04-21 | 2015-08-05 | 东华大学 | Intelligent horizontal-attitude stair-climbing wheelchair and rotary stair-climbing method |
| CN106038106A (en) * | 2016-06-24 | 2016-10-26 | 张学海 | Laser ranging based stair climbing wheelchair control system and method |
| CN107088128A (en) * | 2017-05-03 | 2017-08-25 | 河北工业大学 | It is a kind of to move the behavior safety control method for multiplying nursing robot |
| CN107361934A (en) * | 2017-07-24 | 2017-11-21 | 北京动力京工科技有限公司 | A kind of novel six freedom automatic stari creeping ladder wheelchair |
| CN107671872A (en) * | 2017-11-03 | 2018-02-09 | 长安大学 | A kind of attitude-adaptive is helped the elderly disabled aiding robot |
| CN109172177A (en) * | 2018-09-04 | 2019-01-11 | 东莞理工学院 | A kind of wheel-track combined climbing stairs wheelchair of steady comfort type |
| CN112568899A (en) * | 2019-09-30 | 2021-03-30 | 深圳市荣盛智能装备有限公司 | Personnel posture judgment method and system |
| CN110496002A (en) * | 2019-10-12 | 2019-11-26 | 常州兰迪科技有限公司 | A kind of intelligent wheel chair of image-recognizing method control |
| CN112741739A (en) * | 2019-10-31 | 2021-05-04 | 张效琪 | Electric stair-climbing wheelchair with main wheel driven by elastic bearing and provided with crawler-type front guide wheel and rear auxiliary wheel |
| CN111127497A (en) * | 2019-12-11 | 2020-05-08 | 深圳市优必选科技股份有限公司 | Robot and stair climbing control method and device thereof |
| CN112537713A (en) * | 2020-12-04 | 2021-03-23 | 程学智 | Intelligent movement staircase control system based on stairs |
| CN112529903A (en) * | 2021-02-03 | 2021-03-19 | 德鲁动力科技(成都)有限公司 | Stair height and width visual detection method and device and robot dog |
Non-Patent Citations (5)
| Title |
|---|
| Path planning for clothes climbing robots on deformable clothes surface;Yuanyuan Liu等;《2012 IEEE/RSJ International Conference on Intelligent Robots and Systems》;20121224;882-887 * |
| Wheelchair.q, a motorized wheelchair with stair climbing ability;Giuseppe Quaglia等;《Mechanism and Machine Theory》;20110806;1601-1609 * |
| 爬楼轮椅的可用性因素框架研究;刘香香;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20120715;第2012年卷(第7期);C030-103 * |
| 负重爬楼助力装置的研究与开发;刘腾云;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20210815;第2021年卷(第8期);C028-18 * |
| 轮腿式爬楼轮椅座椅机构的适应性设计;甘晓萌;《万方》;20210205;1-89 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113689498A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8621684B2 (en) | Transfer assist apparatus | |
| CN113689498B (en) | Artificial intelligence-based electric stair climbing vehicle auxiliary control method and system | |
| CN110666791A (en) | RGBD robot nursing system and method based on deep learning | |
| Hossain et al. | Deepbbwae-net: A cnn-rnn based deep superlearner for estimating lower extremity sagittal plane joint kinematics using shoe-mounted imu sensors in daily living | |
| JP2010069282A (en) | Method and system for detecting posture of fitting contour model and method for posture adaptation | |
| KR20120114629A (en) | Falldown detecting method using the image processing, image processing apparatus for the same | |
| CN117084701A (en) | System and method for controlling light field of medical imaging device | |
| Li et al. | A between-subject fNIRS-BCI study on detecting self-regulated intention during walking | |
| CN111609908A (en) | Patient weight estimation from surface data using a patient model | |
| CN113591635A (en) | Intelligent office desk and chair, control method and storage medium | |
| CN114943924A (en) | Pain assessment method, system, device and medium based on facial expression video | |
| CN117671739B (en) | User identity recognition method and device | |
| CN117316453A (en) | Pressure sore early warning system and method by mixing Barden scale with artificial intelligence | |
| Liu et al. | A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment | |
| CN116196196A (en) | Massage armchair control method, system and computer readable storage medium | |
| US12064390B2 (en) | Powered walking assistant and associated systems and methods | |
| JP7314939B2 (en) | Image recognition program, image recognition device, learning program, and learning device | |
| CN112382390A (en) | Method, system and storage medium for generating health assessment report | |
| TWI657800B (en) | Method and system for analyzing gait | |
| Shin et al. | Automatic speed control for SmartWalker | |
| CN113044045B (en) | Self-adaptive adjustment method for seats in intelligent cabin | |
| CN112466089B (en) | System and method for monitoring positional stability | |
| CN204496497U (en) | For the robot system of ward data acquisition | |
| CN112329640A (en) | Facial nerve palsy disease rehabilitation detection system based on eye muscle movement analysis | |
| CN113011333A (en) | System and method for obtaining optimal venipuncture point and direction based on near-infrared image |
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 |