A multifunctional intelligent home care robot system for the elderly

Abstract

The present invention provides a multifunctional intelligent home care robot system, including an RSS sensing network perception platform, a data acquisition, aggregation and transmission unit, a server data processing and task planning platform, and a CareBot robot platform. The present invention realizes the integration of the robot into the home care scenario, deeply integrates the smart home sensing network with the robot, makes up for the deficiencies of the robot's information perception ability and the task assistance ability of the sensing network, and constructs a task planner on the server cloud for complex tasks to solve the problem of robot task execution in complex task scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of elderly care robots, and more specifically, to a multi-functional intelligent home elderly care robot system. Background Art

[0002] Due to the increasing work intensity and pressure of people, they are unable to take good care of the elderly who need care and cannot always be by the side of the elderly. Once an unexpected abnormal situation occurs to the elderly, it is often very difficult to obtain timely assistance and treatment. In recent years, driven by the rapid development of technologies such as computers and communications and the trend of population aging, more and more researchers have started to research related technologies of service robots, making them gradually enter service places such as families, restaurants, and offices, especially having important significance for the field of home elderly care.

[0003] However, the existing intelligent elderly care robots have a relatively narrow working field. Usually, they can only provide assistance services with relatively single functions and narrow application ranges for the elderly, and they are expensive, unable to take into account the daily living assistance and safety problem detection of the elderly indoors. Summary of the Invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a multi-functional intelligent home elderly care robot system, including an RSS sensing network perception platform, a data acquisition, aggregation and transmission unit, a server data processing and task planning platform, and a CareBot robot platform;

[0005] The RSS sensing network perception platform includes a plurality of fixed sensors for perceiving the behavior data, physiological health data and environmental condition data of the elderly at home;

[0006] The data acquisition, aggregation and transmission unit serves as a sensor transmission gateway for aggregating and transmitting the behavior data, physiological health data and environmental condition data of the elderly at home perceived by all fixed sensors to the server data processing and task planning platform;

[0007] The server data processing and task planning platform is used for processing and identifying the behavior data, physiological health data and environmental condition data of the elderly at home to obtain a preliminary identification result, generating a task instruction according to the preliminary identification result, and sending the task instruction to the CareBot robot platform; and adjusting the preliminary identification result according to the perception result feedback by the CareBot robot platform;

[0008] Multiple sensors are provided on the CareBot robot platform, which are used to execute corresponding tasks according to the task instructions, sense the behavior data, physiological health data, and environmental condition data of the elderly at home again through the multiple sensors provided, and feed the sensing results back to the server data processing and task planning platform; and assist the elderly at home according to the task instructions.

[0009] Based on the above technical solutions, the present invention can also be improved as follows.

[0010] Optionally, the RSS sensing network perception platform includes a behavior perception part, a physiological perception part, and an environmental condition perception part;

[0011] The behavior perception part includes a depth camera, a door magnetic sensor, and a human body sensor, which are used to record the daily behavior habits of the elderly at home and detect the fall of the elderly;

[0012] The physiological perception part includes an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent blood glucose meter, and an intelligent weighing scale, which are used to detect the daily physical condition of the elderly;

[0013] The environmental condition perception part includes a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, and an SOS alarm and an intelligent bracelet for safety. The temperature and humidity sensor, the water immersion sensor, the gas sensor, and the fire sensor are used to detect the environmental condition of the home; the SOS alarm and the intelligent bracelet are used to ensure that the elderly can call for help independently when at home or going out.

[0014] Optionally, the data acquisition, aggregation, and transmission unit uses a Zigbee smart gateway to connect all the sensors of the RSS sensing network perception platform, aggregate the sensing data of all the sensors. The sensing data includes the behavior data, physiological health data, and environmental condition data of the elderly at home, and transmits the sensing data to the server data processing and task planning platform based on Internet technology.

[0015] 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;

[0016] The database is used to store the behavior data, physiological health data, and environmental condition data of the elderly at home sensed by each sensor;

[0017] The event detection module is used to detect and identify the behavior data, physiological health data, and environmental condition data of the elderly at home sensed by all fixed sensors, identify the behavior of the elderly, the needs of the elderly, and the environmental condition, and obtain a preliminary identification result;

[0018] The task planner is used to plan tasks according to the preliminary recognition results and generate task instructions.

[0019] The execution instruction conversion module is used to convert the generated task instructions into instructions that can be recognized by the CareBot robot platform.

[0020] Optionally, the CareBot robot platform includes a perception layer, an interaction layer, a SLAM layer, and an execution mechanism.

[0021] The SLAM layer is used to generate a planned path for the CareBot robot according to the received task instructions.

[0022] The execution mechanism is used to move to the corresponding position according to the planned path.

[0023] The perception layer includes multiple sensors that move as the CareBot robot moves, and is used to perceive the behavior data, physiological health data, and environmental condition data of the elderly at home again at the corresponding position, and feedback the perception results to the server data processing and task planning platform.

[0024] The interaction layer includes an on-board voice module and a display module, and is used for emotional interaction with the elderly and video conversations with family members in the home scenario.

[0025] Optionally, the SLAM layer and the execution layer respectively act on the robot mobile chassis, camera lifting, both side drawers, and water volume management.

[0026] Optionally, the execution mechanism is provided with a sensor box, and the sensor box is loaded with an on-board camera, a human body detector, a fire sensor, and a gas sensor. The sensor box can perform operations in three degrees of freedom: lifting, pitching, and yawing, to achieve 360° dead-angle-free detection and viewing of the robot in the moving scenario.

[0027] Optionally, it further includes a tablet remote terminal platform, which includes a robot operation module, a data reading module, a sensor operation module, and an information recording module.

[0028] The robot operation module is used for the children of the elderly or community staff to remotely control the robot, so that the robot can move indoors to view the indoor situation.

[0029] The sensor control module is used for the children of the elderly and community staff to remotely control the on-board camera and various sensors for 360° dead-angle-free viewing and detection indoors.

[0030] The data reading module is used for the elderly's children and community staff to view the current status of the elderly, the indoor situation, and the execution status of the robot tasks;

[0031] The information recording module is used to record the perception results and operation behaviors of each sensor.

[0032] Optionally, the task planner is used to plan tasks according to the preliminary recognition results and generate task instructions, including:

[0033] The task planner plans tasks according to the preliminary recognition results and generates task instructions by using a multi-objective clustering genetic task planning algorithm.

[0034] Optionally, the task planner plans tasks according to the preliminary recognition results and generates task instructions by using a multi-objective clustering genetic task planning algorithm, including:

[0035] Step1: Initialize the population and various parameters. The various parameters include the maximum number of iterations, population size, crossover rate, and mutation probability;

[0036] Step2: Determine whether the termination condition is satisfied. If the termination condition is satisfied, output the optimal solution and end. If not, execute Step3;

[0037] Step3: Perform Canopy-Kmeans clustering;

[0038] Step4: Determine whether the perturbation condition is satisfied. The perturbation condition is the perturbation factor B based on the number of clusters. If not, determine whether the number of clusters is less than 3. Here, the number of clusters can be understood as the number of tasks. If so, mc = mc + 1, where m is the number of tasks and c is the number of grids divided in one dimension, where c is a positive integer, N represents the number of populations, M represents the number of objectives, and jump to Step8; if the perturbation condition is satisfied, set mc to 0 and execute Step5;

[0039] Step5: Perform Canopy-Kmeans clustering again;

[0040] Step6: Set the of this iteration to 2, where z is a random number between 0 and 1, d is the current number of iterations, and d max is the maximum number of iterations;

[0041] Step7: Determine takes values in [0, n]. If so, perform cross-group crossover; if not, perform within-group crossover;

[0042] Step 8: Perform mutation;

[0043] Step 9: Perform decoding and jump to Step 2, and loop in sequence until the optimal solution set is output.

[0044] A multifunctional intelligent home care robot system provided by the present invention includes an RSS sensing network perception platform, a data acquisition, aggregation and transmission unit, a server data processing and task planning platform, and a CareBot robot platform. The present invention realizes integrating the robot into the home care scenario, deeply integrating the smart home sensing network with the robot, making up for the deficiencies in the robot's information perception ability and the task assistance ability of the sensing network, etc. And for complex tasks, a task planner is built on the server cloud to solve the problem of robot task execution in complex task scenarios. Description of the Drawings

[0045] Figure 1 It is a schematic diagram of the real scenario of the multifunctional intelligent home care robot system;

[0046] Figure 2 It is a schematic structural diagram of a multifunctional intelligent home care robot system provided by the present invention;

[0047] Figure 3 It is a schematic diagram of the overall structure of the multifunctional intelligent home care robot system provided by the present invention. Detailed Embodiments

[0048] To make the objectives, 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 accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. In addition, the technical features in each embodiment or a single embodiment provided by the present invention can be combined with each other arbitrarily to form a feasible technical solution. This combination is not restricted by the order of steps and / or the structural composition mode, but must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0049] The present invention intends to study a care robot system that can be integrated with an intelligent home environment system and an intelligent elderly care service platform, and construct a comprehensive intelligent elderly care system with intelligent robots as the main body, integrating Internet + technologies such as artificial intelligence, big data, Internet of Things, and robots, aiming to create a comprehensive intelligent elderly care system for communities, institutions, and homes that integrates health, life, and safety, and solve three problems of elderly people living at home: 1) Realize the care function for the elderly living at home at low cost, so that more elderly people living at home can enjoy more intelligent home-based elderly care services. 2) Utilize the mobility characteristics of service robots to solve the problem that in a conventional smart home environment, intelligent detection cannot be carried out in the entire indoor range, and strongly couple and cooperate the intelligent robot with the smart home environment to meet the effective allocation and adaptation of daily and abnormal service needs. 3) Utilize Internet big data and remote teleoperation technology to improve the service efficiency of care robots and enhance the service effectiveness of robots. The Figure 1 is a system schematic diagram used to show the brief flow chart of the entire system, as Figure 1 shown. The RSS system is fully called Robot Support System, which aims to integrate a robot system into a smart home environment, enabling the smart home to not only have strong sensing capabilities but also strong execution capabilities; the system deeply arranges various sensors in the home environment of the elderly, collects the physiological data of the elderly's behavior and environmental safety data, and through long-term data collection and a multi-correlation fusion algorithm based on machine learning, identifies the behavior, needs, physical health, and environmental safety status of the elderly, and then transmits the identification results to the task planner for task planning, allowing the robot to act as an execution agency to help the elderly complete their daily life. At the same time, children and community staff can also remotely view the real-time situation of the elderly, ensuring the safety of the elderly living alone, having company in their solitary life without loneliness, and being able to communicate face-to-face remotely with their children.

[0050] Figure 2 is a structural schematic diagram of a multifunctional intelligent home-based elderly care robot system provided by the present invention. Refer to Figure 2 , this elderly care robot system includes an RSS sensing network perception platform, a data collection, aggregation, and transmission unit, a server data processing and task planning platform, and a CareBot robot platform.

[0051] Among them, the RSS sensing network perception platform includes multiple fixed sensors for perceiving the behavior data, physiological health data, and environmental condition data of the elderly living at home. The data acquisition, aggregation, and transmission unit serves as a sensor transmission gateway for aggregating and transmitting the behavior data, physiological health data, and environmental condition data of the elderly living at home perceived by all fixed sensors to the server data processing and task planning platform; the server data processing and task planning platform is used to process and identify the behavior data, physiological health data, and environmental condition data of the elderly living at home to obtain a preliminary identification result, generate a task instruction based on the preliminary identification result, and send the task instruction to the CareBot robot platform; and adjust the preliminary identification result according to the perception result feedback by the CareBot robot platform; multiple sensors are provided on the CareBot robot platform for performing corresponding tasks according to the task instruction, perceiving the behavior data, physiological health data, and environmental condition data of the elderly living at home again through the provided multiple sensors, and feeding back the perception result to the server data processing and task planning platform; and realizing the assistance to the elderly living at home according to the task instruction.

[0052] It can be understood that the present invention provides a smart elderly care service robot system that deeply integrates robot technology and smart home Internet of Things technology to solve problems such as the health protection, emotional companionship, home environment safety, and daily living of existing elderly people living alone. The elderly care robot system mainly includes an RSS sensing network perception platform, a data acquisition, aggregation, and transmission platform, a server data processing and task planning platform, and a CareBot robot platform. The RSS sensing network perception platform includes multiple perception modules for perceiving the behavior data, health status data, and environmental status information of the elderly living at home; the data acquisition, aggregation, and transmission platform includes a sensing network intelligent gateway platform, and the RSS sensing network perception platform transmits the perceived data of the elderly living at home and the home environment data to the Internet server data processing and task planning platform through the data acquisition, aggregation, and transmission platform; the server data processing and task planning platform identifies the perception result to obtain an initial identification result, and generates a task instruction based on the initial identification result; the CareBot robot platform is used to execute the task instruction from the server data processing and task planning platform and feed back the information perceived by the robot to the server data processing and task planning platform, so that the server data processing and task planning platform adjusts the initial identification result according to the perception result of the CareBot robot platform again, and adjusts the generated task instruction according to the adjusted identification result.

[0053] The present invention realizes the integration of robots into the home-based elderly care scenario, deeply integrating the smart home sensing network with robots to make up for the deficiencies in the information perception ability of robots and the task assistance ability of the sensing network. For complex tasks, a task planner is built on the server cloud to solve the problem of robot task execution in complex task scenarios.

[0054] Among them, Figure 3 FIG. is a schematic diagram of the entire structural block diagram of the elderly care robot system. As an embodiment, the RSS sensing network perception platform includes a behavior perception part, a physiological perception part, and an environmental condition perception part. The behavior perception part includes a depth camera, a door magnetic sensor, and a human body sensor, which are used to record the daily behavior habits of the elderly at home and detect the fall of the elderly; the physiological perception part includes a smart sleep detector, a smart sphygmomanometer, a smart blood glucose meter, and a smart weighing scale, which are used to detect the daily physical condition of the elderly; the environmental condition perception part includes a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, and a safety SOS alarm and a smart bracelet. The temperature and humidity sensor, the water immersion sensor, the gas sensor, and the fire sensor are used to detect the home environmental condition; the SOS alarm and the smart bracelet are used to ensure that the elderly can make an independent alarm when at home or going out.

[0055] It can be understood that the RSS sensing network perception platform is used to collect the behavior data, physiological health data, and environmental condition data of the elderly; the RSS sensing network perception platform mainly includes a behavior perception part, a physiological condition perception part, and an environmental condition perception part. The behavior perception part has a depth camera, a door magnetic sensor, and a human body sensor, which are used to record the daily behavior habits of the elderly and detect the fall of the elderly, and transmit information in time when the elderly have an accident such as a fall; the physiological perception part has a smart sleep detector, a smart sphygmomanometer, a smart blood glucose meter, and a smart weighing scale for daily detection of the physical condition of the elderly, and at the same time formulates a suitable care plan for the elderly; the environmental condition perception has a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, and a safety SOS alarm and a smart bracelet. Such sensors are used to detect the home environmental condition and feedback the situation to the server background in time when a dangerous situation occurs; the SOS alarm and the smart bracelet are used to ensure that the elderly can make an independent alarm when at home or going out.

[0056] As an example, the data acquisition, aggregation, and transmission platform is used as a sensor transmission gateway. All sensor data is aggregated through the intelligent gateway and jointly transmitted to the server data processing and task planning platform. Among them, the data acquisition, aggregation, and transmission platform collects various types of data from the RSS platform. In the home scenario, the Zigbee intelligent gateway technology is used to connect all sensors, thus saving the cost of building the Internet network channel, and using Internet technologies such as 5G to transmit the data to the server in a timely and effective manner.

[0057] As an example, 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 to store the behavior data, physiological health data, and environmental condition data of the elderly at home sensed by each sensor; the event detection module is used to detect and identify the behavior data, physiological health data, and environmental condition data of the elderly at home sensed by all fixed sensors, identify the behavior of the elderly, the needs of the elderly, and the environmental conditions, and obtain a preliminary identification result; the task planner is used to plan tasks according to the preliminary identification result and generate task instructions; the execution instruction conversion module is used to convert the generated task instructions into instructions that the CareBot robot platform can recognize.

[0058] It can be understood that the server data processing and task planning platform consists of a task planner, a database, an event detection module, and an execution instruction conversion module, and receives various types of sensor data from the data acquisition, aggregation, and transmission platform. The event detection module processes the various types of sensor data, processes and identifies the behavior of the elderly, the needs of the elderly, and the environmental conditions, and obtains a preliminary identification result, which is then used as the input of the task planner. The output of the task planner is a task-level instruction. The event detection module includes the identification of the behavior of the elderly, the identification of the needs of the elderly, and the identification of the environmental conditions, and inputs events for the planner. Among them, the identification of the behavior of the elderly is a vision detection algorithm based on deep learning, the identification of the needs of the elderly is a demand perception algorithm based on machine learning, and the perception of the home environment is a multi-sensor fusion algorithm with multiple correlations. The execution instruction conversion module converts the output event of the task planner into specific instructions that the SLAM layer of the robot movement mechanism and the robot execution mechanism can recognize and execute.

[0059] As an example, the CareBot robot platform includes a perception layer, an interaction layer, a SLAM layer, and an actuator; the SLAM layer is used to generate a planned path for the CareBot robot according to the received task instructions; the actuator is used to move to the corresponding position according to the planned path; the perception layer includes multiple sensors that move as the CareBot robot moves, and is used to perceive the behavior data, physiological health data, and environmental condition data of the elderly at home again at the corresponding position, and feedback the perception results to the server data processing and task planning platform; the interaction layer includes an on-board voice module and a display module, and is used to perform emotional interaction with the elderly and video conversations with family members in a home scenario.

[0060] It can be understood that the CareBot robot platform consists of a perception layer, an interaction layer, a SLAM layer, and an actuator. Among them, the SLAM layer and the actuator receive specific execution instructions from the server data processing and task planning platform and feedback the execution results to the task planner. The SLAM layer is used for positioning and navigation as well as path planning, acting on the robot's mobile chassis to move the robot. The actuator has a sensor box, which is used to load an on-board camera, a human detector, a fire sensor, and a gas sensor. The sensor box can perform three degrees of freedom operations, such as lifting, pitching, and looking left and right, to achieve 360° dead-angle-free detection and viewing in the robot's moving scenario. The actuator acts on the camera lifting, the two drawers on both sides, and the water volume management. The perception layer has an on-board camera, a human detector, a fire sensor, and a gas sensor. The sensor data perception information is transmitted as an input to the task planner to the server data processing and task planning platform. Among them, when an accident such as a fall occurs to the elderly, the human detector can detect the abnormality and transmit the information to the background server in a timely manner. When an accident such as a fire occurs in the room, the fire sensor and the gas sensor can detect the environmental abnormality in a timely manner and transmit the information to the background server in a timely manner for further processing by the server. The interaction layer (8) has an on-board voice module and a display module, and is used to perform emotional interaction with the elderly and video conversations with family members in a home scenario.

[0061] As an embodiment, the elderly care robot system also includes a tablet computer remote terminal platform, including 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 elderly's children or community workers to remotely control the robot, so that the robot moves indoors to view the indoor situation; the sensor control module is used for the elderly's children and community workers to remotely control the onboard camera and various sensors to view and detect indoors at 360° without blind spots; the data reading module is used for the elderly's children and community workers to view the current elderly's condition, indoor conditions and robot task execution; the information recording module is used to record the perception results and operation behaviors of each sensor.

[0062] It can be understood that the tablet computer remote terminal platform is composed of a robot operation module, a data reading module, a sensor control module and an information recording module. Among them, the robot operation module is used for the elderly's children or community workers to remotely control the robot, so that the robot can move indoors to view the indoor conditions; the sensor control module is used for the elderly's children and community workers to remotely control the onboard camera and various sensors to perform 360° blind-angle viewing and detection indoors; the data reading module and the information recording module are used for the elderly's children and community workers to check the current condition of the elderly, indoor conditions and the execution of the robot's tasks to ensure that the elderly are in a safe situation.

[0063] It should be noted that the task planner in the server data processing and task planning platform, as the core of this system, needs to process and plan various events. The task planner of this system adopts a multi-objective clustering genetic task planning algorithm. Home service robots need to perform various complex tasks in home scenes. These tasks include daily safety inspections, daily life assistance, daily environmental protection and emergency handling. They are divided into daily tasks and emergency tasks. The execution process of such tasks is the superposition of NP-hard problems. Its solution space is huge and complex. It is difficult for precise algorithms to obtain the optimal solution within an acceptable time. Heuristic algorithms are more suitable for this type of problem. Genetic algorithm is a heuristic algorithm with strong global search capabilities and good robustness. It has been widely used in the field of multi-objective optimization. Crossover is an important operation in genetic algorithms, which largely determines the performance of the algorithm, while the original crossover operation has a certain degree of randomness and blindness. Clustering is a commonly used method in the field of data mining. It can effectively mine the potential connections between data objects and can be used to extract the distribution characteristics of individuals in the decision space. According to the system situation, the situations that the robot needs to perform are classified as follows:

[0064] (1) Daily safety inspections: cleaning of the living room, kitchen, bedroom, and bathroom; disinfection of the living room, kitchen, bedroom, and bathroom; removal of water stains in the living room, kitchen, bedroom, and bathroom; inspection for safety hazards in the living room, bedroom, kitchen, and bathroom.

[0065] (2) Daily life assistance: health management (measuring blood pressure), health management (measuring body temperature), daily reminders (delivering water and medicine), watering flowers.

[0066] (3) Assistance in special situations: emergency lighting during power outages, guiding the elderly to get up at night, assisting the elderly when they fall, extinguishing fires in case of emergencies.

[0067] (4) Special situations of equipment: insufficient robot battery, insufficient robot water volume.

[0068] (5) The entire task is divided into daily tasks and abnormal tasks, especially when the response requirements for the algorithm are extremely high in emergency situations.

[0069] The proposed multi-objective clustering genetic task planning algorithm has the following steps:

[0070] Step1: Initialize the population and various parameters. Set the maximum number of iterations to 200, the population size to 150, the crossover rate to 0.85, and the mutation probability to 0.5.

[0071] Step2: Determine whether the termination condition is met. The termination condition is the maximum number of iterations. If the termination condition is met, output the optimal solution and end. If not, proceed to the next step.

[0072] Step3: Perform Canopy-Kmeans clustering. Canopy and K-means are classical clustering algorithms. In the Canopy-Kmeans clustering method, first use the Canopy algorithm for preliminary clustering, and then use the K-means algorithm to cluster the population.

[0073] Step4: Determine whether the perturbation condition is met. The perturbation condition is the perturbation factor B based on the number of clusters. If not, determine whether the number of clusters is less than 3. Here, the number of clusters can be understood as the number of tasks. If so, mc = mc + 1, where m is the number of tasks and c is the number of grids divided in one dimension. where c is a positive integer, N represents the number of the population, M represents the number of objectives, and jump to Step8; if the perturbation condition is met, set mc to 0 and proceed to the next step.

[0074] Step5: Perform Canopy-Kmeans clustering again.

[0075] Step6: Set the of this iteration to 2, where z is a random number between 0 and 1, d is the current number of iterations, and d max is the maximum number of iterations.

[0076] Step7: Judge If the value is in the range of [0, n], perform cross-group crossover; otherwise, perform in-group crossover.

[0077] Step8: Perform mutation.

[0078] Step9: Perform decoding and jump to Step2, and loop in turn until the optimal solution set is output.

[0079] It can be understood that the preliminary recognition result output by the event detection module is input into the task planner, and the task planner uses the above multi-objective clustering genetic task planning algorithm for task planning.

[0080] A multi-functional intelligent home care robot system provided by an embodiment of the present invention has the following beneficial effects compared with the prior art:

[0081] (1) In the home indoor environment, due to the large number of home furnishings and electrical appliances, the usage situation of each home and electrical appliance and the indoor behavior actions can all reflect the behavior habits of the indoor residents. By arranging various fixed sensors (RSS sensing network perception platform), various health and behavior data of the residents are collected, and the health status and abnormal behaviors of the elderly are predicted through the multi-correlation data fusion analysis algorithm.

[0082] (2) Using the distributed intelligent environment, home environment data, the physiological health data and behavior data of the elderly are collected, the current state and needs of the elderly are analyzed, and the data is transmitted to the intelligent robot through the intelligent network node, making up for the deficiencies of the mobile robot in environmental perception and demand perception, and improving the efficiency and reliability of the robot task execution.

[0083] (3) According to the intelligent sensing network and the robot capabilities, the task outline of the robot in this scenario is determined, and a task planning system model for robot cognition and planning based on machine learning is built. According to the two dynamic situations of environmental change and task change, the overall framework of the online replanning system is designed, and these two situations are analyzed respectively, and then a multi-task scheduling algorithm is designed to realize the scheduling of multiple tasks.

[0084] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0086] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0087] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that realizes the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, thereby providing the steps for realizing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0089] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A multi-functional intelligent home care robot system for the elderly, characterized in that, It includes an RSS sensing network perception platform, a data acquisition, aggregation and transmission unit, a server data processing and task planning platform, and a CareBot robot platform; The RSS sensing network perception platform includes multiple fixed sensors for perceiving the behavior data, physiological health data and environmental condition data of the elderly at home; The data acquisition, aggregation and transmission unit serves as a sensor transmission gateway for aggregating and transmitting the behavior data, physiological health data and environmental condition data of the elderly at home perceived by all fixed sensors to the server data processing and task planning platform; The server data processing and task planning platform is used to process and identify the behavior data, physiological health data and environmental condition data of the elderly at home to obtain a preliminary identification result, generate a task instruction according to the preliminary identification result, and send the task instruction to the CareBot robot platform; and adjust the preliminary identification result according to the perception result feedback by the CareBot robot platform; Multiple sensors are arranged on the CareBot robot platform for performing corresponding tasks according to the task instruction, perceiving the behavior data, physiological health data and environmental condition data of the elderly at home again through the arranged multiple sensors, and feeding back the perception result to the server data processing and task planning platform; and realizing the assistance to the elderly at home according to the task instruction.

2. The multifunctional intelligent home care robot system according to claim 1, wherein, The RSS sensing network perception platform includes a behavior perception part, a physiological perception part and an environmental condition perception part; The behavior perception part includes a depth camera, a door magnetic sensor and a human body sensor for recording the daily behavior habits of the elderly at home and detecting the fall of the elderly; The physiological perception part includes an intelligent sleep detector, an intelligent sphygmomanometer, an intelligent blood glucose meter and an intelligent weighing scale for detecting the daily physical condition of the elderly; The environmental condition perception part includes a temperature and humidity sensor, a water immersion sensor, a gas sensor, a fire sensor, an SOS alarm for safety and an intelligent bracelet. The temperature and humidity sensor, the water immersion sensor, the gas sensor and the fire sensor are used to detect the environmental condition of the home; the SOS alarm and the intelligent bracelet are used to ensure the elderly's independent alarm when at home or going out.

3. The multifunctional intelligent home care robot system according to claim 1, characterized in that, The data acquisition, aggregation and transmission unit uses a Zigbee smart gateway to connect all the sensors of the RSS sensing network perception platform, aggregate the perception data of all the sensors. The perception data includes the behavior data, physiological health data and environmental condition data of the elderly at home, and transmits the perception data to the server data processing and task planning platform based on Internet technology.

4. The multifunctional intelligent home care robot system according to claim 1, characterized in that 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 to store the behavior data, physiological health data and environmental condition data of the elderly at home perceived by each sensor; The event detection module is used to detect and identify the behavior data, physiological health data, and environmental condition data of the elderly at home sensed by all fixed sensors, identify the behavior of the elderly, the needs of the elderly, and the environmental conditions, and obtain a preliminary identification result; The task planner is used to plan tasks according to the preliminary identification result and generate task instructions; The execution instruction conversion module is used to convert the generated task instructions into instructions that can be recognized by the CareBot robot platform.

5. The multi-functional intelligent home care robot system according to claim 1, characterized in that, The CareBot robot platform includes a sensing layer, an interaction layer, a SLAM layer, and an actuator; The SLAM layer is used to generate a planned path for the CareBot robot according to the received task instructions; The actuator is used to move to the corresponding position according to the planned path; The sensing layer includes multiple sensors that move as the CareBot robot moves, and is used to sense the behavior data, physiological health data, and environmental condition data of the elderly at home again at the corresponding position, and feedback the sensing results to the server data processing and task planning platform; The interaction layer includes an on-board voice module and a display module, and is used to conduct emotional interaction with the elderly and video conversations with family members in the home scenario.

6. The multifunctional intelligent home care robot system according to claim 5, characterized in that The SLAM layer and the actuator respectively act on the robot mobile chassis, camera lifting, both side drawers, and water volume management.

7. The multifunctional intelligent home care robot system according to claim 5, characterized in that, The actuator is provided with a sensor box, and the sensor box is loaded with an on-board camera, a human detector, a fire sensor, and a gas sensor. The sensor box can perform operations in three degrees of freedom: lifting, pitching, and yawing, to achieve 360° dead-angle-free detection and viewing of the robot in the moving scenario.

8. The multifunctional intelligent home care robot system according to claim 7, characterized in that, It further includes a tablet remote terminal platform, which includes a robot operation module, a data reading module, a sensor control module, and an information recording module; The robot operation module is used for the children of the elderly or community workers to remotely control the robot, so that the robot can move indoors to view the indoor situation; The sensor control module is used for the children of the elderly and community workers to remotely control the on-board camera and various sensors for 360° dead-angle-free viewing and detection indoors; The data reading module is used for the children of the elderly and community workers to view the current situation of the elderly, the indoor situation, and the task execution situation of the robot; The information recording module is used to record the sensing results and operation behaviors of each sensor.

9. The multifunctional intelligent home care robot system according to claim 4, wherein, The task planner is used to plan tasks according to the preliminary identification result and generate task instructions, including: The task planner plans the tasks according to the preliminary identification result and generates task instructions by using a multi-objective clustering genetic task planning algorithm.

10. The multifunctional intelligent home-based elderly care robot system according to claim 9, characterized in that, The task planner plans the tasks according to the preliminary identification result and generates task instructions by using a multi-objective clustering genetic task planning algorithm, including: Step1: Initialize the population and various parameters. The various parameters include the maximum number of iterations, population size, crossover rate, and mutation probability; Step 2: Determine whether the termination condition is met. If the termination condition is met, output the optimal solution and end. If not, execute Step 3; Step 3: Perform Canopy-Kmeans clustering; Step 4: Determine whether the perturbation condition is satisfied. The perturbation condition is the perturbation factor B based on the number of clusters. If not satisfied, determine whether the number of clusters is less than 3. Here, the number of clusters is understood as the number of tasks. If so, then mc = mc + 1, where m is the number of tasks and c is the number of grids divided in one dimension. , where c takes a positive integer, N represents the number of populations, M represents the number of objectives, and jump to Step 8; if the perturbation condition is satisfied, then set mc to 0 and execute Step 5; Step 5: Perform Canopy-Kmeans clustering again; Step6: Set the of this iteration to 2, where , , is a random number between 0 and 1, d is the current iteration number, is the maximum number of iterations; Step7: Determine , takes the value of , if so, perform cross-group crossover; if not, perform within-group crossover; Step 8: Perform mutation; Step 9: Perform decoding and jump to Step 2, and loop in sequence until the optimal solution set is output.

Images