Cleaning clothes drying robot control method and system, medium and cleaning clothes drying robot

Abstract

The invention provides a cleaning clothes-airing robot control method and system, a computer readable storage medium and a cleaning clothes-airing robot. The control method comprises the steps that multi-mode sensing data of the environment where the cleaning clothes drying robot is located are acquired, wherein the multi-mode sensing data comprise at least one of visual data, humidity data, radar data, networking data and voice data; performing fusion analysis on the multi-modal sensing data to generate a task execution instruction; and executing a corresponding cleaning task and / or clothes airing and collecting task according to the task execution instruction. According to the method, a mobile cleaning module and an intelligent clothes drying module are creatively integrated into an integrated device, namely the cleaning and clothes drying robot, the flexible response of single device to the requirements of two balcony scenes of cleaning and clothes drying is achieved, the cleaning and clothes drying robot can collect multi-modal sensing data, fusion analysis and active intelligent decision making are achieved, and the cleaning and clothes drying efficiency is improved. The cleaning task and the clothes airing and collecting task are automatically executed, and the intelligent degree of equipment is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent devices, in particular, the present application relates to a cleaning and clothes airing robot control method and system, a computer readable storage medium and a cleaning and clothes airing robot. BACKGROUND

[0002] With the rapid development of the smart home market, intelligent devices such as electric clothes airing machines and robotic vacuum cleaners have been widely popularized. However, existing products generally have the problems of single function and shallow intelligence. On the one hand, different devices, such as electric clothes airing machines and robotic vacuum cleaners, are independent of each other in terms of hardware and function, and can only complete corresponding single function tasks respectively, resulting in a large number of devices in the home, and no device can independently respond to complex life scenarios such as "clean the balcony after collecting clothes". On the other hand, existing products have generally introduced voice control or APP remote control functions, and their "intelligence" is mostly limited to triggering and controlling single devices and single functions, and cannot make active decisions and perform automatic tasks.

[0003] This functional isolation and insufficient intelligence result in a poor device control experience for users in the balcony scenario, and therefore, there is an urgent need for a device with complex functions and autonomous decision-making and a control method thereof. SUMMARY

[0004] To at least solve one of the above technical defects, the present application provides a cleaning and clothes airing robot control method and corresponding system, computer readable storage medium and cleaning and clothes airing robot.

[0005] According to an aspect, an embodiment of the present application provides a cleaning and clothes airing robot control method, comprising: obtaining multi-modal perception data of an environment in which a cleaning and clothes airing robot is located, the multi-modal perception data including at least one of visual data, humidity data, radar data, networking data and voice data; performing fusion analysis on the multi-modal perception data to generate a task execution instruction; executing a corresponding cleaning task and / or clothes airing and collecting task according to the task execution instruction.

[0006] Preferably, the cleaning and clothes airing robot comprises a separable mobile cleaning module and a clothes airing module. Before executing the corresponding cleaning task and / or clothes airing and collecting task according to the task execution instruction, the method further comprises: controlling the mobile cleaning module and the clothes airing module to separate or connect according to the task to be executed corresponding to the task execution instruction; Specifically, when the task to be performed is a cleaning task, the control of the mobile cleaning module is separated from the clothes drying module; when the task to be performed is a clothes drying and collection task or a cleaning task and a clothes drying and collection task are performed simultaneously, the control of the mobile cleaning module is connected to the clothes drying module.

[0007] Preferably, the acquisition of multimodal perception data of the environment in which the clothes-drying robot is located includes at least one of the following: Ground environment images are acquired by the first image acquisition unit set on the mobile cleaning module; Images of the clothes-drying area are acquired by a second image acquisition unit installed on the clothes-drying module; Detects ambient humidity using a humidity sensor; Obstacle information is detected using lidar and / or ultrasonic radar; Obtain weather forecast information and / or remote control information through the communication unit; The microphone array receives user voice commands.

[0008] Preferably, the step of fusing and analyzing the multimodal sensing data to generate task execution instructions includes: Based on preset task execution conditions, when the multimodal sensing data meets the task execution conditions, a corresponding task execution instruction is generated; and / or, The multimodal perception data is input into a pre-trained task decision model, and the task decision model outputs the task execution instructions. Preferably, when multiple task execution instructions are generated, before executing the corresponding cleaning task and / or laundry drying task according to the task execution instructions, the method further includes: The execution instructions of multiple tasks are scheduled and sorted according to the preset global task priority rules; The tasks are pre-categorized according to the task triggering mechanism, and the priority order of the tasks corresponding to the global task priority rule from high to low is: user immediate instruction tasks, environment adaptive tasks, and timed tasks.

[0009] Preferably, the task execution instructions include at least one of the following: Targeted cleaning instructions and / or clothing grabbing instructions triggered by image recognition results; The instruction to bring in clothes or open the rain cover is triggered based on ambient humidity and / or weather forecast information. Cleaning commands triggered by ground humidity; Cleaning commands and / or clothes drying / collecting commands triggered by user voice commands; Automatic laundry collection and / or automatic cleaning commands triggered by scheduled tasks.

[0010] Preferably, the corresponding cleaning tasks are performed, including: The mobile cleaning module is controlled to perform sweeping, mopping, or spot cleaning. Perform the corresponding tasks of drying and collecting clothes, including: The robotic arm controlling the clothes drying module performs the tasks of grabbing, transferring, and hanging clothes.

[0011] Furthermore, according to another aspect, embodiments of the present invention provide a control system for a clothes-drying robot, comprising: The controller, along with a mobile cleaning module, a clothes drying module, and a multimodal sensing module connected to the controller; wherein: The multimodal sensing module is used to collect multimodal perception data of the environment in which the cleaning and drying robot is located and feed it back to the controller so that the controller can determine the cleaning task and / or clothes drying and collection task to be performed. The mobile cleaning module is used to perform cleaning tasks under the control of the controller; The clothes drying module is used to perform clothes drying and collecting tasks under the control of the controller; The controller is used to execute the cleaning and drying robot control method described in any of the above embodiments.

[0012] According to yet another aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described control method for a clothes-drying robot.

[0013] According to another aspect of the present invention, a clothes-drying robot is provided, the computer including one or more processors; a memory; one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs being configured to perform the above-described clothes-drying robot control method.

[0014] Compared with the prior art, the present invention has the following advantages: The present invention provides a cleaning and drying robot control method, system, storage medium, and cleaning and drying robot. By innovatively integrating a mobile cleaning module and an intelligent drying module into an integrated device—the cleaning and drying robot—it achieves flexible response of a single device to the needs of both cleaning and drying on balconies. Furthermore, the cleaning and drying robot can collect multimodal perception data, fuse and analyze it, and make proactive intelligent decisions to automatically execute cleaning and drying / collecting tasks, significantly improving the intelligence level of the device.

[0015] Furthermore, the cleaning and drying robot features a detachable structure, enabling a single unit to flexibly respond to the needs of both cleaning and drying on balconies. The device can dynamically adjust its form according to task instructions, solving the pain points of traditional equipment's limited functionality and large space occupation, making it perfectly suited for multi-functional spaces such as balconies.

[0016] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of the invention. Attached Figure Description

[0017] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating the control method for a clothes-drying robot provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of the cleaning and drying robot control system provided in an embodiment of the present invention. Detailed Implementation

[0018] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0019] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0020] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0021] The technical solutions of this application and how they solve the aforementioned technical problems of the prior art are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0022] like Figure 1 As shown, this embodiment provides a control method for a clothes-drying robot, which mainly includes the following steps: Step S110: Obtain multimodal perception data of the environment in which the clothes-drying robot is located. The multimodal perception data includes at least one of visual data, humidity data, radar data, network data, and voice data.

[0023] The clothes-drying robot uses its onboard multimodal sensing module to collect multi-source information about its environment in real time. This multimodal sensing data specifically includes: Visual data: Ground environment images are captured by the first image acquisition unit on the mobile cleaning module, such as an RGB-D camera. These ground environment images are used to identify dirty areas, obstacles, liquid spills, etc.; and images of the drying area are captured by the second image acquisition unit on the clothes drying module, such as a rotatable high-definition camera. These drying area images are used to identify the status of clothes, the location of idle clothes hangers or drying rods, and the load on the drying rods, etc.

[0024] Environmental data: Ambient temperature and humidity are detected by temperature and humidity sensors to provide a basis for drying decisions. Specifically, the mobile cleaning module is equipped with a first humidity sensor to detect ground humidity; the clothes drying module is equipped with a second humidity sensor to detect the dryness of the clothes and whether there is rain.

[0025] Radar data: Radar data is collected through lidar and / or ultrasonic radar. This radar data serves as spatial perception data, enabling the construction of environmental maps and real-time detection of dynamic and static obstacles, thus ensuring mobile navigation and obstacle avoidance. Specifically, lidar is installed on the clothes-drying module, with a detection range of 0.2-5m and a 360° angle, enabling obstacle detection in the direction of travel; ultrasonic radar is installed on the mobile cleaning module, with a detection range of 0.1-3m, capable of detecting ground undulations.

[0026] Networked data: Access to home networks and the Internet via communication units such as Wi-Fi and Bluetooth to obtain real-time weather forecasts, such as temperature, humidity, and precipitation probability; remote control commands or reservation commands sent by users through mobile apps, smart speakers, smart screens, and other devices.

[0027] Voice data: Received, noise-reduced, and recognized by the user's voice commands via a microphone matrix array.

[0028] Step S120: Perform fusion analysis on the multimodal sensing data to generate task execution instructions.

[0029] In this embodiment, the step may specifically include: generating a corresponding task execution instruction when the multimodal perception data meets the preset task execution conditions; and / or inputting the multimodal perception data into a pre-trained task decision model, and having the task decision model output the task execution instruction.

[0030] In this embodiment, the collected multimodal perception data can be processed and analyzed based on a preset rule base and / or a pre-trained task decision module to generate task execution instructions. Specifically, task execution instructions can be confirmed by using a rule base matching method or a model decision method, depending on the type of multimodal perception data.

[0031] The task execution instructions are generated based on rule-based matching, specifically as follows: For structured data such as humidity data and network data, the system standardizes the data based on preset logical processing rules, compares thresholds, and then generates corresponding task execution instructions.

[0032] A rule base is pre-built, which includes a series of "condition-action" rules.

[0033] For example, the rule base is pre-set to take in the laundry when the ambient humidity reaches 75%RH and / or the weather forecast shows a rainfall probability greater than 60%. Then, when the humidity sensor detects a sudden increase in ambient humidity, such as exceeding 85%RH, and the weather forecast obtained by the communication unit shows a rainfall probability greater than 60% in the next half hour, an emergency laundry take-in command is generated.

[0034] For example, if the weather forecast indicates a rainfall probability of more than 80% and it is light rain, then when the weather forecast obtained by the communication unit shows a rainfall probability of 99% and it is light rain in the next half hour, a command to open the rain shield will be generated.

[0035] For example, if the floor is pre-set to be cleaned at noon, the cleaning command will be triggered when the device clock reaches 12 o'clock.

[0036] Based on a rule-based matching method, it enables simple and clear judgments on structured data such as humidity and timing. The rule system has a millisecond-level response time, resulting in high efficiency and reliability.

[0037] The task execution instructions are generated based on a model-driven decision-making approach, specifically as follows: Unstructured data such as visual data, radar data, voice data, and network data are preprocessed by normalization and noise reduction, and features are extracted. Corresponding models, such as image recognition, speech recognition, and NLP (Neural Language Pattern Recognition) models, are loaded and run. Through decision models, feature extraction and correlation analysis are performed on the data, and task decision results are output to obtain corresponding task execution instructions.

[0038] For example, the second image acquisition unit acquires an image of the clothes drying area, inputs the image of the clothes drying area into a pre-trained image recognition module, and recognizes that the clothes drying have shown dry characteristics, such as texture shrinkage and color restoration, and then generates a clothes collection instruction. For example, when a microphone matrix array receives a user's voice command, it inputs the user's voice command into a pre-trained speech recognition module. If the module recognizes the user saying "I've finished washing the clothes," it generates a clothes-drying command.

[0039] Based on model-driven decision-making, it can perceive and analyze complex data such as images and voice, significantly improving the level of intelligence.

[0040] In this embodiment, the initial decision obtained from two methods is received, and then a comprehensive decision is made based on priority to generate a final, conflict-free task instruction queue.

[0041] Step S130: Execute the corresponding cleaning task and / or laundry drying task according to the task execution instruction.

[0042] In this embodiment, the controller parses the task instructions and controls the corresponding modules to execute the tasks. Specifically, the cleaning task includes controlling the mobile cleaning module to sweep, mop, or perform targeted deep cleaning at a designated location. The clothes drying task includes controlling the robotic arm of the clothes drying module to locate clothing or hangers based on image recognition results, and performing operations such as precise grasping, transferring from the drying rack, or hanging from a storage box or by hand onto the drying rack.

[0043] For cleaning tasks, the mobile cleaning module is activated. For example, for a global cleaning command, it is controlled to vacuum and sweep according to the planned path; for a mopping command, it is controlled to fill the water tank and lower the mop unit; for a spot cleaning command, it is controlled to move to the coordinates of the stains identified by the image and perform targeted cleaning.

[0044] For the task of drying and collecting clothes, the robotic arm and its auxiliary mechanisms of the drying module are controlled. For example, when executing the collection instruction, the robotic arm moves above the target clothes according to the positioning information of the second image acquisition unit, grabs the clothes with the flexible gripper or hook at the end of the robotic arm, and then transfers them to the user's hand or a designated storage basket or wardrobe; when executing the drying instruction, the robotic arm grabs the clothes from the user's hand or the area where the clothes are to be dried (such as the washing machine outlet or a specific basket) and accurately hangs them on an empty clothes drying rod or hanger identified by the sensor.

[0045] The cleaning and drying robot control method provided by this invention innovatively integrates a mobile cleaning module and an intelligent drying module into an integrated device—the cleaning and drying robot. This enables a single device to flexibly respond to the needs of both cleaning and drying on balconies. Furthermore, the cleaning and drying robot can collect multimodal perception data, fuse and analyze it, and make proactive intelligent decisions to automatically execute cleaning and drying / collecting tasks, significantly improving the intelligence level of the device.

[0046] In some embodiments, the cleaning and drying robot includes a detachable mobile cleaning module and a drying module.

[0047] Specifically, the cleaning and drying robot adopts a modular design, with the mobile cleaning module and the drying module capable of intelligent separation. The detachable connection mechanism for the mobile cleaning module and the drying module includes an electromagnetic lock assembly and guide pin disposed on the upper surface of the mobile cleaning module, and corresponding lock holes and guide grooves disposed on the bottom of the drying module. Separation or connection of the mobile cleaning module and the drying module can be achieved by controlling the on / off state of the electromagnetic lock assembly.

[0048] When the two modules are connected, the guide pin first inserts into the guide groove for coarse positioning and mechanical guidance. Then, the electromagnetic lock is energized, the bolt extends and engages with the lock hole, completing a secure mechanical lock. Simultaneously, charging contacts and a multi-functional communication interface are arranged on the mating surface to ensure power transmission and high-speed data communication during connection.

[0049] In this embodiment, before step S130 executes the corresponding cleaning task and / or clothes drying task according to the task execution instruction, it further includes: controlling the mobile cleaning module to separate or connect with the clothes drying module according to the task to be executed corresponding to the task execution instruction.

[0050] When the task to be performed is cleaning, the mobile cleaning module is separated from the clothes drying module. Specifically, the connecting mechanism is released, such as the electromagnetic lock or mechanical buckle, so that the mobile cleaning module is separated from the base of the clothes drying module. This makes the robot smaller and the cleaning module can work flexibly. The separated cleaning module can move freely to other areas such as the living room and bedroom to perform tasks, no longer limited by the balcony space, avoiding the restriction of the clothes drying module and affecting the operation, and also reducing energy consumption.

[0051] When the task to be performed is either drying or cleaning, or both tasks are performed simultaneously, the mobile cleaning module connects to the drying module. This allows the mobile cleaning module to act as a stable aerial platform for the drying module, ensuring the absolute stability of the robotic arm during delicate operations such as gripping and suspending. It can also move flexibly according to drying needs. Furthermore, the mobile cleaning module can perform cleaning tasks while the drying module is performing drying, significantly improving work efficiency.

[0052] In a preferred embodiment, step S110 acquires multimodal perception data of the environment in which the clothes-drying robot is located, including at least one of the following: Ground environment images are acquired by a first image acquisition unit set on the mobile cleaning module. For example, ground environment images acquired by the first image acquisition unit on the mobile cleaning module, such as RGB-D cameras, are used to identify dirty areas, obstacles, liquid spills, etc.

[0053] Images of the drying area are acquired by a second image acquisition unit set on the drying module. For example, images of the drying area are acquired by a rotatable high-definition camera on the second image acquisition unit on the drying module. The images of the drying area are used to identify the status of the clothes, the location of idle clothes hangers or drying rods, the load status of the drying rods, etc.

[0054] The system detects ambient humidity using a humidity sensor, or for example, ambient temperature and humidity using a temperature and humidity sensor, to provide a basis for drying decisions. Specifically, the mobile cleaning module is equipped with a first humidity sensor to detect ground humidity, and the clothes drying module is equipped with a second humidity sensor to detect the dryness of the clothes and whether there is rain.

[0055] Obstacle information is detected using lidar and / or ultrasonic radar. Specifically, by collecting spatial perception data, an environmental map is constructed, and dynamic and static obstacles are detected in real time, providing support for mobile navigation and obstacle avoidance. Lidar is installed on the clothes-drying module, with a detection range of 0.2-5m and a 360° angle, enabling obstacle detection in the direction of travel. Ultrasonic radar is installed on the mobile cleaning module, with a detection range of 0.1-3m, capable of detecting ground undulations.

[0056] Weather forecast information and / or remote control information are obtained through communication units. For example, real-time weather forecasts, such as temperature, humidity, and precipitation probability, can be obtained by connecting to a home network and the internet via communication units such as Wi-Fi and Bluetooth. Another example is remote control commands or reservation instructions sent by users through devices such as mobile apps, smart speakers, and smart screens.

[0057] The system receives user voice commands via a microphone matrix; specifically, it receives, reduces noise, and recognizes user voice commands through a microphone matrix array.

[0058] In this embodiment, by integrating multi-source heterogeneous information such as ground vision, aerial vision, environmental humidity, space radar, external weather, and user voice, the system constructs a comprehensive, high-precision, real-time perception network that reflects the working environment of the clothes-drying robot and the user's intentions. This solves the problems of limited perception dimensions and incomplete scene understanding inherent in traditional single-sensor devices. Furthermore, the multimodal perception data provides rich and reliable input for the controller's intelligent decision-making, enabling the clothes-drying robot to not only automatically adapt to complex dynamic environments but also accurately understand and respond to user interaction commands, thereby achieving an improvement in intelligence from passive execution to proactive decision-making.

[0059] In some embodiments, when the system generates multiple task instructions in a short period of time, before step S130, which executes the corresponding cleaning task and / or clothes drying task according to the task execution instructions, the method further includes: scheduling and sorting the multiple task execution instructions according to a preset global task priority rule.

[0060] The tasks are pre-categorized according to the task triggering mechanism, and the priority order of the tasks corresponding to the global task priority rule from high to low is: user immediate instruction tasks, environment adaptive tasks, and timed tasks.

[0061] In actual operation, multiple task execution instructions may be generated simultaneously or within a short period. For example, while the clothes-drying robot is performing a scheduled cleaning task, the user suddenly issues a voice command to collect the clothes, and at the same time, the system detects impending rain through network information. Therefore, before executing the task according to the instructions, these task execution instructions need to be scheduled and sorted according to a preset global task priority rule. A preferred task priority order is: first, responding to immediate user commands, such as direct commands triggered by voice, gestures, or the app, which represents the highest priority user intent; second, environmentally adaptive tasks, i.e., tasks that the system autonomously triggers based on real-time perceived environmental changes, such as immediately cleaning stains or automatically collecting clothes when rain is detected; and finally, preset scheduled tasks, such as daily cleaning or clothes-collecting tasks set to be executed at fixed times. The controller manages the task queue according to this priority order, ensuring that high-priority tasks are responded to in a timely manner, while rationally scheduling the execution of low-priority tasks. This method can avoid robot system lag or logical confusion caused by task conflicts, ensuring the orderly and reliable operation of the equipment in complex balcony scenarios.

[0062] In some embodiments, the task execution instructions include at least one of the following: Targeted cleaning commands are triggered based on image recognition results. For example, by using an RGB-D camera located at the bottom of the mobile cleaning module to identify image feature data of pet hair clumps with specific shapes and textures on the ground, a targeted cleaning command is triggered. The controller then guides the mobile cleaning module to navigate to the coordinates of the hair clump, switches to high suction mode, and activates the roller brush for focused cleaning.

[0063] Clothing retrieval commands are triggered based on image recognition results. For example, if a rotatable high-definition camera on the clothes drying module detects a blue long-sleeved shirt that the user has requested on the clothesline, a clothing retrieval command is triggered, and the clothes are automatically retrieved for the user.

[0064] The system can trigger commands to collect clothes and / or open rain shelters based on ambient humidity. For example, if the humidity sensor on the clothes drying module detects a sharp increase in ambient humidity from 50%RH to 85%RH within 10 minutes, an emergency command to collect clothes is triggered, controlling the robotic arm to move all the clothes drying on the drying rack to the designated storage basket or wardrobe. It can also trigger a command to open the rain shelter.

[0065] The system can trigger laundry collection commands and / or rain cover opening commands based on weather forecast information. For example, if the forecast predicts a greater than 80% chance of rain, an emergency laundry collection command will be triggered, activating a robotic arm to move all the clothes drying on the clothesline to designated storage baskets or wardrobes. It can also trigger a rain cover opening command.

[0066] Cleaning commands are triggered based on ground humidity. For example, if the infrared humidity sensor on the mobile cleaning module detects that the humidity value of a local area of ​​the ground exceeds the safety threshold, such as 70%RH, a cleaning command is triggered, and the dry sweeping and water suction mode quickly removes the water from the ground.

[0067] Cleaning and / or clothes drying commands triggered by user voice commands. For example, if a user wakes up the cleaning and drying robot with a wake word and specifies the corresponding task, the relevant command will be triggered.

[0068] Automatic laundry collection commands triggered by scheduled tasks. For example, the system automatically collects laundry when the internal clock reaches a user-preset time.

[0069] Automatic cleaning commands are triggered by scheduled tasks. For example, cleaning is automatically performed when the system's internal clock reaches a user-preset time.

[0070] Among them, the cleaning command, automatic cleaning command, and fixed-point cleaning command are used to control the mobile cleaning module to perform cleaning tasks, specifically including sweeping, mopping, or fixed-point cleaning. The clothes grabbing command, clothes collection command, clothes drying and collection command, and automatic clothes collection command are used to control the clothes drying module to perform clothes drying and collection tasks, specifically including controlling the robotic arm of the clothes drying module to grab, transfer, or hang clothes.

[0071] In this embodiment, diverse task execution instructions are automatically generated based on rich multimodal sensor data, which can adapt to the complex needs of the balcony scenario and significantly improve the level of intelligence.

[0072] Furthermore, embodiments of the present invention provide a control system for a clothes-drying robot, such as... Figure 2 As shown, the system includes: a controller and a mobile cleaning module, a clothes drying module, and a multimodal sensing module connected to the controller; The multimodal sensing module is used to collect multimodal perception data of the environment in which the cleaning and drying robot is located and feed it back to the controller so that the controller can determine the cleaning task and / or the drying and collecting task to be performed.

[0073] Specifically, the multimodal sensing module is installed on the mobile cleaning module and the clothes-drying module and connected to the controller. It is used to collect multimodal perception data of the environment in which the cleaning and drying robot operates and feed it back to the controller. Each unit of the multimodal sensing module is used to collect various types of detection data, which can be used for fusion analysis. By setting up the multimodal sensing module, the collected multimodal perception data provides rich and reliable input for the controller's intelligent decision-making, enabling the cleaning and drying robot to not only automatically adapt to complex dynamic environments but also accurately understand and respond to user interaction commands, thereby improving its intelligence from passive execution to proactive decision-making. The multimodal perception data includes at least one of visual data, humidity data, radar data, network data, and voice data.

[0074] The mobile cleaning module is used to perform cleaning tasks under the control of the controller.

[0075] Specifically, the mobile cleaning module includes a sweeping and mopping unit controlled by a controller and a moving unit driven by a hub motor. Under the control of the controller, it can plan its path, move, and perform corresponding sweeping and mopping tasks. The mobile cleaning module includes a moving unit and a sweeping and mopping unit.

[0076] The moving unit is connected to the controller and is used for navigation and movement under the controller's control. The moving unit may use a hub motor with an encoder, supporting continuously variable speed and climbing ability at a certain angle. The sweeping and mopping unit is connected to the controller and is used to perform sweeping and / or mopping tasks. The sweeping part includes a main roller brush and two side brushes, and the mopping part includes a rotating mop, a clean water tank and a dirty water tank, and integrates a self-cleaning function.

[0077] The clothes drying module is used to perform clothes drying and collecting tasks under the control of the controller.

[0078] Specifically, the clothes drying module is connected to the controller and can be detachably connected to the mobile cleaning module, used to perform clothes drying and collection tasks under the control of the controller. The clothes drying module includes a foldable robotic arm driven by the controller, which controls several servo motors via a CAN bus. Each servo motor corresponds to one joint, realizing coordinated movement of multiple joints, and can flexibly handle the grabbing, transfer, and hanging of clothes.

[0079] The controller is used to execute the cleaning and drying robot control method described in any of the above embodiments. In this embodiment, the controller may specifically use an ARM Cortex-A72 quad-core processor as the central processing unit, with a main frequency of 1.5GHz, integrating a lightweight large model, and possessing multimodal data fusion and intelligent decision-making capabilities. The controller obtains multimodal perception data from the multimodal sensing module connected to it via wired and / or wireless means, and determines the cleaning task and / or clothes drying task to be executed based on a preset rule base or decision model. In addition, an RS485 serial port is used to realize real-time data interaction between the mobile cleaning module and the clothes drying module, such as cleaning progress, robotic arm status, etc., which has strong anti-interference capabilities and is suitable for stable short-distance communication.

[0080] As a preferred example, the following illustrates a well-structured cleaning and drying control system, which includes a controller, a multimodal sensing module, a mobile cleaning module, and a clothes drying module connected to the controller.

[0081] The detachable connection mechanism between the mobile cleaning module and the clothes drying module specifically includes an electromagnetic lock assembly and a guide pin disposed on the upper surface of the mobile cleaning module, and a lock hole and a guide groove disposed on the bottom of the clothes drying module. The electromagnetic lock is connected to a controller, and the separation or connection of the mobile cleaning module and the clothes drying module can be achieved by controlling the power supply of the electromagnetic lock assembly through the controller.

[0082] The mobile cleaning module is connected to the controller and is used to perform cleaning tasks under the control of the controller. The mobile cleaning module includes a sweeping and mopping unit controlled by the controller and a moving unit driven by a hub motor. The moving unit is connected to the controller and can be a hub motor with an encoder. The sweeping and mopping unit is connected to the controller. The sweeping part includes a main roller brush and two side brushes, and the mopping part includes a rotating mop, a clean water tank and a dirty water tank, and integrates a self-cleaning function.

[0083] The multimodal sensing module connected to the controller on the mobile cleaning module includes a first image acquisition unit, which may be an RGB-D camera, installed on the front side of the bottom of the mobile cleaning module; it also includes an ultrasonic radar, which is installed on the front end of the mobile cleaning module near the bottom; it also includes a first humidity sensor, installed on the bottom of the mobile cleaning module; and it also includes a first communication unit, which may be a Bluetooth / WiFi communication unit.

[0084] The clothes drying module is connected to a controller and is used to perform clothes drying and collection tasks under the control of the controller. The clothes drying module includes a foldable robotic arm driven by the controller, which controls several servo motors via a CAN bus. Each servo motor corresponds to one joint, realizing coordinated movement of multiple joints and flexibly handling the gripping, transfer, and hanging of clothes.

[0085] The clothes drying module also includes a rainproof baffle driven by a controller. The rainproof baffle includes a motor, a gear and rack mechanism, a lightweight waterproof cloth and an aluminum alloy frame. The controller is connected to the motor, and under the control of the controller, the motor drives the gear and rack mechanism to extend and retract. When extended, it can provide a rain-proof area for the drying area below.

[0086] The clothes drying module also includes a speaker controlled by a controller.

[0087] The multimodal sensing module on the clothes drying module includes a second image acquisition unit, which may have a rotatable high-definition camera mounted on the top of the clothes drying module; a lidar mounted on the front end of the clothes drying module; a second humidity sensor mounted on the top or front end of the clothes drying module; a pressure sensor located inside the end gripper of the foldable robotic arm; a microphone and voice wake-up unit; and a second communication unit, which may be a Bluetooth / WiFi communication unit.

[0088] The content of the method embodiments of the present invention is applicable to the system embodiments. The specific functions implemented in the system embodiments are the same as those in the method embodiments described above. Please refer to the description in the method embodiments for details, which will not be repeated here. This system innovatively integrates a mobile cleaning module and an intelligent clothes drying module into an integrated device—a cleaning and clothes drying robot. This enables a single device to flexibly respond to the needs of both cleaning and clothes drying on balconies. Furthermore, the cleaning and clothes drying robot can collect multimodal perception data, fuse and analyze it, and make proactive intelligent decisions to automatically execute cleaning and clothes drying tasks, significantly improving the intelligence level of the device.

[0089] Furthermore, embodiments of the present invention provide a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the cleaning and drying robot control method described in any of the above embodiments. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. That is, the storage device includes any medium that stores or transmits information in a readable form by a device (e.g., a computer, a mobile phone), and can be a read-only memory, a disk, or an optical disk, etc.

[0090] The content of the method embodiments of the present invention is applicable to the storage medium embodiments. The specific functions implemented by the storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods. For details, please refer to the description in the method embodiments, which will not be repeated here.

[0091] Furthermore, this invention also provides a clothes-drying robot. The clothes-drying robot includes one or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, and the one or more computer programs are configured to execute the clothes-drying robot control method described in any of the above embodiments. The clothes-drying robot provided in this embodiment is the complete physical carrier and final product form of the technical solutions described in the above embodiments. It successfully integrates a separate modular structure, multimodal environmental perception, intelligent decision-making based on a large model, dexterous robotic arm operation, a high-efficiency cleaning system, and user-friendly human-computer interaction, and can meet the complex needs of balcony scenarios.

[0092] The content of the method embodiments of the present invention is applicable to the embodiments of the cleaning and drying robot. The specific functions implemented by the embodiments of the cleaning and drying robot are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods. For details, please refer to the description in the method embodiments, which will not be repeated here.

[0093] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0094] The above description is only a partial embodiment of 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 principle 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 clothes-drying robot, characterized in that, The method includes: Acquire multimodal perception data of the environment in which the clothes-drying robot is located, wherein the multimodal perception data includes at least one of visual data, humidity data, radar data, network data, and voice data; The multimodal sensing data is fused and analyzed to generate task execution instructions; According to the task execution instructions, perform the corresponding cleaning tasks and / or laundry drying and collection tasks.

2. The method according to claim 1, characterized in that, The cleaning and drying robot includes a detachable mobile cleaning module and a drying module; Before executing the corresponding cleaning task and / or laundry drying task according to the task execution instruction, the method further includes: According to the task to be executed corresponding to the task execution instruction, control the separation or connection of the mobile cleaning module and the clothes drying module; Specifically, when the task to be performed is a cleaning task, the control of the mobile cleaning module is separated from the clothes drying module; when the task to be performed is a clothes drying and collection task or a cleaning task and a clothes drying and collection task are performed simultaneously, the control of the mobile cleaning module is connected to the clothes drying module.

3. The method according to claim 1, characterized in that, The acquisition of multimodal perception data of the environment in which the clothes-drying robot is located includes at least one of the following: Ground environment images are acquired by the first image acquisition unit set on the mobile cleaning module; Images of the clothes-drying area are acquired by a second image acquisition unit installed on the clothes-drying module; Detects ambient humidity using a humidity sensor; Obstacle information is detected using lidar and / or ultrasonic radar; Obtain weather forecast information and / or remote control information through the communication unit; The microphone array receives user voice commands.

4. The method according to claim 1, characterized in that, The process of fusing and analyzing the multimodal sensing data to generate task execution instructions includes: Based on preset task execution conditions, when the multimodal sensing data meets the task execution conditions, a corresponding task execution instruction is generated; and / or, The multimodal perception data is input into a pre-trained task decision model, and the task decision model outputs the task execution instructions.

5. The method according to claim 1, characterized in that, When multiple task execution instructions are generated, before executing the corresponding cleaning task and / or laundry hanging task according to the task execution instructions, the method further includes: The execution instructions of multiple tasks are scheduled and sorted according to the preset global task priority rules; The tasks are pre-categorized according to the task triggering mechanism, and the priority order of the tasks corresponding to the global task priority rule from high to low is: user immediate instruction tasks, environment adaptive tasks, and timed tasks.

6. The method according to claim 1, characterized in that, The task execution instructions include at least one of the following: Targeted cleaning instructions and / or clothing grabbing instructions triggered by image recognition results; The instruction to bring in clothes or open the rain cover is triggered based on ambient humidity and / or weather forecast information. Cleaning commands triggered by ground humidity; Cleaning commands and / or clothes drying / collecting commands triggered by user voice commands; Automatic laundry collection and / or automatic cleaning commands triggered by scheduled tasks.

7. The method according to claim 1, characterized in that, Perform the corresponding cleaning tasks, including: The mobile cleaning module is controlled to perform sweeping, mopping, or spot cleaning. Perform the corresponding tasks of drying and collecting clothes, including: The robotic arm controlling the clothes drying module performs the tasks of grabbing, transferring, and hanging clothes.

8. A control system for a clothes-drying robot, characterized in that, It includes a controller and a mobile cleaning module, a clothes drying module, and a multimodal sensing module connected to the controller; wherein: The multimodal sensing module is used to collect multimodal perception data of the environment in which the cleaning and drying robot is located and feed it back to the controller so that the controller can determine the cleaning task and / or clothes drying and collection task to be performed. The mobile cleaning module is used to perform cleaning tasks under the control of the controller; The clothes drying module is used to perform clothes drying and collecting tasks under the control of the controller; The controller is used to execute the cleaning and drying robot control method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the cleaning and drying robot control method according to any one of claims 1 to 7.

10. A clothes-drying robot, characterized in that, include: One or more processors; Memory; One or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more computer programs being configured to: perform the cleaning and drying robot control method according to any one of claims 1 to 7.

Images