CN114589697B - Intelligent disinfection inspection environment adjusting robot and control method - Google Patents
Intelligent disinfection inspection environment adjusting robot and control method Download PDFInfo
- Publication number
- CN114589697B CN114589697B CN202210282711.7A CN202210282711A CN114589697B CN 114589697 B CN114589697 B CN 114589697B CN 202210282711 A CN202210282711 A CN 202210282711A CN 114589697 B CN114589697 B CN 114589697B
- Authority
- CN
- China
- Prior art keywords
- point
- environment
- node
- robot
- open list
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004659 sterilization and disinfection Methods 0.000 title claims abstract description 41
- 238000007689 inspection Methods 0.000 title claims abstract description 19
- 230000007613 environmental effect Effects 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 10
- 230000002147 killing effect Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 241000894006 Bacteria Species 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000003750 conditioning effect Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000001105 regulatory effect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000000889 atomisation Methods 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000000645 desinfectant Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61L—METHODS OR APPARATUS FOR STERILISING MATERIALS OR OBJECTS IN GENERAL; DISINFECTION, STERILISATION OR DEODORISATION OF AIR; CHEMICAL ASPECTS OF BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES; MATERIALS FOR BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES
- A61L2/00—Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor
- A61L2/24—Apparatus using programmed or automatic operation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/1605—Simulation of manipulator lay-out, design, modelling of manipulator
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61L—METHODS OR APPARATUS FOR STERILISING MATERIALS OR OBJECTS IN GENERAL; DISINFECTION, STERILISATION OR DEODORISATION OF AIR; CHEMICAL ASPECTS OF BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES; MATERIALS FOR BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES
- A61L2202/00—Aspects relating to methods or apparatus for disinfecting or sterilising materials or objects
- A61L2202/10—Apparatus features
- A61L2202/14—Means for controlling sterilisation processes, data processing, presentation and storage means, e.g. sensors, controllers, programs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61L—METHODS OR APPARATUS FOR STERILISING MATERIALS OR OBJECTS IN GENERAL; DISINFECTION, STERILISATION OR DEODORISATION OF AIR; CHEMICAL ASPECTS OF BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES; MATERIALS FOR BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES
- A61L2202/00—Aspects relating to methods or apparatus for disinfecting or sterilising materials or objects
- A61L2202/10—Apparatus features
- A61L2202/16—Mobile applications, e.g. portable devices, trailers, devices mounted on vehicles
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Automation & Control Theory (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Manipulator (AREA)
- Feedback Control In General (AREA)
Abstract
The invention is suitable for the field of disinfection robots, and provides an intelligent disinfection inspection environment adjusting robot and a control method. The invention adopts various sensors and execution modules, can detect and classify the environmental state based on the artificial intelligence technology, carries out self-adaptive feedback control aiming at different working conditions, and also adds an environmental regulation function on the basis of the disinfection function, namely, regulating the temperature, humidity, environmental quality and the like of the environment, thereby realizing the personalized environmental regulation function based on the artificial intelligence technology.
Description
Technical Field
The invention belongs to the field of disinfection robots, and particularly relates to an intelligent disinfection inspection environment adjusting robot and a control method thereof.
Background
The intelligent disinfection robot generally adopts a disinfectant atomization mode, so that the indoor environment can be comprehensively disinfected. The disinfection system can be rapidly deployed in public places such as office buildings, halls, restaurants, meeting rooms and the like, can be used for realizing disinfection of application scenes, is unattended, is safe and healthy. The disinfection robot comprises a movable chassis and a plurality of disinfection modules, the disinfection process of the disinfection robot is generally preset manually, and then the robot is used for disinfection on an installation setting track according to a setting program. In the actual use process, the robot is in an environment and faces complex working conditions, the applicable working conditions of different killing modes and the killing effects are different, and after the killing is completed, the effect of the killing cannot be estimated.
In addition, at present, the disinfection robot is manually adjusted, and is slow, different requirements may exist in each area, and the equipment usually operates in various environments, even in the same space, the control targets may be greatly different in different weather and seasons. Therefore, the traditional disinfection robot control method is relatively fixed, and the problem of insufficient environment adaptability can be caused.
Disclosure of Invention
In view of the above problems, the invention aims to provide an intelligent disinfection inspection environment adjusting robot and a control method thereof, which aim to solve the technical problems that the existing disinfection robot is single in control mode and cannot be adjusted adaptively according to the environment.
The invention adopts the following technical scheme:
In one aspect, the intelligent disinfection inspection environment adjustment robot control method comprises the following steps:
s1, the robot builds an indoor map according to the current indoor environment and collects environmental parameters according to the sensor;
s2, modeling and estimating the whole space indoor according to the indoor map and the environmental parameters acquired by the robot sensor in the map construction scanning process to obtain a plurality of classification working conditions;
step S3, performing robot disinfection work pre-planning according to the classification working conditions, wherein the pre-planning result comprises planning paths and planning reference actions of different execution modules of each point location;
and S4, controlling the robot to execute actions according to the pre-planning result, collecting environment information in real time, and dynamically adjusting according to the environment change.
Further, in the step S2, a kalman filter is used to process the environmental parameters acquired by the sensor.
Further, in step S2, the specific process of obtaining the plurality of classification working conditions by performing modeling estimation on the whole space chamber is as follows:
Constructing a hyperplane D based on a support vector machine method, and obtaining a target sample set (p i,qi) through environment parameter data acquired in a modeling stage, wherein pi refers to information of a certain point on a certain map under a certain working condition, and qi refers to the type of the working condition;
The point p i on the hyperplane D satisfies: b qi(t)＝-ωqi(t)*f(pi),bqi (t) is a classification threshold, ω qi (t) is an improvement weight, f (p i) is a kernel function, ω qi(t)＝ωqi+γ(t),ωqi is a weight parameter, γ (t) is a compensation weight coefficient, and the hyperplane D constraint is qi (ω qi(t)*f(pi)+bqi(t))≥1-εi,εi is a relaxation variable;
The minimisation function under this constraint is: c qi is a penalty factor applied to out-of-range sampling points, where c qi-min corresponding to the smallest a qi-min in the population is obtained aqi-min＝min{aqi(t1),aqi(t2),aqi(t3),...aqi(ti)};
The final decision function is: And finally, qi different working condition classifications are obtained.
Further, the step S3 specifically includes:
s31, determining an environment weight value H by using the gridding map;
S32, initializing an open list, wherein the open list is used for storing information of points to be calculated and a closed list, the closed list is used for storing information of points which are not calculated as path points, and starting nodes related to starting points are put into the open list;
S33, calculating a weight value in the open list, wherein the weight value consists of two parts, namely a distance weight E and an environment weight H, finding out a comprehensive weight F=E+H with the minimum weight value, searching a point with the minimum F value in the open list, and taking the point as a current point;
s34, removing the point from the open list and placing the point into the closed list;
S35, each node adjacent to the current node is calculated according to the following principle, if the adjacent node is at a closed node or does not exist, the point in the next open list is directly calculated, if the next point is not in the open list, the point is added into the open list, and the F value is calculated; if the adjacent node is in the open list, comparing the F value of the node with that of other adjacent nodes, if the F value is smaller than that of the other adjacent nodes, setting the node as the current node, and resetting the adjacent node of the node;
S36, repeating the step S35 until the end point is added into the open list.
On the other hand, the intelligent disinfection inspection environment adjusting robot comprises a sensor, an execution module and a control module, wherein the control module comprises:
The environment modeling unit is used for constructing an indoor map according to the current indoor environment and collecting environment parameters according to the sensor;
The working condition classification unit is used for carrying out modeling estimation on the whole space indoor according to the indoor map and the environmental parameters acquired by the robot sensor in the map construction scanning process to obtain a plurality of classification working conditions;
The pre-planning unit is used for carrying out pre-planning on the robot killing work according to the classification working conditions, and the pre-planning result comprises a planning path and reference actions of different execution modules of each point position;
And the execution and dynamic classification unit is used for controlling the robot to execute actions according to the pre-planning result, collecting environment information in real time and dynamically adjusting according to the environment change.
Further, the sensor comprises an abnormal gas sensor, an acousto-optic sensor, a bacteria concentration sensor and a temperature and humidity sensor.
Further, the execution module comprises an ultraviolet lamp tube, an ozone generator, an ultrasonic atomizer and a dehumidifier.
Further, the sensor comprises an abnormal gas sensor, an acousto-optic sensor, a bacteria concentration sensor and a temperature and humidity sensor.
The beneficial effects of the invention are as follows:
firstly, the invention provides an intelligent disinfection inspection environment adjusting robot, which integrates multifunctional detection, adjustment and automatic navigation, particularly, the environment is collected and monitored by arranging various sensors in the robot, the environment is classified by adopting an artificial intelligent control method, different working conditions are obtained, different targets are planned, different parameters can be provided for a later controller, and the self-adaptive capacity of the robot for self adjustment is improved;
The invention further provides a robot control method, which adopts an artificial intelligence technology to detect and classify the environment states, performs self-adaptive feedback control on different working conditions, and can automatically complete the functions of data acquisition, processing, pattern recognition, inspection, environment monitoring and environment regulation.
Drawings
Fig. 1 is a hardware configuration diagram of an intelligent disinfection inspection environment adjustment robot provided by an embodiment of the invention;
Fig. 2 is a flowchart of a control method of the intelligent disinfection inspection environment adjustment robot provided by the embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Fig. 1 shows a hardware structure diagram of an intelligent disinfection inspection environment adjusting robot provided by an embodiment of the invention, wherein the robot can walk indoors through a chassis motor, and a camera and a laser radar are arranged in the robot, so that the indoor environment can be scanned. Various sensors, such as an abnormal gas sensor, an acousto-optic sensor, a bacteria concentration sensor, a temperature and humidity sensor and the like shown in fig. 1, are mounted in the intelligent disinfection inspection environment adjustment robot provided by the embodiment of the invention, and the sensors are not particularly limited. Meanwhile, the robot is also provided with execution modules, such as various disinfection modules and environment adjustment modules, including ultraviolet lamp tubes, ozone generators, ultrasonic atomizers, dehumidifiers and the like. In addition, the robot of this embodiment also includes control module, control module is used for carrying out artificial intelligence processing according to the data that the sensor gathered, then control execution module carries out corresponding operation. The control module comprises an environment modeling unit, a working condition classifying unit, a pre-planning unit and an executing and dynamic classifying unit. Based on the intelligent disinfection inspection environment adjustment robot, correspondingly, the embodiment of the invention provides a control method of the intelligent disinfection inspection environment adjustment robot, which comprises the following steps as shown in fig. 2:
S1, an environment modeling step: the robot builds an indoor map according to the current indoor environment, and collects environmental parameters according to the sensors.
The map construction is to construct a map of the current indoor environment layout, and the specific robot can perform map construction and automatic navigation through the laser SLAM technology, and the specific map construction process is not the focus of the embodiment, and is not repeated here. In the mapping process, the sensor collects environmental data.
Because noise may be generated in the process of collecting the sensor due to external interference or internal circuit problems, the collected data may be affected, and therefore, the Kalman filter is adopted to process each signal in the step.
Specifically, assuming that the state quantity detected by the sensor at time t is x_me (t) = (X 1,X2,X3..Xk), k is the state of the kth sensor, filtering high-frequency noise by adopting a smoothing method based on the sensor performance, wherein sigma is an error matrix of the sensor,For the range of the sensor, θ is the filter coefficient, and there is/>
S2, working condition classification: and modeling and estimating the whole space indoor according to the indoor map and the environmental parameters acquired by the robot sensor in the map construction scanning process to obtain a plurality of classification working conditions.
After data preprocessing, modeling estimation and classification working conditions are carried out in the step, and the specific process is as follows:
S21, constructing a hyperplane D based on a support vector machine method, and obtaining a target sample set (p i,qi) through environment parameter data acquired in a modeling stage, wherein pi refers to information of a certain point on a certain map under a certain working condition, and qi refers to the type of the working condition.
The model of modeling estimation is: p i＝(POSi,Xi (t)), wherein POS i is position information under i conditions, and X i (t) is environmental parameter information of a current position under i conditions. p i is the eigenvector of the above information, which is k+2-dimensional p i∈Rk+2. Considering pi as a vector, the SVM is used to introduce a kernel function f (p i)＝M(POSi,Xi (t)) to construct a hyperplane D to ensure data separability.
S22, a point p i on the hyperplane D meets the following conditions: b qi(t)＝-ωqi(t)*f(pi),bqi (t) is a classification threshold, ω qi (t) is an improvement weight, f (p i) is a kernel function, ω qi(t)＝ωqi+γ(t),ωqi is a weight parameter, γ (t) is a compensation weight coefficient, and the hyperplane D is constrained to qi (ω qi(t)*f(pi)+bqi(t))≥1-εi,εi is a relaxation variable).
The working condition classification is carried out according to environmental parameters such as temperature and humidity, illumination intensity, bacterial quantity, ozone concentration, personnel quantity and the like.
Firstly, constructing a hyperplane D based on a support vector machine method, obtaining a target sample set (p i,qi) through data in a modeling stage, wherein pi refers to information of a certain point on a certain map under a certain working condition, qi refers to the type of the working condition, for example, qi refers to four working conditions of spring, summer, autumn and winter. p i∈Rk+2,qi e {1,2,..l } represents the number of classifications. The point p i on this plane D satisfies: b qi(t)＝-ωqi(t)*f(pi). Here ω qi(t)＝ωqi+γ(t).bqi (t) is a classification threshold, ω qi (t) is an improvement weight, f (p i) is a kernel function satisfying the Mercer condition, ω qi is a weight parameter, and γ (t) is a compensation weight coefficient.
In general, ω qi is a pre-adjusted parameter matrix, which has a better effect in a static or quasi-static system, and in consideration of the real-time performance of the operation of a robot and the dynamic change performance of the system, if a certain sensor fails, the traditional method may cause error classification, so that the fault working condition is considered, the invention realizes the goal by improving the weight ω qi (t), and when a sudden new working condition occurs, a manager can be timely notified to process, in order to improve the calculation efficiency, a gaussian weight is adopted to acquire a compensation weight coefficient γ (t), the parameter is related to the state value Λ (X i (t)) of each sensor, and when a certain sensor exceeds a threshold value, infinity is obtained, namely:
Equation b qi(t)＝-ωqi(t)*f(pi) to find the optimal classification plane, ω qi (t) and b qi (t) satisfy the following conditions:
qi*ωqi(t)*f(pi)+bqi(t)≥1
Considering that some samples cannot be correctly classified by the hyperplane, a relaxation variable ε i is more than or equal to 0, and the hyperplane constraint is:
qi*ωqi(t)*f(pi)+bqi(t)≥1-εi。
S23, the minimisation function value under the constraint is as follows: c qi is a penalty factor applied to out-of-range sampling points, where c qi-min corresponding to the smallest a qi-min in the population is obtained aqi-min＝min{aqi(t1),aqi(t2),aqi(t3),...aqi(ti)}.
C qi is a penalty factor applied to out-of-range sample points that can be traded off between the complexity of the algorithm and the error rate of the samples. Similar to ω qi (t), the selection of this parameter also uses dynamic changes to adapt to the continuous addition of new data in the mobile environment to refine the model. Since the sensor acquisition frequency is higher and the system parameter changes slowly, the embodiment adopts the value of the minimisation floodfunction within a period of time to select a reasonable c qi, continuously calculates a qi (t) within a period of time, calculates a qi (t) by randomly selecting c qi, and obtains the c qi-min corresponding to the smallest a qi-min in the group as the final parameter for solving the decision function ψ qi (p):
aqi-min＝min{aqi(t1),aqi(t2),aqi(t3),...aqi(ti)}
s24, finally obtaining a decision function as follows: And finally, qi different working condition classifications are obtained.
Step S3, a pre-planning step: and carrying out pre-planning on the robot killing work according to the classified working conditions, wherein a pre-planning result comprises a planning path and reference actions of different execution modules of each point position.
The path planning adopts a scene weight combination method. The specific process is as follows:
S31, determining an environment weight value H by using the gridding map.
S32, initializing an open list, wherein the open list is used for storing information of points to be calculated and a closed list, the closed list is used for storing information of points which are not calculated as path points, and a start node related to a starting point is put into the open list.
S33, calculating a weight value in the open list, wherein the weight value consists of two parts, namely a distance weight E and an environment weight H, finding out a comprehensive weight F=E+H with the minimum weight value, searching a point with the minimum F value in the open list, and taking the point as a current point. The distance weight represents the path length, the environment weight represents the necessity of whether the robot reaches the point according to different working conditions, the environment weight value H is obtained by classification according to the working conditions, and the smaller the weight value is, the more important the representation is.
S34, removing the point from the open list, and placing the point into the closed list.
S35, each node adjacent to the current node is calculated according to the following principle, if the adjacent node is at a closed node or does not exist, the point in the next open list is directly calculated, if the next point is not in the open list, the point is added into the open list, and the F value is calculated; if the neighbor node is in the open list, the F values of this node and other neighbors are compared, and if it is less than, the node is set as the current node and the neighbors of the node are reset.
S36, repeating the step S35 until the end point is added into the open list. If the end point does not enter the open list, it represents a path that does not meet the requirements. At this time, the calculation mode of the weight F can be adjusted to try whether a new path exists, and the steps are repeated until a solution exists.
Step S4, executing and dynamically classifying: and controlling the robot to execute actions according to the pre-planning result, collecting environment information in real time, and dynamically adjusting according to the change of the environment, wherein the steps comprise spraying, starting an ultraviolet lamp, an ozone generator, a fan and the like. And dynamically classifying the executed process, dynamically planning and executing, and repeatedly executing S2-S4 to meet the disinfection requirement.
In summary, the invention provides an intelligent robot capable of moving autonomously and performing automatic disinfection and environment adjustment tasks according to different working conditions, the intelligent robot is based on an artificial intelligence technology to realize the recognition of various environment working conditions, the automatic planning of a disinfection scheme is performed through a parameter recognition result, and finally, the adjustment of the indoor environment is realized through an execution module such as a built-in disinfection module, an environment adjustment module and the like, so as to achieve a target adjustment effect.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. The intelligent disinfection inspection environment adjustment robot control method is characterized by comprising the following steps of:
s1, the robot builds an indoor map according to the current indoor environment and collects environmental parameters according to the sensor;
s2, modeling and estimating the whole space indoor according to the indoor map and the environmental parameters acquired by the robot sensor in the map construction scanning process to obtain a plurality of classification working conditions;
step S3, performing robot disinfection work pre-planning according to the classification working conditions, wherein the pre-planning result comprises planning paths and planning reference actions of different execution modules of each point location;
s4, controlling the robot to execute actions according to the pre-planning result, collecting environment information in real time, and dynamically adjusting according to the environment change;
In step S2, the modeling estimation is performed on the whole space indoor to obtain a plurality of classification working conditions, and the specific process is as follows:
Constructing a hyperplane D based on a support vector machine method, and acquiring a target sample set (p i,qi) through environmental parameters acquired in an indoor map construction stage, wherein p i refers to information of a certain point on a certain map under a certain working condition, and q i refers to the type of the working condition;
the point p i on the hyperplane D satisfies: for the classification threshold value,/> To improve the weight, f (p i) is a kernel function,/> As the weight parameter, gamma (t) is the compensation weight coefficient, and the hyperplane D is constrained to be/>Epsilon i is the relaxation variable;
The minimisation function under this constraint is: Is a punishment factor applied to out-of-range sampling points, and the minimum/>, among the groups, is obtained Corresponding/>Here/>
The final decision function is: q i different working condition classifications are finally obtained;
The step S3 specifically includes:
s31, determining an environment weight value H by using the gridding map;
S32, initializing an open list, wherein the open list is used for storing information of points to be calculated and a closed list, the closed list is used for storing information of points which are not calculated as path points, and starting nodes related to starting points are put into the open list;
S33, calculating a weight value in the open list, wherein the weight value consists of two parts, namely a distance weight E and an environment weight H, finding out a comprehensive weight F=E+H with the minimum weight value, searching a point with the minimum F value in the open list, and taking the point as a current point;
s34, removing the point from the open list and placing the point into the closed list;
S35, each node adjacent to the current node is calculated according to the following principle, if the adjacent node is at a closed node or does not exist, the point in the next open list is directly calculated, if the next point is not in the open list, the point is added into the open list, and the F value is calculated; if the adjacent node is in the open list, comparing the F value of the node with that of other adjacent nodes, if the F value is smaller than that of the other adjacent nodes, setting the node as the current node, and resetting the adjacent node of the node;
S36, repeating the step S35 until the end point is added into the open list.
2. The method for controlling an intelligent disinfection inspection environment adjustment robot according to claim 1, wherein in the step S2, the environmental parameters collected by the sensor are processed by a kalman filter.
3. The utility model provides an environment adjustment robot is patrolled and examined in intelligence disinfection, its characterized in that, the environment adjustment robot is patrolled and examined in intelligence disinfection includes sensor, execution module and control module, wherein control module includes:
The environment modeling unit is used for constructing an indoor map according to the current indoor environment and collecting environment parameters according to the sensor;
The working condition classification unit is used for carrying out modeling estimation on the whole space indoor according to the indoor map and the environmental parameters acquired by the robot sensor in the map construction scanning process to obtain a plurality of classification working conditions;
The pre-planning unit is used for carrying out pre-planning on the robot killing work according to the classification working conditions, and the pre-planning result comprises a planning path and reference actions of different execution modules of each point position;
The execution and dynamic classification unit is used for controlling the robot to execute actions according to the pre-planning result, collecting environment information in real time and dynamically adjusting according to the environment change;
In the working condition classification unit, modeling estimation is carried out on the whole space indoor to obtain a plurality of classification working conditions, wherein the specific process is as follows:
Constructing a hyperplane D based on a support vector machine method, and acquiring a target sample set (p i,qi) through environmental parameters acquired in an indoor map construction stage, wherein p i refers to information of a certain point on a certain map under a certain working condition, and q i refers to the type of the working condition;
the point p i on the hyperplane D satisfies: for the classification threshold value,/> To improve the weight, f (p i) is a kernel function,/> As the weight parameter, gamma (t) is the compensation weight coefficient, and the hyperplane D is constrained to be/>Epsilon i is the relaxation variable;
The minimisation function under this constraint is: Is a punishment factor applied to out-of-range sampling points, and the minimum/>, among the groups, is obtained Corresponding/>Here/>
The final decision function is: q i different working condition classifications are finally obtained;
The execution process of the pre-planning unit comprises the following steps:
s31, determining an environment weight value H by using the gridding map;
S32, initializing an open list, wherein the open list is used for storing information of points to be calculated and a closed list, the closed list is used for storing information of points which are not calculated as path points, and starting nodes related to starting points are put into the open list;
S33, calculating a weight value in the open list, wherein the weight value consists of two parts, namely a distance weight E and an environment weight H, finding out a comprehensive weight F=E+H with the minimum weight value, searching a point with the minimum F value in the open list, and taking the point as a current point;
s34, removing the point from the open list and placing the point into the closed list;
S35, each node adjacent to the current node is calculated according to the following principle, if the adjacent node is at a closed node or does not exist, the point in the next open list is directly calculated, if the next point is not in the open list, the point is added into the open list, and the F value is calculated; if the adjacent node is in the open list, comparing the F value of the node with that of other adjacent nodes, if the F value is smaller than that of the other adjacent nodes, setting the node as the current node, and resetting the adjacent node of the node;
S36, repeating the step S35 until the end point is added into the open list.
4. The intelligent disinfection inspection environment adjustment robot of claim 3, wherein said sensors include an abnormal gas sensor, an acousto-optic sensor, a bacteria concentration sensor and a temperature and humidity sensor.
5. The intelligent disinfection, inspection environment conditioning robot of claim 3, wherein the execution module comprises an ultraviolet tube, an ozone generator, an ultrasonic atomizer, and a dehumidifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210282711.7A CN114589697B (en) | 2022-03-22 | 2022-03-22 | Intelligent disinfection inspection environment adjusting robot and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210282711.7A CN114589697B (en) | 2022-03-22 | 2022-03-22 | Intelligent disinfection inspection environment adjusting robot and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114589697A CN114589697A (en) | 2022-06-07 |
| CN114589697B true CN114589697B (en) | 2024-05-28 |
Family
ID=81810157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210282711.7A Active CN114589697B (en) | 2022-03-22 | 2022-03-22 | Intelligent disinfection inspection environment adjusting robot and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114589697B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115585524B (en) * | 2022-09-30 | 2024-04-19 | 上海帝伽医疗科技有限公司 | Disinfection method and device for dynamically removing pathogens |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109568623A (en) * | 2018-12-28 | 2019-04-05 | 珠海市微半导体有限公司 | A kind of the disinfection controlling of path thereof and chip of portable intelligent disinfection robot |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
| CN111376268A (en) * | 2020-02-27 | 2020-07-07 | 达闼机器人有限公司 | Disinfection method, disinfection robot and storage medium |
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
| CN111588875A (en) * | 2020-05-18 | 2020-08-28 | 常州工学院 | Disinfection and sterilization robot |
| CN112985397A (en) * | 2019-12-13 | 2021-06-18 | 北京京东乾石科技有限公司 | Robot trajectory planning method and device, storage medium and electronic equipment |
| CN113144264A (en) * | 2021-03-18 | 2021-07-23 | 武汉联一合立技术有限公司 | Intelligent killing system and method |
| CN113296501A (en) * | 2021-05-07 | 2021-08-24 | 北京农业智能装备技术研究中心 | Greenhouse inspection robot, and greenhouse environment three-dimensional monitoring system and method |
| CN113483757A (en) * | 2021-06-17 | 2021-10-08 | 浙江图讯科技股份有限公司 | Control system of sterilization robot |
-
2022
- 2022-03-22 CN CN202210282711.7A patent/CN114589697B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109568623A (en) * | 2018-12-28 | 2019-04-05 | 珠海市微半导体有限公司 | A kind of the disinfection controlling of path thereof and chip of portable intelligent disinfection robot |
| CN110908370A (en) * | 2019-10-31 | 2020-03-24 | 华能国际电力股份有限公司海门电厂 | Unmanned inspection task planning method and system for thermal power plant |
| CN112985397A (en) * | 2019-12-13 | 2021-06-18 | 北京京东乾石科技有限公司 | Robot trajectory planning method and device, storage medium and electronic equipment |
| CN111376268A (en) * | 2020-02-27 | 2020-07-07 | 达闼机器人有限公司 | Disinfection method, disinfection robot and storage medium |
| CN111582510A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Intelligent identification method and system based on support vector machine and civil aircraft engine |
| CN111588875A (en) * | 2020-05-18 | 2020-08-28 | 常州工学院 | Disinfection and sterilization robot |
| CN113144264A (en) * | 2021-03-18 | 2021-07-23 | 武汉联一合立技术有限公司 | Intelligent killing system and method |
| CN113296501A (en) * | 2021-05-07 | 2021-08-24 | 北京农业智能装备技术研究中心 | Greenhouse inspection robot, and greenhouse environment three-dimensional monitoring system and method |
| CN113483757A (en) * | 2021-06-17 | 2021-10-08 | 浙江图讯科技股份有限公司 | Control system of sterilization robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114589697A (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Krajník et al. | Fremen: Frequency map enhancement for long-term mobile robot autonomy in changing environments | |
| US10833888B2 (en) | IoT device plug-in method and device in data analysis-based automation systems | |
| Choudhary et al. | Autonomous crop irrigation system using artificial intelligence | |
| US8160729B2 (en) | Application of microsystems for a building system employing a system knowledge base | |
| CN107655159B (en) | Air conditioner energy-saving control method and system based on crowd density sensing model | |
| CN112269416B (en) | Monitoring and maintaining robot system and method applied to data center | |
| CN114589697B (en) | Intelligent disinfection inspection environment adjusting robot and control method | |
| CN110610275B (en) | Variable air volume air conditioner load prediction method and system based on ACQPSO-ELM | |
| Pan et al. | An electronic nose network system for online monitoring of livestock farm odors | |
| CN112728727A (en) | Intelligent adjusting system for indoor environment comfort level based on edge calculation | |
| KR20190114929A (en) | Electronic apparatus for managing heating and cooling and controlling method of the same | |
| CN114489070A (en) | Household inspection method, nonvolatile readable storage medium and computer equipment | |
| JP4389046B2 (en) | State vector estimation method and autonomous moving body | |
| CN117515854A (en) | Intelligent optimization method and device for central air conditioner | |
| CN114489200A (en) | Warmhouse booth environmental control system | |
| CN106502121A (en) | A kind of intelligent home control system | |
| Pandiyaraju et al. | An optimal energy utilization model for precision agriculture in WSNs using multi-objective clustering and deep learning | |
| Outanoute et al. | Synthesis of an Optimal Dynamic Regulator Based on Linear Quadratic Gaussian (LQG) for the Control of the Relative Humidity Under Experimental Greenhouse. | |
| CN117794023A (en) | Self-adaptive energy-saving adjustment method and system for illumination system based on high-efficiency LED lamp | |
| Crispim et al. | Prediction of the solar radiation evolution using computational intelligence techniques and cloudiness indices | |
| JP6559182B2 (en) | Control system for response time estimation and automatic operating parameter adjustment | |
| CN117128624A (en) | Control method and device for fresh air conditioner and air conditioner management system and storage medium | |
| CN104090608B (en) | A kind of phytotron control method | |
| CN108419439A (en) | Housed device learning method and server | |
| CN116594285A (en) | Big data environment parameter Internet of things intelligent control method and system |
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 |