Task execution method, apparatus, device, and product

Abstract

The present disclosure relates to a task execution method, apparatus, device and product. The method comprises determining a clothing state of a clothing, the clothing state indicating whether the clothing can be taken off and stored. The method comprises in response to the clothing state indicating that the clothing can be taken off and stored, generating, by an action model, an action policy based on clothing information of the clothing and a predetermined instruction, the action model being a multi-modal model. The method comprises executing, by an intelligent robot, the action policy.

Description

Technical Field

[0001] This disclosure relates to the field of computers, and more specifically to methods, apparatus, devices and products for performing tasks. Background Technology

[0002] Intelligent robots (hereinafter referred to as robots) are most widely used in manufacturing. They can perform various complex, repetitive, or dangerous tasks, such as welding, painting, assembly, and handling. These robots can significantly improve production efficiency, reduce costs, and ensure consistent product quality. Furthermore, with continuous technological advancements, the application of robots is expanding from the industrial sector to other fields. For example, in the field of household chores, robots can assist with simple tasks such as sweeping and mopping. Summary of the Invention

[0003] In a first aspect of the embodiments of this disclosure, a task execution method is provided, applicable to an intelligent robot. The method includes determining the state of clothing, the clothing state indicating whether the clothing can be removed and stored. The method includes, in response to the clothing state indicating that the clothing can be removed and stored, generating an action strategy by an action model based on clothing information and predetermined instructions, the action model being a multimodal model. The method includes the intelligent robot executing the action strategy.

[0004] In a second aspect of the embodiments of this disclosure, a task execution device suitable for an intelligent robot is provided. The device includes a clothing state determination module configured to determine the clothing state, indicating whether the clothing can be removed and stored. The device includes a motion strategy generation module configured to generate a motion strategy based on clothing information and predetermined instructions from a motion model, wherein the motion model is a multimodal model, in response to the clothing state indicating that the clothing can be removed and stored. The device includes an execution module configured to execute the motion strategy by the intelligent robot.

[0005] In a third aspect of the embodiments of this disclosure, an electronic device is provided. The electronic device includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method of the first aspect.

[0006] In a fourth aspect of the embodiments of this disclosure, a computer program product is provided. The computer program product is tangibly stored on a non-transitory computer-readable medium and includes machine-executable instructions that, when executed, cause a machine to implement the method of the first aspect.

[0007] The summary section is provided to present the chosen concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or principal features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Attached Figure Description

[0008] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram of an example environment in which several embodiments of the present disclosure may be implemented is shown;

[0010] Figure 2 A flowchart of a task execution method according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A schematic diagram illustrating the determination of clothing information based on clothing images according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A schematic diagram illustrates an example flow of task execution to achieve clothing management according to some embodiments of the present disclosure;

[0013] Figure 5 A schematic diagram illustrates an example process for determining whether to retrieve clothing based on the condition of the clothing, according to some embodiments of the present disclosure;

[0014] Figures 6A-6B A schematic diagram illustrating an example of controlling a robot to perform clothing management according to a first predetermined prompt, based on some embodiments of the present disclosure;

[0015] Figures 7A-7B A schematic diagram illustrating an example of controlling a robot to perform clothing management according to a second predetermined prompt, based on some embodiments of the present disclosure;

[0016] Figures 8A-8B A schematic diagram illustrating an example of controlling a robot to perform clothing management according to a third predetermined prompt, based on some embodiments of the present disclosure;

[0017] Figure 9 A block diagram of a task execution apparatus according to some embodiments of the present disclosure is shown; and

[0018] Figure 10 A block diagram of a device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0019] It is understood that all user-related data involved in this technical solution should be obtained and used only after authorization from the user. This means that if it is necessary to use a user's personal information in this technical solution, the user's explicit consent and authorization are required before obtaining this data; otherwise, no related data collection and use will be carried out. It should also be understood that when implementing this technical solution, relevant laws and regulations should be strictly followed in the process of data collection, use, and storage, and necessary technical measures should be taken to protect user data security and ensure the secure use of data.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] For example, upon receiving a user's proactive request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0022] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0023] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0024] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0025] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0026] As mentioned above, in the field of household chores, robots can assist humans with simple tasks such as sweeping and mopping, freeing up human hands. However, robots rarely handle more complex chores, such as drying, collecting, folding, or organizing clothes. Traditional manual drying requires humans to monitor the dryness of clothes and promptly remove and fold them after they are dry. This process is not only time-consuming and laborious but also prone to over-drying or failure to organize clothes in time due to human negligence.

[0027] To address this, this disclosure proposes a method for controlling a robot that can assist humans in handling clothing and household chores, freeing up human hands. In the solution provided in this disclosure, it is first determined whether the clothing can be removed and stored, i.e., the clothing's state is determined. If the clothing can be removed and stored, a multimodal motion model can generate a motion strategy that the robot can execute based on the clothing information and predetermined instructions. The robot then executes this motion strategy to provide a service that assists humans in managing their clothing, thereby improving their quality of life.

[0028] Figure 1 A schematic diagram of an example environment 100 in which various embodiments of this disclosure may be implemented is shown. For example... Figure 1 As shown, example environment 100 includes robot 110. In embodiments of this disclosure, robot 110 is a programmable machine device capable of automatically performing tasks, comprising mechanical structures, control systems, sensors, and actuators.

[0029] like Figure 1 As shown, robot 110 is equipped with hardware devices including a camera, a robotic arm and mechanical grippers, temperature and humidity sensors, etc. The robotic arm and mechanical grippers can be used to grasp, fold, and move clothing. Alternatively, robot 110 may also be equipped with other hardware devices, including a LiDAR, WiFi device, Bluetooth beacon receiver / transmitter, and sound acquisition device.

[0030] To facilitate the collection and storage of clothing, it is necessary to determine the condition of the clothing, which indicates whether it can be removed and stored. Only clothing that meets the conditions for removal and storage can be taken down. In some embodiments, the determination of whether clothing can be retrieved and stored can be based on its dryness, drying time, or weather conditions.

[0031] For example, if the clothing reaches a preset dryness level, it can be removed by the robot and stored in the target location. Similarly, if the clothing has been continuously dried for the predetermined drying time, it can be retrieved and stored. The required drying time can be determined based on the clothing's material. For instance, cotton clothing only needs about 2 hours of sun exposure, while wool clothing needs half a day. The material of the clothing can be determined based on images captured by a camera. Furthermore, if the weather forecast predicts light rain while the clothing is drying, it can be retrieved in advance and stored in the target location.

[0032] Once it is determined that the clothing can be retrieved and stored, the motion model can generate a motion strategy that the robot can execute based on the pre-set prompts and clothing information, so that the robot can perform actions according to the pre-set prompts, thereby meeting the user's needs regarding clothing and housework.

[0033] In some embodiments, clothing information may include information such as the material, size, type, and ownership of the clothing. Clothing information may also include the location information of the clothing, including current location information (i.e., source location information), target location information, and transfer location information.

[0034] In some embodiments, the pre-set prompts can be automatically set by the user. For example, pre-set prompts can be entered by the user via text or voice, and can be automatically applied under certain conditions. For instance, the user can choose to hang the collected clothes directly in the cabinet, or the user can choose to fold the collected clothes before putting them in the cabinet. The user can then set different pre-set prompts so that the robot can automatically perform the corresponding actions according to their needs. Alternatively, the pre-set prompts can also be automatically generated using a multimodal language model after learning the user's habits of collecting clothes.

[0035] In some embodiments, the robot 110 is configured with a multimodal motion model for computation and analysis to generate motion strategies for real-time control of the actions performed by the robot. A Large Action Model (LAM) focuses on generating complex sequence of actions or decisions. For example, a LAM can break down "making a cup of coffee" into physical actions such as moving, grasping the cup, and operating the coffee machine. The input to the motion model is multimodal and may include text instructions, images, video information, etc., and its output is a sequence of actions (such as control signals that control the robot's joint movements) or real-time decisions. Using data such as robot operation records and videos of human behavior, the motion model can be pre-trained to learn general action patterns, such as retrieving clothes from the sun, folding and organizing them, and storing them.

[0036] The robot will only be triggered to perform the action of collecting clothes if certain conditions for collection are met. For example, the following description assumes that the clothes have already met the collection conditions:

[0037] In some embodiments, assuming the predetermined prompt could be an instruction for the robot to remove clothing from the drying rack and collect it for hanging in a closet, the motion model can generate an execution action strategy based on the position of the clothing on the drying rack and the target storage location, such as the closet location. For example, the action strategy could be [grab clothing, move to the target location, place clothing]. The robot can then perform the corresponding actions based on this action strategy. For example, it could use a robotic arm and gripper to grab the clothing, use the chassis wheels to move to the target location, and then use the robotic arm and gripper again to place the clothing.

[0038] In some embodiments, suppose the predetermined prompt instructs the robot to fold the clothing. In this case, the motion model can generate an action strategy based on clothing information such as the type, size, and thickness of the clothing. For example, the action strategy could be [identify clothing, unfold clothing, fold or fold clothing multiple times, adjust and arrange clothing, place in a predetermined position].

[0039] Then, the robot can perform corresponding actions based on this action strategy. For example, a camera can be used to capture images of clothing to identify information such as the type, shape, position, and orientation of the clothing. For instance, it can determine whether the clothing is a shirt, pants, or other type of clothing, and it can also identify the angle at which the clothing is positioned on a plane. For example, a robotic arm and end effectors such as grippers or clamps can be used to grasp the edges or specific parts of the clothing, and then lift the clothing into a suspended state for subsequent operations.

[0040] For example, if the clothing is crumpled, a robotic arm and gripper can be used to flatten it. After flattening, the clothing can be folded according to its type and the associated folding order. For a shirt, the sleeves can be folded inwards first, then the garment can be folded in half; for trousers, the legs can be aligned before folding horizontally or vertically. After the initial folding, the clothing can be inspected and adjusted to ensure a neat shape. Finally, after folding, the clothing can be moved outside the folding area or to a fixed location.

[0041] In some embodiments, the pre-defined prompt may be to categorize and place clothing in fixed locations based on ownership. In this case, the action model can store the clothing in the corresponding location based on the target storage location information. The target storage location can be determined based on the categorization information. For example, if the shirt belongs to the mother, and the mother's clothing is fixedly placed in area A, then the target location can be determined to be in area A. Similarly, if the pants belong to the child, and the child's clothing is fixedly placed in area B. For example, assuming the clothing has already been folded, the action strategy could be [determine the fixed location for the clothing, place the clothing in a portable container, move the portable container to the target location, and place the clothing in the fixed location]; the action strategy could also be [determine the fixed location for the clothing, clamp the clothing with a clamp, move it to the target location, and place the clothing in the fixed location].

[0042] Afterward, the robot can perform corresponding actions based on this motion strategy. The robot can directly grasp the pants using its gripper or clamp, move them to the target location using its chassis wheels, and then use its robotic arm and gripper again to place the clothing.

[0043] To enable the robot to move smoothly, it is also equipped with a home environment map. In some embodiments, the robot 110 is also equipped with a home environment map for use in organizing and moving clothes for the user within the home environment. Alternatively, the home environment map can be constructed by the robot based on a SLAM algorithm or imported by the user.

[0044] Based on the above-described method of controlling robots, it is possible to assist humans in handling clothing and household chores, freeing up human hands. In the solution provided in this disclosure, it is first determined whether the clothing can be removed and stored, i.e., the clothing status is determined. If the clothing can be removed and stored, a multimodal motion model can generate a motion strategy that the robot can execute based on the clothing information and predetermined instructions. The robot then executes this motion strategy to provide services that assist humans in managing clothing, thereby improving the quality of life. In other words, through this method, robots can be used to intelligently collect, fold, and organize clothing, achieving a positive interaction between robots and humans.

[0045] The following will combine Figures 2 to 10 The method according to embodiments of this disclosure is described in detail. For ease of understanding, the specific data mentioned in the following description are exemplary and not intended to limit the scope of this disclosure. It is understood that the embodiments described below may also include additional actions not shown and / or actions shown may be omitted, and the scope of this disclosure is not limited in this respect.

[0046] Figure 2 A flowchart of a task execution method 200 according to some embodiments of the present disclosure is shown. Method 200 can be applied to intelligent robots and can be executed by a task execution device, which may be, for example, a standalone device or system. The device can be implemented in software and / or hardware. The method 200 will now be illustrated schematically using a task execution device as an example. Method 200 includes blocks 202, 204, and 206.

[0047] like Figure 2 As shown in box 202, the garment's status is determined, indicating whether the garment can be removed and stored. To collect and store garments, their status needs to be determined; the garment's status determines whether it can be removed and stored. Only garments that meet the conditions for removal and storage can be taken down. Figure 1 As shown, whether clothes can be removed from the drying rack depends on their condition. For example, if the clothes are dry enough to meet a preset dryness level, then they can be removed.

[0048] In box 204, in response to a clothing status indication that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information and a predetermined instruction. The action model is a multimodal model. (See reference) Figure 1 If the clothes on the drying rack are removable, a multimodal motion model can generate a motion strategy that the robot can execute based on pre-defined prompts and clothing information. This allows the robot to perform actions according to the pre-defined prompts, thereby meeting the user's needs regarding clothing and household chores. For example, clothing information could include the material, size, type, and ownership of the clothing, as well as its location information, including its current location, target location, and transfer location. For instance, a pre-defined prompt could instruct the robot to remove the clothes from the drying rack and collect them to hang in a closet. In this case, the motion model can generate an execution motion strategy based on the position of the clothes on the drying rack and the target storage location, such as the closet. For example, the motion strategy could be: [Grab the clothes, move to the target location, and put the clothes in].

[0049] In box 206, the intelligent robot executes the motion strategy. Once the motion strategy described in box 204 is generated, the robot can perform corresponding actions based on that strategy. For example, it can use a robotic arm and gripper to pick up clothing, use the chassis wheels to move to the target location, and use the robotic arm and gripper again to place the clothing.

[0050] Based on the above method 200, it is possible to assist humans in handling clothing and household chores, freeing up human hands. According to method 200, it is first determined whether the clothing can be removed and stored, that is, the clothing status is determined. If the clothing can be removed and stored, then a multimodal motion model can generate a motion strategy that the robot can execute based on the clothing information and predetermined instructions. The robot then executes the motion strategy to provide services that assist humans in managing clothing, thereby improving the quality of human life. In other words, through this method, robots can be used to intelligently collect, fold, and organize clothing, achieving a positive interaction between robots and humans.

[0051] In implementing robot-assisted clothing management, visual devices, such as cameras, are needed to capture images of the clothing to determine information such as material, size, ownership, and thickness. This information allows the robot to be controlled based on subsequent actions and pre-defined prompts. For example, Figure 3 A schematic diagram 300 illustrates determining clothing information based on clothing images according to some embodiments of the present disclosure. For example... Figure 3 As shown, at 310, an image of the clothing is acquired. In some embodiments, a camera configured on the robot can be used to acquire images of the clothing, as well as other environmental images. After acquiring the image of the clothing, clothing information such as clothing material 302, clothing size 304, clothing ownership 306, and clothing thickness 308 can be determined. This clothing information can be used to subsequently generate motion strategies for the robot.

[0052] After obtaining the relevant clothing information, the robot can then be controlled to perform corresponding actions based on this information. For example, Figure 4 A schematic diagram of an example flow 400 for task execution to achieve clothing management according to some embodiments of the present disclosure is shown. Figure 4 As shown, at step 410, the operation of determining the status of clothing is performed. In order to collect and store clothing, it is necessary to determine the status of the clothing, which indicates whether the clothing can be removed and stored. Only clothing that meets the conditions for removal and storage can be removed.

[0053] At 420, a garment retrieval judgment operation is performed. As described at 410, only garments that meet the conditions for being removed and stored can be removed. For example, Figure 5 A schematic diagram of an example process 500 for determining whether to retrieve clothing based on the condition of the clothing, according to some embodiments of the present disclosure, is shown. For ease of explanation, it will be described below in conjunction with... Figure 5 To describe. For example... Figure 5 As shown, the example process 500 can be divided into dryness determination, drying time determination, and weather determination.

[0054] At position 502, a dryness determination operation can be performed. In some embodiments, the dryness of the clothing can be used to determine whether it can be retrieved and stored. For example, if the dryness of the clothing reaches a preset dryness level, then the clothing can be removed by the robot and stored in the target location. For example, clothing A has a dryness level of 90%, which has reached or exceeded the preset dryness level, and can be removed, while clothing B has a dryness level of 85%, and according to the preset dryness level, it needs to be aired for a while longer. Dryness level can be replaced by terms such as humidity to describe the dryness or wetness of clothing.

[0055] In step 504, a drying time determination operation can be performed. In some embodiments, it can be determined whether clothing can be retrieved and stored based on the drying time. For example, if the continuous drying time of clothing reaches a predetermined drying time, then the clothing can be retrieved and stored. In some embodiments, the required drying time of clothing can be determined according to the material of the clothing. For example, cotton clothing can be dried in the sun for about 2 hours, while wool clothing should be dried for half a day.

[0056] At 506, a weather condition determination operation can be performed. In some embodiments, it can be determined whether clothing can be retrieved and stored based on the weather condition. For example, if the weather forecast predicts light rain while the clothing is being dried, the clothing can be retrieved in advance and stored at a target location.

[0057] This automatic method of determining the condition of clothing saves users the cost of monitoring their garments. It also accurately assesses the dryness of clothing, extending its lifespan and improving the quality of life.

[0058] Alternatively, users can customize the criteria for judging the condition of clothing. For example, for a particular garment, a user might decide that it only needs to be aired for one hour, and once that time is up, it can be retrieved and stored. Alternatively, users can force the garment to be set to a condition where it can be retrieved.

[0059] Back Figure 4 Once it is determined that the clothing can be retrieved and stored, at step 430, the operation can be performed by an intelligent robot. For example, the robot can be controlled to perform the operation of retrieving the clothing 431, the operation of folding the clothing 432, the operation of moving the clothing 433, and the operation of storing the clothing 434.

[0060] In some embodiments, when it is determined that the clothing can be retrieved and stored, a motion model can be used to generate a motion strategy that the robot can execute based on a predetermined prompt and clothing information, so that the robot can perform actions according to the predetermined prompt, thereby meeting the user's needs regarding clothing and housework.

[0061] In some embodiments, the pre-set prompts can be automatically set by the user. For example, pre-set prompts can be entered by the user via text or voice, and can be automatically applied under certain conditions. For instance, the user can choose to hang the collected clothes directly in the cabinet, or the user can choose to fold the collected clothes before putting them in the cabinet. The user can then set different pre-set prompts so that the robot can automatically perform the corresponding actions according to their needs. Alternatively, the pre-set prompts can also be automatically generated using a multimodal language model after learning the user's habits of collecting clothes.

[0062] In some embodiments, the predetermined prompt may include a first prompt, which may be set by the user through input or automatically generated by learning human habits. For example, Figures 6A-6B Schematic diagrams of examples 600A-600B, which control a robot to perform clothing management according to a first predetermined prompt, are shown below, representing some embodiments of the present disclosure. For ease of explanation, the following will be combined with... Figures 6A-6B To describe.

[0063] refer to Figure 6A In some embodiments, the first predetermined prompt 602 may be an instruction to the robot to remove the clothes from the drying rack and collect them for hanging in the cabinet. If the determination of removing the clothes is correct, then at 601, an image of the clothes can be acquired. In some embodiments, the location of the clothes, i.e., the clothing source location 604, can be located based on the clothing image so that the robot's robotic arm can be subsequently controlled to move to the location of the clothes.

[0064] Meanwhile, taking a "cabinet" as an example, the motion model 603 can also determine the location information of the "cabinet" based on the predetermined prompt 602 and the home environment map 605. In some embodiments, the home environment map 605 can be pre-configured in the motion model for use in organizing and moving clothes for the user in the home environment. Alternatively, the home environment map can be constructed by the robot based on the SLAM algorithm or imported by the user.

[0065] The action model 603 can generate a first action strategy 607 based on the position of the clothes on the drying rack and the target storage location 606, such as the wardrobe location. For example, the first action strategy 607 could be [grab the clothes, move them to the target location, and put them in]. Figure 6B The first action strategy associated with the first predetermined prompt is shown. Combined with... Figure 6B In 6071, the operation of grasping clothing can be performed. In some embodiments, the position of the clothing can be located by using images captured by the camera configured on the robot, and the robotic arm can be controlled to move to the location of the clothing. For example, the robotic arm and grippers can be used to gently grasp the clothing and smoothly remove it from the clothes rack without damaging it.

[0066] In section 6072, the robot can move to the target location. It can use its chassis wheels to move to the target location, i.e., the "cabinet." In section 6073, the robot can place clothing inside. It can again use its robotic arm and grippers to place the clothing into the designated location, i.e., the "cabinet."

[0067] In some embodiments, the target storage location 606 may be a folding platform, which may be built into the robot or a fixed location.

[0068] Using examples 600A and 600B, robots can assist humans in automatically sorting clothes taken from clotheslines, freeing up human hands and improving the user experience.

[0069] In some embodiments, the predetermined prompt may include a second prompt, which may be set by the user through input or automatically generated by learning human habits. For example, Figures 7A-7B Schematic diagrams of examples 700A-700B, which control a robot to perform clothing management according to a second predetermined prompt, are shown according to some embodiments of the present disclosure. For ease of explanation, the following will be combined with... Figures 7A-7B To describe.

[0070] refer to Figure 7A In some embodiments, the second predetermined prompt 702 may be an instruction to the robot to fold the removed clothing. At 701, an image of the clothing is acquired. In some embodiments, the motion model 703 may determine clothing attribute information 704 of the clothing based on the clothing image. The clothing attribute information 704 may include clothing material 7041, clothing thickness 7042, clothing size 7043, and clothing type, etc.

[0071] The action model 703 can generate a second action strategy 705 based on clothing attribute information and the second cue 702. For example, the second action strategy 705 could be [identify clothing, unfold clothing, fold or fold clothing multiple times, adjust and organize clothing, and place it in a predetermined position].

[0072] Figure 7B A second action strategy related to the second predetermined prompt is shown. Combined with... Figure 7B In section 7051, the operation of recognizing clothing can be performed. For example, a camera can be used to capture images of clothing to identify its placement and orientation. For instance, the angle at which clothing is positioned on a flat surface can be identified. In section 7052, the operation of unfolding clothing can be performed. For example, a robotic arm and end effectors such as grippers or clamps can be used to grasp the edges or specific parts of the clothing, then lift the clothing, suspending it in the air for subsequent operations. Also, if the clothing is lumped together, a robotic arm and grippers can be used to flatten it.

[0073] In section 7053, perform a folding or splitting operation. For example, after flattening, the garment can be folded according to its type and the folding order associated with that type. For a shirt, the sleeves can be folded inwards first, then the garment can be folded in half from the middle; for trousers, the pant legs can be aligned before folding horizontally or vertically. In section 7054, perform adjustment and processing operations. For example, after completing the initial folding, the garment can be checked and adjusted to ensure it is in a neat shape. In section 7055, perform a placement operation at a predetermined location. For example, after folding, the garment can be moved outside the folding area or to a fixed location.

[0074] With examples 700A and 700B, robots can assist humans in automatically folding clothes taken from clotheslines, freeing up human hands and improving the user experience.

[0075] In some embodiments, the predetermined prompt may include a third prompt, which may be set by the user through input or automatically generated by learning human habits. For example, Figures 8A-8B Schematic diagrams of examples 800A-800B, which control a robot to perform clothing management according to a third predetermined prompt, are shown according to some embodiments of the present disclosure. For ease of explanation, the following will be combined with... Figures 8A-8B To describe.

[0076] refer to Figure 8A In some embodiments, the third predetermined prompt 802 may be an instruction to the robot to sort and categorize the folded and removed clothing into a designated location. At 801, an image of the clothing is acquired. In some embodiments, the motion model 803 may determine the clothing classification information 804 based on the clothing image. The clothing classification information 804 indicates which user the garment belongs to. For example, it may be identified that the garment belongs to the mother.

[0077] The target storage location of clothing (805) can be determined based on category information. For example, if the shirt belongs to the mother, and mother's clothing is always placed in area A, then the target location can be determined to be in area A. Similarly, if the pants belong to the child, and child's clothing is always placed in area B, then the target location can be determined to be in area B.

[0078] Simultaneously, the motion model 803 can determine the location information of "Area A" / "Area B" based on "Area A" / "Area B" and in conjunction with the home environment map 605. In some embodiments, the home environment map 605 can be pre-configured in the motion model for use in organizing and moving clothes for the user in the home environment. Alternatively, the home environment map can be constructed by the robot based on a SLAM algorithm or imported by the user.

[0079] At this point, the action model 803 can generate a third action strategy 806 based on the target storage location information of the clothing (such as area A) and the third pre-defined prompt 802. For example, assuming that the clothing has already been folded, action strategy 1 could be [determine the fixed location of the clothing, place the clothing in the portable container, move the portable container to the target location, and place the clothing in the fixed location].

[0080] If the robot does not have a portable container, action strategy 2 can also be [determine the fixed position for placing the clothes, clamp the clothes with a gripper, move to the target position, and place the clothes in the fixed position].

[0081] Figure 8B Action strategy 2 related to the third predetermined cue is shown. Combined with... Figure 8B The robot can then perform corresponding actions based on action strategy 2. At step 8062, it performs the operation of gripping clothing. The robot can directly grip the clothing using its gripper or clamp, such as the mother's pants mentioned above. At step 8064, it performs the operation of moving to a fixed position. The robot can use its chassis wheels to move to the target position, such as area A. At step 8066, it performs the operation of placing the clothing in the fixed position. The robot can again use its robotic arm and gripper to place the clothing.

[0082] With examples 800A and 800B, robots can assist humans in automatically folding clothes taken from clotheslines and storing them in a fixed location, freeing up human hands and improving the user experience.

[0083] In some embodiments, after the robot completes the clothing management action, a report with timestamps of each action with the action execution strategy can be generated. This report can then be used for subsequent optimization and analysis to control the robot's actions.

[0084] In some embodiments, feedback from the user after performing clothing management actions on the robot can also be obtained, and the multimodal action model configured for the robot can be adjusted based on the feedback.

[0085] In some embodiments, the robot may be equipped with visual acquisition devices such as a camera, a robotic arm, a voice acquisition module, a voice output module, a display screen, and a folding platform. The voice acquisition module can be used to obtain predetermined prompts from the user, the voice output module can output a generated report to the user, the display screen can be used to display the generated report to the user, and the built-in folding platform can be used to fold clothing for the user.

[0086] Combination Figures 3-8B Robots can assist humans in managing their clothing, thereby improving their quality of life.

[0087] Figure 9 A block diagram of a task execution apparatus 900 according to some embodiments of the present disclosure is shown. Figure 9 As shown, the device 900 includes a clothing state determination module 902, configured to determine the clothing state, which indicates whether the clothing can be removed and stored. The device 900 also includes a motion strategy generation module 904, configured to generate a motion strategy based on the clothing information and predetermined instructions from a motion model, in response to the clothing state indicating that the clothing can be removed and stored. The motion model is a multimodal model. Furthermore, the device 900 includes an execution module 906, configured for the robot to execute the motion strategy.

[0088] Figure 10 A block diagram of a device 1000 capable of implementing various embodiments of the present disclosure is shown. For example... Figure 10 As shown, device 1000 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 1001, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 1002 or loaded from storage unit 1008 into random access memory (RAM) 1003. Various programs and data required for the operation of device 1000 can also be stored in RAM 1003. The CPU / GPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004. Although not shown in... Figure 10 As shown, device 1000 may also include a coprocessor.

[0089] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0090] The various methods or processes described above can be executed by CPU / GPU 1001. For example, in some embodiments, the methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by CPU / GPU 1001, one or more steps or actions in the methods or processes described above can be performed.

[0091] In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.

[0092] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0093] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, a local area network (LAN), a wide area network (WAN), and / or a wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0094] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​and conventional procedural programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0095] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0096] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0098] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

[0099] The following are some example implementations of this disclosure.

[0100] Example 1. A task execution method, characterized in that it is applicable to intelligent robots and includes:

[0101] Determine the status of the clothing, which indicates whether the clothing can be removed and stored.

[0102] In response to the clothing status indicating that the clothing can be removed and stored, an action strategy is generated by an action model based on the clothing information and a predetermined instruction; the action model is a multimodal model.

[0103] The action strategy is executed by the intelligent robot.

[0104] Example 2. According to the method described in Example 1, determining the garment's condition includes:

[0105] The condition of the clothing is determined based on at least one of the following: dryness of the clothing, continuous drying time, and weather conditions.

[0106] Example 3. The method according to any one of Examples 1-2, wherein determining the condition of the clothing based on at least one of the dryness of the clothing, continuous airing time, and weather conditions includes:

[0107] In response to the dryness level meeting a predetermined dryness level, it is determined that the garment can be removed and stored; or

[0108] In response to the continuous drying time meeting the required drying time, it is determined that the garment can be removed and stored, wherein the required drying time is determined based on the fabric of the garment; or

[0109] In response to the weather conditions meeting a predetermined weather condition, it is determined that the clothing can be removed and stored.

[0110] Example 4. The method according to any one of Examples 1-3 further includes:

[0111] Based on the image of the garment, determine the material of the garment; and

[0112] Based on the material of the clothing, the appropriate drying time for the clothing is determined.

[0113] Example 5. The method according to any one of Examples 1-4, wherein the predetermined prompt includes a first predetermined prompt instructing the garment to be removed from the source location and placed in the target location.

[0114] Example 6. According to any one of Examples 1-5, the clothing information includes the source location information of the clothing and the target storage location information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0115] The source location information and the target storage location information are determined, wherein the source location is determined based on the image of the clothing; and

[0116] The action model generates a first action strategy based on the source location information, the target storage location information, and the first predetermined prompt.

[0117] Example 7. The method according to any one of Examples 1-6, wherein determining the source location information and the target storage location information includes:

[0118] The motion model determines the source location information based on the image of the clothing; and

[0119] The target location information is determined by the action model based on the home environment map.

[0120] Example 8. The method according to any one of Examples 1-7, wherein the target location is a folding platform.

[0121] Example 9. The method according to any one of Examples 1-8, wherein the predetermined prompt includes a second predetermined prompt, the second predetermined prompt instructing the folding of the garment.

[0122] Example 10. According to any one of Examples 1-9, the clothing information further includes the attribute information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0123] The motion model generates a second motion strategy based on the attribute information and the second predetermined prompt, wherein the attribute information is determined based on the image of the clothing.

[0124] Example 11. According to any one of Examples 1-10, the attribute information includes at least one of the size, type, material, and thickness of the garment.

[0125] Example 12. The method according to any one of Examples 1-11, wherein the predetermined prompt includes a third predetermined prompt, the third predetermined prompt instructing the garment to be stored at a target location.

[0126] Example 13. The method according to any one of Examples 1-12, wherein the clothing information includes the classification information of the clothing, and in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0127] The action model determines the target storage location information of the clothing based on the classification information, wherein the classification information indicates the ownership of the clothing; and

[0128] The action model generates a third action strategy based on the target storage location information and the third predetermined prompt.

[0129] Example 14. The method according to any one of Examples 1-13 further includes:

[0130] Determine the timestamp of the intelligent robot executing the action strategy; and

[0131] An execution report is generated for the clothing, the execution report including the timestamp.

[0132] Example 15. The method according to any one of Examples 1-14 further includes:

[0133] Obtain user feedback after the intelligent robot executes the action strategy; and

[0134] Based on the feedback, the action model is optimized.

[0135] Example 16. The method according to any one of Examples 1-15 further includes:

[0136] The predetermined prompt is determined based on user input.

[0137] Example 17. According to any one of Examples 1-16, the intelligent robot is equipped with a vision acquisition device, a robotic arm, a voice acquisition module, a voice output module, a display screen, and a folding platform.

[0138] Example 18. A task execution device, characterized in that it is suitable for intelligent robots and comprises:

[0139] The clothing status determination module is configured to determine the clothing status, which indicates whether the clothing can be removed and stored.

[0140] An action strategy generation module is configured to, in response to a clothing status indication that the clothing can be removed and stored, generate an action strategy based on clothing information and a predetermined indication using an action model, wherein the action model is a multimodal model; and

[0141] The execution module is configured to have the intelligent robot execute the action strategy.

[0142] Example 19. The apparatus according to Example 18, wherein the clothing state determination module includes:

[0143] The first determining module is configured to determine the condition of the clothing based on at least one of the clothing's dryness, continuous airing time, and weather conditions.

[0144] Example 20. The apparatus according to any one of Examples 18-19, wherein the first determining module comprises:

[0145] The second determining module is configured to determine that the clothing can be removed and stored in response to the dryness level meeting a predetermined dryness level; or

[0146] The second determining module is configured to determine that the clothing can be removed and stored in response to the continuous drying time meeting the required drying time, wherein the required drying time is determined based on the fabric of the clothing; or

[0147] The third determining module is configured to determine that the clothing can be removed and stored in response to the weather condition meeting a predetermined weather condition.

[0148] Example 21. The apparatus according to any one of Examples 18-20 further includes:

[0149] The fourth determining module is configured to determine the fabric material of the garment based on an image of the garment; and

[0150] The fifth determining module is configured to determine the drying time of the clothing based on the clothing material.

[0151] Example 22. The apparatus according to any one of Examples 18-21, wherein the predetermined prompt includes a first predetermined prompt instructing the garment to be removed from the source location and placed in the target location.

[0152] Example 23. The apparatus according to any one of Examples 18-22, wherein the clothing information includes source location information of the clothing and target storage location information of the clothing, wherein the action strategy generation module includes:

[0153] The sixth determining module is configured to determine the source location information and the target storage location information, wherein the source location is determined based on the image of the clothing; and

[0154] The first generation module is configured to generate a first action strategy based on the source location information, the target storage location information, and the first predetermined prompt by the action model.

[0155] Example 24. The apparatus according to any one of Examples 18-23, wherein the sixth determining module comprises:

[0156] The seventh determining module is configured to determine the source location information based on the image of the clothing by the motion model; and

[0157] The eighth determining module is configured to determine the target location information based on the home environment map by the action model.

[0158] Example 25. The apparatus according to any one of Examples 18-24, wherein the target location is a folding platform.

[0159] Example 26. The apparatus according to any one of Examples 18-25, wherein the predetermined prompt includes a second predetermined prompt instructing the folding of the garment.

[0160] Example 27. The apparatus according to any one of Examples 18-26, wherein the clothing information further includes attribute information of the clothing, wherein the action strategy generation module includes:

[0161] The second generation module is configured to generate a second action strategy based on the action model and the second predetermined prompt, wherein the attribute information is determined based on the image of the clothing.

[0162] Example 28. The apparatus according to any one of Examples 18-27, wherein the attribute information includes at least one of the size, type, material, and thickness of the garment.

[0163] Example 29. The apparatus according to any one of Examples 18-28, wherein the predetermined prompt includes a third predetermined prompt instructing the garment to be stored at a target location.

[0164] Example 30. The apparatus according to any one of Examples 18-29, wherein the clothing information includes classification information of the clothing, and the motion strategy generation module includes:

[0165] The ninth determining module is configured to determine the target storage location information of the clothing based on the classification information by the action model, wherein the classification information indicates the ownership of the clothing; and

[0166] The third generation module is configured to generate a third action strategy based on the target storage location information and the third predetermined prompt by the action model.

[0167] Example 31. The apparatus according to any one of Examples 18-30 further includes:

[0168] The tenth determining module is configured to determine the timestamp of the intelligent robot executing the action strategy; and

[0169] The fourth generation module is configured to generate an execution report for the clothing, the execution report including the timestamp.

[0170] Example 32. The apparatus according to any one of Examples 18-31 further includes:

[0171] The acquisition module is configured to acquire user feedback after the intelligent robot executes the action strategy; and

[0172] The optimization module is configured to optimize the action model based on the feedback.

[0173] Example 33. The apparatus according to any one of Examples 18-32 further includes:

[0174] The eleventh determining module is configured to determine the predetermined prompt based on user input.

[0175] Example 34. The apparatus according to any one of Examples 18-33, wherein the intelligent robot is configured with a vision acquisition device, a robotic arm, a voice acquisition module, a voice output module, a display screen, and a folding platform.

[0176] Example 35. An electronic device comprising:

[0177] Processor; and

[0178] A memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the electronic device to perform actions, the actions including:

[0179] Determine the status of the clothing, which indicates whether the clothing can be removed and stored.

[0180] In response to the clothing status indicating that the clothing can be removed and stored, an action strategy is generated by an action model based on the clothing information and a predetermined instruction; the action model is a multimodal model.

[0181] The action strategy is executed by the intelligent robot.

[0182] Example 36. The electronic device according to Example 35, wherein determining the garment's garment state includes:

[0183] The condition of the clothing is determined based on at least one of the following: dryness of the clothing, continuous drying time, and weather conditions.

[0184] Example 37. An electronic device according to any one of Examples 35-36, wherein determining the condition of the clothing based on at least one of the dryness of the clothing, continuous drying time, and weather conditions includes:

[0185] In response to the dryness level meeting a predetermined dryness level, it is determined that the garment can be removed and stored; or

[0186] In response to the continuous drying time meeting the required drying time, it is determined that the garment can be removed and stored, wherein the required drying time is determined based on the fabric of the garment; or

[0187] In response to the weather conditions meeting a predetermined weather condition, it is determined that the clothing can be removed and stored.

[0188] Example 38. The electronic device according to any one of Examples 35-37 further includes:

[0189] Based on the image of the garment, determine the material of the garment; and

[0190] Based on the material of the clothing, the appropriate drying time for the clothing is determined.

[0191] Example 39. An electronic device according to any one of Examples 35-38, wherein the predetermined prompt includes a first predetermined prompt instructing the garment to be removed from a source location and placed in a target location.

[0192] Example 40. An electronic device according to any one of Examples 35-39, wherein the clothing information includes source location information of the clothing and target storage location information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0193] The source location information and the target storage location information are determined, wherein the source location is determined based on the image of the clothing; and

[0194] The action model generates a first action strategy based on the source location information, the target storage location information, and the first predetermined prompt.

[0195] Example 41. An electronic device according to any one of Examples 35-40, wherein determining the source location information and the target storage location information includes:

[0196] The motion model determines the source location information based on the image of the clothing; and

[0197] The target location information is determined by the action model based on the home environment map.

[0198] Example 42. An electronic device according to any one of Examples 35-41, wherein the target location is a folding platform.

[0199] Example 43. The electronic device according to any one of Examples 35-42, wherein the predetermined prompt includes a second predetermined prompt instructing the folding of the clothing.

[0200] Example 44. An electronic device according to any one of Examples 35-43, wherein the clothing information further includes attribute information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0201] The motion model generates a second motion strategy based on the attribute information and the second predetermined prompt, wherein the attribute information is determined based on the image of the clothing.

[0202] Example 45. The electronic device according to any one of Examples 35-44, wherein the attribute information includes at least one of the size, type, material, and thickness of the clothing.

[0203] Example 46. The electronic device according to any one of Examples 35-45, wherein the predetermined prompt includes a third predetermined prompt instructing the garment to be stored at a target location.

[0204] Example 47. An electronic device according to any one of Examples 35-46, wherein the clothing information includes classification information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including:

[0205] The action model determines the target storage location information of the clothing based on the classification information, wherein the classification information indicates the ownership of the clothing; and

[0206] The action model generates a third action strategy based on the target storage location information and the third predetermined prompt.

[0207] Example 48. The electronic device according to any one of Examples 35-47 further includes:

[0208] Determine the timestamp of the intelligent robot executing the action strategy; and

[0209] An execution report is generated for the clothing, the execution report including the timestamp.

[0210] Example 49. The electronic device according to any one of Examples 35-48 further includes:

[0211] Obtain user feedback after the intelligent robot executes the action strategy; and

[0212] Based on the feedback, the action model is optimized.

[0213] Example 50. The electronic device according to any one of Examples 35-49 further includes:

[0214] The predetermined prompt is determined based on user input.

[0215] Example 51. An electronic device according to any one of Examples 35-50, wherein the intelligent robot is configured with a vision acquisition device, a robotic arm, a voice acquisition module, a voice output module, a display screen, and a folding platform.

[0216] Example 52. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of Examples 1 to 17.

[0217] Example 53. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of Examples 1 to 17.

[0218] Although this disclosure has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A task execution method, characterized in that, Suitable for intelligent robots, including: Determine the status of the clothing, which indicates whether the clothing can be removed and stored. In response to the clothing status indicating that the clothing can be removed and stored, an action strategy is generated by an action model based on the clothing information and a predetermined instruction; the action model is a multimodal model. The action strategy is executed by the intelligent robot.

2. The method according to claim 1, wherein determining the garment's condition includes: The condition of the clothing is determined based on at least one of the following: dryness of the clothing, continuous drying time, and weather conditions.

3. The method according to claim 2, wherein determining the condition of the clothing based on at least one of the dryness of the clothing, continuous airing time, and weather conditions includes: In response to the dryness level meeting a predetermined dryness level, it is determined that the clothing can be removed and stored. or In response to the continuous drying time meeting the required drying time, it is determined that the garment can be removed and stored, wherein the required drying time is determined based on the fabric of the garment; or In response to the weather conditions meeting a predetermined weather condition, it is determined that the clothing can be removed and stored.

4. The method according to claim 2, further comprising: Based on the image of the garment, determine the material of the garment; as well as Based on the material of the clothing, the appropriate drying time for the clothing is determined.

5. The method of claim 1, wherein the predetermined prompt includes a first predetermined prompt, the first predetermined prompt instructing the garment to be removed from the source location and placed in the target location.

6. The method according to claim 5, wherein the clothing information includes the source location information of the clothing and the target storage location information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including: The source location information and the target storage location information are determined, wherein the source location is determined based on the image of the clothing; as well as The action model generates a first action strategy based on the source location information, the target storage location information, and the first predetermined prompt.

7. The method according to claim 6, wherein determining the source location information and the target storage location information comprises: The motion model determines the source location information based on the image of the clothing; as well as The target location information is determined by the action model based on the home environment map.

8. The method according to claim 6, wherein the target location is a folding platform.

9. The method of claim 5, wherein the predetermined prompt includes a second predetermined prompt, the second predetermined prompt instructing the folding of the garment.

10. The method according to claim 9, wherein the clothing information further includes the attribute information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including: The motion model generates a second motion strategy based on the attribute information and the second predetermined prompt, wherein the attribute information is determined based on the image of the clothing.

11. The method according to claim 10, wherein the attribute information includes at least one of the size, type, material, and thickness of the garment.

12. The method of claim 9, wherein the predetermined prompt includes a third predetermined prompt, the third predetermined prompt instructing the garment to be stored at a target location.

13. The method of claim 12, wherein the clothing information includes the classification information of the clothing, wherein in response to the clothing status indicating that the clothing can be removed and stored, the action model generates an action strategy based on the clothing information of the clothing and a predetermined prompt, including: The action model determines the target storage location information of the clothing based on the classification information, wherein the classification information indicates the ownership of the clothing; as well as The action model generates a third action strategy based on the target storage location information and the third predetermined prompt.

14. The method according to claim 1, further comprising: Determine the timestamp of the intelligent robot executing the action strategy; as well as An execution report is generated for the clothing, the execution report including the timestamp.

15. The method of claim 14, further comprising: Obtain user feedback after the intelligent robot executes the action strategy; as well as Based on the feedback, the action model is optimized.

16. The method of claim 15, further comprising: The predetermined prompt is determined based on user input.

17. The method according to claim 1, wherein the intelligent robot is equipped with a vision acquisition device, a robotic arm, a voice acquisition module, a voice output module, a display screen, and a folding platform.

18. A task execution device, characterized in that, Suitable for intelligent robots, including: The clothing status determination module is configured to determine the clothing status, which indicates whether the clothing can be removed and stored. An action strategy generation module is configured to, in response to a clothing status indication that the clothing can be removed and stored, generate an action strategy based on clothing information and a predetermined indication using an action model, wherein the action model is a multimodal model; and The execution module is configured to have the intelligent robot execute the action strategy.

19. An electronic device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1 to 17.

20. A computer program product tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions that, when executed, cause a machine to perform the method according to any one of claims 1 to 17.

Images