Movable home environment adjusting robot based on user behavior perception and control method thereof

Abstract

The invention relates to a control method of a mobile home environment adjusting robot based on user behavior perception. The mobile home environment adjusting robot comprises a mobile chassis module, an environment adjusting execution module, a multi-mode non-imaging perception module and a local intelligent control module. The control method comprises the following steps: S1, multi-modal non-image sensing; s2, behavior feature extraction and intention recognition; s3, service stationary point mapping and strategy generation; s4, path planning and user avoidance are carried out; and S5, executing autonomous movement and environment adjustment. According to the method, the user behavior and environment information is obtained in a non-image multi-mode sensing mode, an environment adjustment decision mechanism with the user behavior intention as the core is constructed in combination with indoor space semantic mapping, environment adjustment is converted into active and directional service from passive triggering, and active environment adjustment facing the user behavior intention is achieved.

Description

Technical Field

[0001] This invention belongs to the field of smart home technology, and in particular relates to a mobile home environment adjustment robot based on user behavior perception and its control method. Background Technology

[0002] Existing home environment control devices such as air purifiers, humidifiers, and dehumidifiers are mostly fixed devices, and their adjustment range is limited. They can usually only cover a local space around the device and are difficult to dynamically adjust their position as the user moves in different areas of the room.

[0003] Meanwhile, most existing environmental control devices are controlled based on environmental parameter thresholds or manual commands, which cannot understand the user's current behavioral state, such as sleeping, cooking, or short-term activity. This results in a mismatch between the control method and the user's actual needs, leading to energy waste or insufficient comfort.

[0004] With the development of service robot technology, some home robots with autonomous mobility have been introduced into the home environment. However, their main functions are concentrated on cleaning, inspection or simple companionship. Their movement behavior and environmental regulation equipment lack a unified perception and decision-making mechanism, making it difficult to form a collaborative service oriented towards user needs.

[0005] In addition, some existing technologies use cameras to collect image information to achieve human body recognition and behavior analysis, which poses privacy risks in private home settings such as bedrooms. They are also easily affected by lighting conditions and occlusion factors, which limits their application scope.

[0006] Therefore, there is an urgent need for a mobile home environment control technology solution that can understand user behavior intentions and proactively determine the location and method of environmental control services while protecting user privacy. Summary of the Invention

[0007] The purpose of this invention is to provide a mobile home environment adjustment robot based on user behavior perception and its control method. By acquiring user behavior and environmental information through non-image-based multimodal perception, and combining it with indoor space semantic mapping, an environmental adjustment decision mechanism with user behavior intention as the core is constructed, so that environmental adjustment is transformed from passive triggering to active and targeted service.

[0008] This invention provides a control method for a mobile home environment regulating robot based on user behavior perception, wherein the mobile home environment regulating robot includes: The mobile chassis module is used to drive the robot to move autonomously in the indoor environment and perform obstacle avoidance, fixed-point docking and recharging operations; An environmental control module, including an air purification module, a humidification module, a dehumidification module, and / or an odor control module, is used to regulate the indoor environment; The multimodal non-image perception module is used to collect user behavior data and environmental parameter data. It does not include an image acquisition device, or the image acquisition function is not enabled in the default working mode. The local intelligent control module is communicatively connected to the mobile chassis module, the environmental adjustment execution module, and the multimodal non-image perception module, and is used to execute the robot's control method; The control method includes the following steps: S1: Indoor environmental parameter data and behavioral data related to user presence and behavior are collected through the multimodal non-image perception module; S2: Preprocess and extract features from the indoor environmental parameter data and behavioral data, and combine them with a pre-established indoor spatial semantic map to determine the user's current behavioral intent; S3: Based on the behavioral intent and the corresponding spatial semantic information, invoke the preset spatial mapping rules, calculate the target service station coordinates relative to the user, and generate an environmental adjustment strategy that matches the behavioral intent; S4: During the path planning process, the user's current activity area is set as a high-cost avoidance area, and a movement path is generated to the target service station coordinates. S5: Control the mobile home environment adjustment robot to move along the movement path to the target service station coordinates, and perform environmental adjustment operations at that location according to the environmental adjustment strategy.

[0009] Furthermore, the multimodal non-image sensing module includes at least a millimeter-wave radar, an air quality sensor, and a temperature and humidity sensor. The millimeter-wave radar is used to detect one or more of the following without acquiring image information: the presence of a human body, changes in position, changes in posture, or micro-motion information of the human body.

[0010] Furthermore, the millimeter-wave radar is used to detect chest cavity micro-movements caused by human respiration, and to determine whether the user is asleep based on the chest cavity micro-movement characteristics.

[0011] Furthermore, in step S2, the behavioral intention includes at least one or more of the following: sleep behavior intention, cooking behavior intention, home entry behavior intention, or abnormal environment behavior intention.

[0012] Furthermore, in step S3, when the behavioral intention is a sleep behavior intention, the target service station coordinates are calculated as a preset safe distance position located on the side of the bed, and the environmental adjustment strategy corresponds to a low-noise operation mode and a wind-avoidance and air-ventilation mode.

[0013] Furthermore, in step S3, when the behavioral intent is a cooking intent, the target service station coordinates are calculated as the airflow interception position located between the user operation area and the kitchen ventilation area, and the environmental adjustment strategy corresponds to the enhanced air purification mode.

[0014] Furthermore, in step S5, when no clear user behavior intention is determined and environmental parameters are detected to exceed the abnormal threshold, the mobile home environment adjustment robot plans a movement path based on the spatial distribution changes of environmental parameters and moves to the abnormal parameter area as a target service station to perform fixed-point environmental adjustment.

[0015] Furthermore, in step S5, the environmental conditioning operation includes one or more of air purification, humidification, dehumidification, or odor control.

[0016] Furthermore, the portable home environment regulating robot also includes: The communication module is used for data interaction and model updates with the cloud server.

[0017] Furthermore, it also includes: S6: The collected environmental adjustment operation performance data is summarized and anonymized and then uploaded to the cloud server. The cloud server performs model training or parameter optimization based on data from multiple home environments, and then sends the updated model or parameters to the mobile home environment adjustment robot to update the local control strategy.

[0018] By employing the above-described solution, a mobile home environment adjustment robot based on user behavior perception and its control method achieves the following technical effects: (1) Adopt a non-image-based user behavior perception method to achieve effective identification of user behavior while protecting user privacy.

[0019] (2) Dynamically calculate the location of environmental adjustment service based on user behavior intentions to improve the targeting and efficiency of environmental adjustment.

[0020] (3) Introduce a user activity avoidance mechanism in the mobile path planning to reduce the robot's interference with users' lives.

[0021] (4) Support cloud-based collaborative learning to achieve model evolution and strategy optimization across family environments.

[0022] (5) The system can still operate independently under network outage conditions, and has good stability and reliability.

[0023] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Brief Description of the Drawings

[0024] Figure 1 It is a structural block diagram of the movable household environment regulation robot of the present invention; Figure 2 It is an interaction diagram of the functional modules of the movable household environment regulation robot of the present invention; Figure 3 It is a flowchart of the environment regulation control method based on user behavior perception of the present invention; Figure 4 It is a schematic diagram of space mapping and service stop points based on different behavior intentions of the present invention. Detailed Embodiments

[0025] The following combines the drawings and embodiments to further describe in detail the specific embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0026] Refer to Figure 1 、 Figure 2 As shown, this embodiment provides a movable household environment regulation robot based on user behavior perception, including: A mobile chassis module, which is used to drive the robot to move autonomously in the indoor environment and perform obstacle avoidance, fixed-point docking and recharging operations.

[0027] An environment regulation execution module, including an air purification module, a humidification module, a dehumidification module and / or an odor regulation module, which is used to regulate the indoor environment.

[0028] A multi-modal non-visual perception module, which is used to collect user behavior data and environmental parameter data, does not include an image acquisition device, or does not enable the image acquisition function in the default working mode.

[0029] A local intelligent control module (including a movement control unit and an environmental regulation control unit), which is communicatively connected with the mobile chassis module, the environment regulation execution module and the multi-modal non-visual perception module, and is used to execute the control method of the robot, including user behavior recognition, space scene recognition, service stop point calculation, path planning and environmental regulation decision-making.

[0030] A communication module, which is used to perform data interaction and model update with the cloud server.

[0031] Refer to Figure 3 、 Figure 4 As shown, the control method of the robot includes the following steps: S1) Multi-modal non-visual perception: Collect indoor environmental parameter data and behavior data related to the presence and behavior of the user through the multi-modal non-visual perception module.

[0032] S2) Behavioral feature extraction and intent recognition: The indoor environmental parameter data and behavioral data are preprocessed and feature extracted. Combined with the pre-established indoor spatial semantic map, the user's current behavioral intent is determined.

[0033] S3) Service station mapping and strategy generation: Based on the behavioral intent and the corresponding spatial semantic information, a preset spatial mapping rule is invoked to calculate the target service station coordinates relative to the user and generate an environment adjustment strategy that matches the behavioral intent.

[0034] S4) Path planning and user avoidance: During the path planning process, the user's current activity area is set as a high-cost avoidance area, and a movement path is generated to the target service station coordinates.

[0035] S5) Autonomous movement and environmental adjustment execution: Control the mobile home environment adjustment robot to move along the movement path to the target service station coordinates, and perform environmental adjustment operations at the location according to the environmental adjustment strategy; S6) Execution Feedback and Co-evolution: The collected environmental adjustment operation execution effect data is summarized and anonymized and then uploaded to the cloud server. The cloud server performs model training or parameter optimization based on data from multiple home environments, and sends the updated model or parameters to the mobile home environment adjustment robot to update the local control strategy.

[0036] In this embodiment, the multimodal non-image-based sensing module includes at least a millimeter-wave radar, an air quality sensor, and a temperature and humidity sensor. The millimeter-wave radar is used to detect one or more of the following without acquiring image information: the presence of a human body, changes in position, changes in posture, or micro-motion information of the human body (such as micro-motion information caused by breathing). The millimeter-wave radar is used to detect chest cavity micro-movements caused by human breathing and to determine whether the user is asleep based on the chest cavity micro-movement characteristics.

[0037] In step S2, the behavioral intention includes at least one or more of the following: sleep behavior intention, cooking behavior intention, home entry behavior intention, or abnormal environment behavior intention.

[0038] In step S3, when the behavioral intention is a sleep behavior intention, the target service station coordinates are calculated to be a preset safe distance position located on the side of the bed, and the environmental adjustment strategy corresponds to a low noise operation mode and a windproof and air-ventilation mode.

[0039] In step S3, when the behavioral intent is a cooking intent, the target service station coordinates are calculated as the airflow interception position between the user operation area and the kitchen ventilation area, and the environmental adjustment strategy corresponds to the enhanced air purification mode.

[0040] In step S5, when the user's behavioral intent is not clearly determined and the environmental parameters are detected to exceed the abnormal threshold, the mobile home environment adjustment robot plans a movement path based on the spatial distribution changes of the environmental parameters and moves to the abnormal parameter area as the target service station to perform fixed-point environmental adjustment.

[0041] In step S5, the environmental conditioning operation includes one or more of air purification, humidification, dehumidification, or odor control.

[0042] Example 1: Environmental Regulation in Sleep Behavior Scenarios The robot is deployed in a bedroom environment. When the multimodal non-image perception module detects the presence of a human body and shows low-amplitude, periodic respiratory micro-movements, the local intelligent control module determines that the user is in a state of sleep.

[0043] The control module maps the target service station to a preset safe distance position on the side of the bed based on the spatial semantic map, and generates a low-noise, windproof and ventilated environmental adjustment strategy to control the robot to move to the target service station to perform environmental adjustment operations.

[0044] Example 2: Environmental Adjustment in a Cooking Scenario When a rapid increase in pollutant concentration is detected in the kitchen area and the user continues to move around, the control module determines that the user intends to cook and maps the target service point to an airflow interception location between the user's operating area and the ventilation area to avoid interfering with the user's operation.

[0045] Example 3: Active Source Tracing of Abnormal Environmental Parameters Without identifying the user's explicit behavioral intent, when environmental parameters exceed an abnormal threshold, the robot plans a movement path based on the spatial distribution changes of environmental parameters, actively moves to the abnormal parameter area, and performs fixed-point environmental adjustment.

[0046] This invention achieves proactive environmental adjustment based on user behavioral intentions through non-graphical user behavior perception, spatial semantic mapping, and autonomous movement control. By introducing a user activity avoidance mechanism in path planning, it reduces the interference of robot movement on users' normal lives, improves the system's safety and acceptability, and enables continuous optimization of environmental adjustment strategies through a cloud-based collaborative learning mechanism, giving the system the ability to evolve models across home environments.

[0047] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for a mobile home environment regulation robot based on user behavior perception, characterized in that, The mobile home environment regulating robot includes: The mobile chassis module is used to drive the robot to move autonomously in the indoor environment and perform obstacle avoidance, fixed-point docking and recharging operations; An environmental control module, including an air purification module, a humidification module, a dehumidification module, and / or an odor control module, is used to regulate the indoor environment; The multimodal non-image perception module is used to collect user behavior data and environmental parameter data. It does not include an image acquisition device, or the image acquisition function is not enabled in the default working mode. The local intelligent control module is communicatively connected to the mobile chassis module, the environmental adjustment execution module, and the multimodal non-image perception module, and is used to execute the robot's control method; The control method includes the following steps: S1: Indoor environmental parameter data and behavioral data related to user presence and behavior are collected through the multimodal non-image perception module; S2: Preprocess and extract features from the indoor environmental parameter data and behavioral data, and combine them with a pre-established indoor spatial semantic map to determine the user's current behavioral intent; S3: Based on the behavioral intent and the corresponding spatial semantic information, invoke the preset spatial mapping rules, calculate the target service station coordinates relative to the user, and generate an environmental adjustment strategy that matches the behavioral intent; S4: During the path planning process, the user's current activity area is set as a high-cost avoidance area, and a movement path is generated to the target service station coordinates. S5: Control the mobile home environment adjustment robot to move along the movement path to the target service station coordinates, and perform environmental adjustment operations at that location according to the environmental adjustment strategy.

2. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 1, characterized in that, The multimodal non-image sensing module includes at least a millimeter-wave radar, an air quality sensor, and a temperature and humidity sensor. The millimeter-wave radar is used to detect one or more of the following without acquiring image information: the presence of a human body, changes in position, changes in posture, or micro-motion information of the human body.

3. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 2, characterized in that, The millimeter-wave radar is used to detect micro-movements in the chest cavity caused by human respiration, and to determine whether the user is asleep based on the characteristics of these micro-movements.

4. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 1, characterized in that, In step S2, the behavioral intention includes at least one or more of the following: sleep behavior intention, cooking behavior intention, home entry behavior intention, or abnormal environment behavior intention.

5. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 4, characterized in that, In step S3, when the behavioral intention is a sleep behavior intention, the target service station coordinates are calculated to be a preset safe distance position located on the side of the bed, and the environmental adjustment strategy corresponds to a low noise operation mode and a windproof and air-ventilation mode.

6. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 4, characterized in that, In step S3, when the behavioral intent is a cooking intent, the target service station coordinates are calculated as the airflow interception position between the user operation area and the kitchen ventilation area, and the environmental adjustment strategy corresponds to the enhanced air purification mode.

7. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 1, characterized in that, In step S5, when the user's behavioral intent is not clearly determined and the environmental parameters are detected to exceed the abnormal threshold, the mobile home environment adjustment robot plans a movement path based on the spatial distribution changes of the environmental parameters and moves to the abnormal parameter area as the target service station to perform fixed-point environmental adjustment.

8. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 1, characterized in that, In step S5, the environmental conditioning operation includes one or more of air purification, humidification, dehumidification, or odor control.

9. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 1 is characterized in that, The mobile home environment regulating robot also includes: The communication module is used for data interaction and model updates with the cloud server.

10. The control method for a mobile home environment regulation robot based on user behavior perception according to claim 9, characterized in that, Also includes: S6: The collected environmental adjustment operation performance data is summarized and anonymized and then uploaded to the cloud server. The cloud server performs model training or parameter optimization based on data from multiple home environments, and then sends the updated model or parameters to the mobile home environment adjustment robot to update the local control strategy.

Images