CN115091466A - Multifunctional intelligent home-based care robot system - Google Patents

Abstract

The invention provides a multifunctional intelligent home-based care robot system, which comprises an RSS sensing network sensing platform, a data acquisition and gathering transmission unit, a server data processing and task planning platform and a CareBot robot platform. The invention realizes the integration of the robot into a home-based old-age scene, deeply integrates the intelligent home sensing network and the robot, overcomes the defects of insufficient information perception capability of the robot, insufficient task supporting capability of the sensing network and the like, and constructs a task planner at the cloud end of the server aiming at complex tasks to solve the problem of task execution of the robot in the complex task scene.

Description

Multifunctional intelligent home-based care robot system

Technical Field

The invention relates to the technical field of endowment robots, in particular to a multifunctional intelligent home-based endowment robot system.

Background

The characteristics of China after stepping into the aging stage are as follows: the aging population is large, the aging speed is high, the aging degree is high, the empty nest degree is deepened, and in addition, the problem of 'not being rich but old first' is very serious. As the working strength and the pressure of people are higher and higher, the old people needing to be cared for are unconscious, cannot be cared for by the old people all the time, and are often difficult to rescue and treat in time once the old people have sudden abnormal conditions. In recent years, driven by the rapid development of technologies such as computers and communications and the trend toward aging of population, more and more researchers have started to research related technologies of service robots, and have gradually moved to service places such as homes, restaurants and offices, which is of great significance particularly in the field of home care.

However, the existing intelligent care robot for the aged has a narrow working field, can only generally provide assistance services with single functions and narrow application range for the old, is expensive, and cannot give consideration to indoor daily living assistance and safety problem detection of the old.

Disclosure of Invention

The invention provides a multifunctional intelligent home-based care robot system aiming at the technical problems in the prior art, which comprises an RSS sensing network sensing platform, a data acquisition and gathering transmission unit, a server data processing and task planning platform and a CareBot robot platform;

the RSS sensing network sensing platform comprises a plurality of fixed sensors and is used for sensing behavior data, physiological health data and environmental condition data of the living old;

the data acquisition and summary transmission unit is used as a sensor transmission gateway and is used for summarizing and transmitting the behavior data, the physiological health data and the environmental condition data of the living old, which are sensed by all the fixed sensors, to the server data processing and task planning platform;

the server data processing and task planning platform is used for processing and identifying the behavior data, the physiological health data and the environmental condition data of the living old people to obtain a primary identification result, generating a task instruction according to the primary identification result and issuing the task instruction to the CareBot robot platform; adjusting the preliminary recognition result according to the perception result fed back by the CareBot robot platform;

the CareBot robot platform is provided with a plurality of sensors and is used for executing corresponding tasks according to the task instructions, sensing the behavior data, the physiological health data and the environmental condition data of the old at home again through the plurality of sensors, and feeding back the sensing result to the server data processing and task planning platform; and according to the task instruction, realizing assistance to the old at home.

On the basis of the technical scheme, the invention can be improved as follows.

Optionally, the RSS sensing network sensing platform includes a behavior sensing part, a physiological sensing part, and an environmental condition sensing part;

the behavior sensing part comprises a depth camera, a door sensor and a human body sensor and is used for recording daily behavior habits of the old at home and fall detection of the old;

the physiological sensing part comprises an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent glucometer and an intelligent weighing scale and is used for detecting the daily physical condition of the old;

the environment condition sensing part comprises a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, a safety SOS alarm and an intelligent bracelet, wherein the temperature and humidity sensor, the water immersion sensor, the gas sensor and the fire sensor are used for detecting the condition of a home environment; SOS alarm and intelligent bracelet are used for ensuring the old man and attend to the police independently at home or under the condition of going out.

Optionally, the data acquisition and summary transmission unit connects all sensors of the RSS sensor network sensing platform by using a Zigbee intelligent gateway, summarizes the sensing data of all sensors, where the sensing data includes household old people behavior data, physiological health data, and environmental condition data, and transmits the sensing data to the server data processing and task planning platform based on an internet technology.

Optionally, the server data processing and task planning platform includes a task planner, a database, an event detection module, and an execution instruction conversion module;

the database is used for storing the behavior data, the physiological health data and the environmental condition data of the family old people sensed by each sensor;

the event detection module is used for detecting and identifying behavior data, physiological health data and environmental condition data of the living old, which are sensed by all fixed sensors, and identifying the behavior, the requirement and the environmental condition of the old to obtain a primary identification result;

the task planner is used for planning a task according to the preliminary identification result and generating a task instruction;

and the execution instruction conversion module is used for converting the generated task instruction into an instruction which can be identified by the CareBot robot platform.

Optionally, the CareBot robot platform includes a sensing layer, an interaction layer, an SLAM layer, and an execution mechanism;

the SLAM layer is used for generating a planning path of the CareBot robot according to the received task instruction;

the executing mechanism is used for moving to a corresponding position according to the planned path;

the sensing layer comprises a plurality of sensors, moves along with the movement of the CareBot robot, is used for sensing the behavior data, the physiological health data and the environmental condition data of the living old again at the corresponding positions, and feeds back the sensing result to the server data processing and task planning platform;

the interaction layer comprises an airborne voice module and a display module and is used for carrying out emotion interaction with the old and carrying out video conversation with family members in a home scene.

Optionally, the SLAM layer and the execution layer respectively act on the robot moving chassis, the camera lifting, the drawers at two sides, and water management.

Optionally, the executing mechanism is provided with a sensor box, an airborne camera, a human body detector, a fire sensor and a gas sensor are loaded in the sensor box, and the sensor box can perform three-degree-of-freedom operation including lifting, pitching and left-right operation, so that the robot can detect and check 360-degree dead angles in a moving scene.

Optionally, the system further comprises a tablet personal computer remote terminal platform, wherein the tablet personal computer remote terminal platform comprises a robot operation module, a data reading module, a sensor operation module and an information recording module;

the robot operating module is used for the old, the children or community staff to remotely control the robot so that the robot can move indoors to check indoor conditions;

the sensor control module is used for the old, children and community staff to remotely control the onboard cameras and various sensors to check and detect the indoor 360-degree dead angle-free state;

the data reading module is used for the old, the children and the community staff to check the current old condition, the indoor condition and the robot task execution condition;

and the information recording module is used for recording the sensing results and the operation behaviors of the sensors.

Optionally, the task planner is configured to plan a task according to the preliminary identification result, and generate a task instruction, including:

and the task planner plans the tasks by adopting a multi-target clustering genetic task planning algorithm according to the primary identification result to generate task instructions.

Optionally, the task planner plans the task by using a multi-objective clustering genetic task planning algorithm according to the preliminary identification result to generate a task instruction, including:

step 1: initializing a population and various parameters, wherein the various parameters comprise maximum iteration frequency setting, population scale, cross rate and variation probability;

step 2: judging whether a termination condition is met, if so, outputting an optimal solution and ending, and if not, executing Step 3;

step 3: carrying out Canopy-Kmeans clustering;

step 4: judging whether a disturbance condition is met, wherein the disturbance condition is a disturbance factor B based on the number of clusters, if not, judging whether the number of clusters is less than 3, wherein the number of clusters can be understood as the number of tasks, if so, mc is mc +1, m is the number of tasks, c is the number of grids divided by one dimension,

wherein c is a positive integer, N is the number of the population, M is the number of the targets, and Step8 is skipped; if the disturbance condition is satisfied, mc is set to 0, and Step5 is executed;

step 5: carrying out Canopy-Kmeans clustering again;

step 6: will this iteration

Is set to 2 wherein

z is a random number between 0 and 1, d is the current number of iterations, d _max Is the maximum iteration number;

step 7: judgment of

Taking the value of [0, n]If yes, carrying out different-group crossing; if not, carrying out same-group crossing;

step 8: carrying out mutation;

step 9: decoding is performed and jumps to Step2, and the process loops in turn until the optimal solution set is output.

The invention provides a multifunctional intelligent home-based care robot system which comprises an RSS sensing network sensing platform, a data acquisition and gathering transmission unit, a server data processing and task planning platform and a CareBot robot platform. The invention realizes the integration of the robot into a home-based old-age scene, deeply integrates the intelligent home sensing network and the robot, overcomes the defects of insufficient information perception capability of the robot, insufficient task supporting capability of the sensing network and the like, and constructs a task planner at the cloud end of the server aiming at complex tasks to solve the problem of task execution of the robot in the complex task scene.

Drawings

FIG. 1 is a schematic diagram of a real scene of a multifunctional intelligent home-based elderly people care robot system;

FIG. 2 is a schematic structural diagram of a multifunctional intelligent home-based elderly care robot system provided by the present invention;

fig. 3 is a schematic diagram of an overall structure of the multifunctional intelligent home-based elderly care robot system provided by the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the present invention may be arbitrarily combined with each other to form a feasible technical solution, and such combination is not limited by the sequence of steps and/or the structural composition mode, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, such a technical solution combination should not be considered to exist and is not within the protection scope of the present invention.

The invention aims to research a care robot system capable of being integrated with an intelligent home environment system and an intelligent old-age care service platform, constructs an Internet + technology which takes an intelligent robot as a main body and integrates artificial intelligence, big data, the Internet of things, a robot and the like, aims to create a comprehensive intelligent old-age care system which is oriented to communities, organizations and homes and integrates health, life and safety, and solves three problems of the old people in home old-age care: 1) realize that old man at home under the low cost protects the function realization, make more old man at home can enjoy more intelligent care for the aged at home service. 2) By utilizing the characteristic of mobility of the service robot, the problem that intelligent detection cannot be carried out on the indoor full range under the conventional intelligent home environment is solved, the intelligent robot and the intelligent home environment are strongly coupled and cooperated, and the daily and abnormal service requirements are effectively allocated and adapted. 3) By utilizing the internet big data and remote teleoperation technology, the service efficiency of the care robot is improved, and the service efficiency of the robot is improved. Fig. 1 is a simplified System diagram for showing a brief flow chart of the whole System, and as shown in fig. 1, an RSS System is called a Robot Support System, and is characterized in that a Robot System is integrated in an intelligent home environment, so that the intelligent home has not only a strong sensing capability but also a strong execution capability; the system carries out the degree of depth overall arrangement to all kinds of sensors in old man's house environment, gather old man action physiological data and environmental safety data, fuse the algorithm to old man action through long-time data acquisition and based on the many relativities of machine learning, old man demand and old man health and environmental safety situation discern, later transmit the recognition result to the task planner and carry out the mission planning, let the robot go to help the old man to accomplish daily life and live as actuating mechanism, meanwhile, child and community staff also can long-range the real-time condition of looking over the old man, it is secure to realize old man solitary safety, solitary life has companion and is not solitary and can carry out long-range face-to-face interchange with child.

Fig. 2 is a schematic structural diagram of a multifunctional intelligent home-based care robot system provided by the invention, and referring to fig. 2, the care robot system includes an RSS sensor network sensing platform, a data acquisition and summary transmission unit, a server data processing and task planning platform, and a CareBot robot platform.

The RSS sensing network sensing platform comprises a plurality of fixed sensors and is used for sensing behavior data, physiological health data and environmental condition data of the living old. The data acquisition and summary transmission unit is used as a sensor transmission gateway and is used for summarizing and transmitting the behavior data, the physiological health data and the environmental condition data of the living old, which are sensed by all the fixed sensors, to the server data processing and task planning platform; the server data processing and task planning platform is used for processing and identifying the behavior data, the physiological health data and the environmental condition data of the living old people to obtain a primary identification result, generating a task instruction according to the primary identification result and issuing the task instruction to the CareBot robot platform; adjusting the preliminary recognition result according to the perception result fed back by the CareBot robot platform; the CareBot robot platform is provided with a plurality of sensors and is used for executing corresponding tasks according to the task instructions, sensing the behavior data, the physiological health data and the environmental condition data of the old at home again through the plurality of sensors, and feeding back the sensing result to the server data processing and task planning platform; and according to the task instruction, the old people at home can be helped.

The intelligent service robot system for the aged can be understood to deeply integrate the robot technology and the intelligent home Internet of things technology, and solve the problems of health guarantee, emotional companions, family environment safety, daily living and the like of the existing solitary old people. The nursing care robot system mainly comprises an RSS sensing network sensing platform, a data acquisition and gathering transmission platform, a server data processing and task planning platform and a CareBot robot platform. The RSS sensing network sensing platform comprises a plurality of sensing modules and is used for sensing behavior data, health condition data and environmental state information of the old at home; the RSS sensing network sensing platform transmits sensed data of the old at home and the environment at home to the Internet server data processing and task planning platform through the data acquisition, summarization and transmission platform; the server data processing and task planning platform identifies the sensing result to obtain an initial identification result, and generates a task instruction based on the initial identification result; and the CareBot robot platform is used for executing the task instruction from the server data processing and task planning platform and feeding back information sensed by the robot to the server data processing and task planning platform, so that the server data processing and task planning platform adjusts the primary recognition result according to the secondary sensing result of the CareBot robot platform, and adjusts the generated task instruction according to the adjusted recognition result.

The invention realizes the integration of the robot into a home-based old-age scene, deeply integrates the intelligent home sensing network and the robot, overcomes the defects of insufficient information perception capability of the robot, insufficient task supporting capability of the sensing network and the like, and constructs a task planner at the cloud end of the server aiming at complex tasks to solve the problem of task execution of the robot in the complex task scene.

Fig. 3 is a schematic diagram of the whole structure of the care robot system, and as an embodiment, the RSS sensing network sensing platform includes a behavior sensing part, a physiological sensing part, and an environmental condition sensing part. The behavior sensing part comprises a depth camera, a door sensor and a human body sensor and is used for recording daily behavior habits of the old at home and fall detection of the old; the physiological sensing part comprises an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent glucometer and an intelligent weighing scale and is used for detecting the daily physical condition of the old; the environment condition sensing part comprises a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, a safety SOS alarm and an intelligent bracelet, wherein the temperature and humidity sensor, the water immersion sensor, the gas sensor and the fire sensor are used for detecting the condition of a home environment; SOS alarm and intelligent bracelet are used for guaranteeing old man's autonomous alarm under the condition of staying at home or going out.

It can be understood that the RSS sensing network sensing platform is used for collecting behavior data, physiological health data and environmental condition data of the old; the RSS sensing network sensing platform mainly comprises a behavior sensing part, a physiological condition sensing part and an environmental condition sensing part. The behavior sensing part is provided with a depth camera, a door sensor and a human body sensor and is used for recording the daily behavior habits of the old and the falling detection of the old, and information is timely transmitted when the old falls and other accidents occur; the physiological sensing part is provided with an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent glucometer and an intelligent weighing scale and is used for daily detecting the physical condition of the old, and meanwhile, a proper care scheme is made for the old; the environment condition sensing device comprises a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, a safety SOS alarm and an intelligent bracelet, wherein the sensors are used for detecting the environment condition of a house and feeding back the condition to the server background in time when a dangerous condition occurs; SOS alarm and intelligent bracelet are used for ensuring the old man and attend to the police independently at home or under the condition of going out.

And the data acquisition, collection and transmission platform is used as a sensor transmission gateway, and all the sensor data are collected through the intelligent gateway and are transmitted to the server data processing and task planning platform together. The data acquisition and gathering transmission platform collects various data of the RSS platform, and all sensors are connected by adopting a Zigbee intelligent gateway technology in a home scene, so that the construction cost of an internet network channel is saved, and the data is timely and effectively transmitted to a server by utilizing the 5G and other internet technologies.

As an embodiment, the server data processing and task planning platform includes a task planner, a database, an event detection module, and an execution instruction conversion module. The database is used for storing the behavior data, the physiological health data and the environmental condition data of the family old people sensed by each sensor; the event detection module is used for detecting and identifying the behavior data, the physiological health data and the environmental condition data of the living old, which are sensed by all the fixed sensors, and identifying the behavior, the requirement and the environmental condition of the old to obtain a primary identification result; the task planner is used for planning the task according to the preliminary identification result and generating a task instruction; and the execution instruction conversion module is used for converting the generated task instruction into an instruction which can be identified by the CareBot robot platform.

It can be understood that the server data processing and task planning platform is composed of a task planner, a database, an event detection module and an execution instruction conversion module, receives various sensor data from the data acquisition, summarization and transmission platform, the event detection module processes various sensor data, the old people behaviors, the old people demands and the environmental conditions are processed and identified to obtain a primary identification result, then the event detection module is used as the input of the task planner, the output of the task planner is a task level instruction, the event detection module comprises the behavior recognition of the old people, the demand recognition of the old people and the environmental condition recognition, and event input is carried out for the planner, the old people behavior recognition is a visual detection algorithm based on deep learning, the old people demand recognition is a demand perception algorithm based on machine learning, and the home environment perception is a multi-sensor fusion algorithm with multiple correlations. And the execution instruction conversion module converts the output events of the task planner into specific instructions which can be identified and executed by the SLAM layer of the robot moving mechanism and the robot executing mechanism.

As an embodiment, the CareBot robot platform includes a sensing layer, an interaction layer, a SLAM layer, and an execution mechanism; the SLAM layer is used for generating a planning path of the CareBot robot according to the received task instruction; the executing mechanism is used for moving to a corresponding position according to the planned path; the sensing layer comprises a plurality of sensors, moves along with the movement of the CareBot robot, is used for sensing the behavior data, the physiological health data and the environmental condition data of the living old again at the corresponding positions, and feeds back the sensing result to the server data processing and task planning platform; the interaction layer comprises an airborne voice module and a display module and is used for carrying out emotion interaction with the old and carrying out video conversation with family members in a home scene.

It is understood that the CareBot robot platform consists of a perception layer, an interaction layer, a SLAM layer, and an execution mechanism. The SLAM layer and the execution mechanism receive specific execution instructions from the server data processing and task planning platform and feed execution results back to the task planner, wherein the SLAM layer is used for positioning navigation and path planning, and acts on the robot moving chassis to enable the robot to move. The actuating mechanism is provided with a sensor box, the sensor box is used for loading an onboard camera, a human body detector, a fire sensor and a gas sensor, the sensor box can be operated in three degrees of freedom such as lifting, pitching and left-right viewing, 360-degree dead-angle-free detection and viewing under a robot moving scene are achieved, and the actuating mechanism acts on the lifting of the camera, two drawers and water management. The sensing layer is provided with an airborne camera, a human body detector, a fire sensor and a gas sensor, and sensor data sensing information is input and transmitted to the server data processing and task planning platform as a task planner. When accidents such as falling down of the old people occur, the human body detector can detect the abnormity and timely transmit information to the background server, and when accidents such as fire disasters occur in a room, the fire sensor and the gas sensor can timely detect the environment abnormity and timely transmit the information to the background server for further processing by the server. The interaction layer (8) is provided with an onboard voice module and a display module and is used for carrying out emotion interaction with the old and carrying out video conversation with family in a home scene.

As an embodiment, the care robot system further comprises a tablet personal computer remote terminal platform, which comprises a robot operation module, a data reading module, a sensor operation module and an information recording module. The robot operation module is used for the old, the children or community staff to remotely control the robot so that the robot can move indoors to check indoor conditions; the sensor control module is used for remotely controlling the onboard cameras and various sensors by the old, children and community staff to check and detect the indoor 360-degree dead angle-free state; the data reading module is used for the old, the children and the community staff to check the current old condition, the indoor condition and the robot task execution condition; and the information recording module is used for recording the sensing result and the operation behavior of each sensor.

The tablet personal computer remote terminal platform comprises a robot operation module, a data reading module, a sensor control module and an information recording module, wherein the robot operation module is used for the old, the children or community staff to remotely control the robot, so that the robot can move indoors to check indoor conditions; the sensor control module is used for remotely controlling the onboard cameras and various sensors by the old, children and community staff to check and detect the indoor 360-degree dead angle-free state; the data reading module and the information recording module are used for the old, children and community workers to check the current old condition, the indoor condition and the robot task execution condition, so that the old is ensured to be in a safe condition.

It should be noted that, the task planner in the server data processing and task planning platform needs to process and plan various events as the core of the system, and the task planner of the system adopts a multi-objective clustering genetic task planning algorithm. The household service robot needs to execute various complex tasks in a household scene, the tasks comprise daily safety patrol, daily life assistance, daily environment guarantee and emergency situation processing and are divided into daily tasks and emergency tasks, the execution process of the tasks is superposition of NP-hard problems, the solution space is large and complex, an optimal solution is difficult to obtain by an accurate algorithm within an acceptable time, and a heuristic algorithm is more suitable for the problems. The genetic algorithm is a heuristic algorithm, has the characteristics of strong global search capability, good robustness and the like, and has more applications in the field of multi-target optimization. The crossover is an important operation in a genetic algorithm, and largely determines the performance of the algorithm, while the original crossover operation has certain randomness and blindness. Clustering is a commonly used method in the field of data mining, can effectively mine potential relations among data objects, and can be used for extracting individual distribution characteristics in a decision space. The following classifications are made for the situations that the robot needs to perform according to the system situation:

(1) daily safety patrol: cleaning a living room, a kitchen, a bedroom and a bathroom, killing the living room, the kitchen and the bedroom bathroom, removing water stains in the living room, the kitchen and the bedroom bathroom, and checking the potential safety hazards of the living room, the bedroom, the kitchen and the bathroom.

(2) Daily life helps: health management (measuring blood pressure), health management (measuring body temperature), daily reminding (delivering water and medicine), and watering flowers.

(3) Supporting under special conditions: emergency lighting is performed when power failure occurs, the old people are guided to get up at night, fall down to help the old people, and fire is extinguished emergently when fire occurs.

(4) Device-specific case: the electric quantity of the robot is insufficient, and the water quantity of the robot is insufficient.

(5) The whole task is divided into a daily task and an abnormal task, and particularly the response requirement on the algorithm is high in an emergency situation.

The proposed multi-objective clustering genetic task planning algorithm comprises the following steps:

step 1: initializing a population and various parameters, setting the maximum iteration number as 200, the population scale as 150, the crossing rate as 0.85 and the mutation probability as 0.5.

Step 2: and judging whether a termination condition is met, wherein the termination condition is the maximum iteration number, if the termination condition is met, outputting the optimal solution and finishing, and if the termination condition is not met, performing the next step.

Step 3: and (4) carrying out Canopy-Kmeans clustering, wherein Canopy and K-means are classical clustering algorithms, and in the Canopy-Kmeans clustering method, firstly carrying out primary clustering by using a Canopy algorithm, and then clustering the population by using a K-means algorithm.

Step 4: judging whether a disturbance condition is met, wherein the disturbance condition is a disturbance factor B based on the number of clusters, if not, judging whether the number of clusters is less than 3, wherein the number of clusters can be understood as the number of tasks, if so, mc is mc +1, m is the number of tasks, c is the number of grids divided by one dimension,

wherein c is a positive integer, N is the number of the population, M is the number of the targets, and Step8 is skipped; if the disturbance condition is satisfied, mc is set to 0, and the next step is performed.

Step 5: again, Canopy-Kmeans clustering was performed.

Step 6: will this iteration

Is set to 2, wherein

z is a random number between 0 and 1, d is the current number of iterations, d _max Is the maximum number of iterations.

Step 7: judgment of

Taking the value of [0, n]If yes, the different-group crossing is performed, and if not, the same-group crossing is performed.

Step 8: and (5) carrying out mutation.

Step 9: decoding is performed and jumps to Step2, and the loop is executed until the optimal solution set is output.

It can be understood that the preliminary identification result output by the event detection module is input into the task planner, and the task planner performs task planning by using the multi-objective clustering genetic task planning algorithm.

Compared with the prior art, the multifunctional intelligent robot system for home-based care for the aged has the beneficial effects that:

(1) in the household indoor environment, because the household and the electrical equipment are more, the use condition and the indoor behavior action of each household and electrical equipment can reflect the behavior habit of indoor resident people. Various fixed sensors (RSS sensing network sensing platforms) are arranged to collect various health and behavior data of resident people, and health conditions and abnormal behaviors of the old people are predicted through a multi-correlation data fusion analysis algorithm.

(2) The distributed intelligent environment is utilized to collect home environment data, the physiological health data and the behavior data of the old people, the current state and the demand of the old people are analyzed, the intelligent network nodes are utilized to transmit the data to the intelligent robot, the defects of environment perception and demand perception of the mobile robot are overcome, and the efficiency and the reliability of task execution of the robot are improved.

(3) And determining a task outline of the robot in the scene according to the intelligent sensing network and the robot capability, and constructing a task planning system model of robot cognition and planning based on machine learning. According to the two dynamic conditions of environment change and task change, the overall framework of the online re-planning system is designed, the two conditions are analyzed respectively, and then a multi-task scheduling algorithm is designed to achieve multi-task scheduling.

It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A multifunctional intelligent nursing robot system for home-based care is characterized by comprising an RSS sensing network sensing platform, a data acquisition and gathering transmission unit, a server data processing and task planning platform and a CareBot robot platform;

the RSS sensing network sensing platform comprises a plurality of fixed sensors and is used for sensing behavior data, physiological health data and environmental condition data of the living old;

the data acquisition and summary transmission unit is used as a sensor transmission gateway and is used for summarizing and transmitting the behavior data, the physiological health data and the environmental condition data of the living old, which are sensed by all the fixed sensors, to the server data processing and task planning platform;

the server data processing and task planning platform is used for processing and identifying the behavior data, the physiological health data and the environmental condition data of the living old people to obtain a primary identification result, generating a task instruction according to the primary identification result and issuing the task instruction to the CareBot robot platform; adjusting the preliminary recognition result according to the perception result fed back by the CareBot robot platform;

the CareBot robot platform is provided with a plurality of sensors and is used for executing corresponding tasks according to the task instructions, sensing the behavior data, the physiological health data and the environmental condition data of the old at home again through the plurality of sensors, and feeding back the sensing result to the server data processing and task planning platform; and according to the task instruction, realizing assistance to the old at home.

2. The caregiving robot system of claim 1, wherein the RSS sensing network aware platform comprises a behavior aware portion, a physiological aware portion, and an environmental condition aware portion;

the behavior sensing part comprises a depth camera, a door sensor and a human body sensor and is used for recording daily behavior habits of the old at home and fall detection of the old;

the physiological sensing part comprises an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent glucometer and an intelligent weighing scale and is used for detecting the daily physical condition of the old;

the environment condition sensing part comprises a temperature and humidity sensor, a water sensor, a gas sensor, a fire sensor, a safety SOS alarm and an intelligent bracelet, wherein the temperature and humidity sensor, the water sensor, the gas sensor and the fire sensor are used for detecting the condition of a home environment; SOS alarm and intelligent bracelet are used for guaranteeing old man's autonomous alarm under the condition of staying at home or going out.

3. The care robot system of claim 1, wherein the data collection and summary transmission unit connects all sensors of the RSS sensor network sensing platform by using a Zigbee intelligent gateway, summarizes the sensing data of all sensors, and transmits the sensing data to the server data processing and task planning platform based on internet technology, the sensing data including household elderly behavior data, physiological health data, and environmental condition data.

4. The career robot system of claim 1, wherein the server data processing and mission planning platform comprises a mission planner, a database, an event detection module, and an execution instruction conversion module;

the database is used for storing the behavior data, physiological health data and environmental condition data of the family old people sensed by each sensor;

the event detection module is used for detecting and identifying the behavior data, the physiological health data and the environmental condition data of the living old people sensed by all the fixed sensors, and identifying the behaviors, the requirements and the environmental conditions of the old people to obtain a primary identification result;

the task planner is used for planning a task according to the preliminary identification result and generating a task instruction;

and the execution instruction conversion module is used for converting the generated task instruction into an instruction which can be identified by the CareBot robot platform.

5. The caregiving robot system of claim 1, wherein the CareBot robot platform comprises a perception layer, an interaction layer, a SLAM layer, and an actuator;

the SLAM layer is used for generating a planning path of the CareBot robot according to the received task instruction;

the executing mechanism is used for moving to a corresponding position according to the planned path;

the sensing layer comprises a plurality of sensors, moves along with the movement of the CareBot robot, is used for sensing the behavior data, the physiological health data and the environmental condition data of the living old again at the corresponding positions, and feeds back the sensing result to the server data processing and task planning platform;

the interaction layer comprises an airborne voice module and a display module and is used for carrying out emotion interaction with the old and carrying out video conversation with family members in a home scene.

6. The career robot system of claim 5, wherein the SLAM layer and the executive layer act on a robot movement chassis and camera elevation and side drawers and water volume management, respectively.

7. The robot system for nursing home and care is characterized in that the actuating mechanism is provided with a sensor box, an airborne camera, a human body detector, a fire sensor and a gas sensor are loaded in the sensor box, the sensor box can be operated in three degrees of freedom including lifting, pitching and left-right, and therefore the robot can detect and check the robot in a moving scene at 360 degrees without dead angles.

8. The caregiving robot system of claim 7, further comprising a tablet remote terminal platform comprising a robot operating module, a data reading module, a sensor operating module and an information recording module;

the robot operation module is used for the old, the children or community staff to remotely control the robot, so that the robot can move indoors to check indoor conditions;

the sensor control module is used for the old, children and community staff to remotely control the onboard cameras and various sensors to check and detect the indoor 360-degree dead angle-free state;

the data reading module is used for the old, the children and community staff to check the current old condition, the indoor condition and the robot task execution condition;

and the information recording module is used for recording the sensing result and the operation behavior of each sensor.

9. The caregiving robot system of claim 4, wherein the task planner is configured to plan a task according to the preliminary recognition result and generate a task instruction, and the task planner comprises:

and the task planner plans the tasks by adopting a multi-target clustering genetic task planning algorithm according to the primary identification result to generate a task instruction.

10. The career robot system of claim 9, wherein the task planner is configured to plan tasks using a multi-objective clustering genetic task planning algorithm based on the preliminary identification result to generate task instructions, comprising:

step 1: initializing a population and various parameters, wherein the various parameters comprise maximum iteration frequency setting, population scale, cross rate and variation probability;

step 2: judging whether a termination condition is met, if so, outputting an optimal solution and ending, and if not, executing Step 3;

step 3: carrying out Canopy-Kmeans clustering;

step 4: judging whether a disturbance condition is met, wherein the disturbance condition is a disturbance factor B based on the number of clusters, if not, judging whether the number of clusters is less than 3, wherein the number of clusters can be understood as the number of tasks, if so, mc is mc +1, m is the number of tasks, c is the number of grids divided by one dimension,

wherein c is a positive integer, N is the number of the population, M is the number of the targets, and Step8 is skipped; if the disturbance is satisfiedIf the condition is satisfied, mc is set to 0, and Step5 is executed;

step 4: judging whether disturbance conditions are met or not, if not, judging whether the clustering number is less than 3 or not, if so, determining that mc is mc +1, m is the task number, and jumping to Step 8; if the disturbance condition is satisfied, mc is set to 0, and Step5 is executed;

step 5: thirdly, carrying out Canopy-Kmeans clustering;

step 6: will this iteration

Is set to 2, wherein

z is a random number between 0 and 1, d is the current number of iterations, d _max Is the maximum number of iterations;

step 7: judgment of

Taking the value of [0, n]If yes, carrying out different-group crossing; if not, carrying out same-group crossing;

step 8: carrying out mutation;

step 9: decoding is performed and jumps to Step2, and the loop is executed until the optimal solution set is output.

Images