Humanoid robot control method based on clothing storage and related products

Abstract

The embodiment of the present invention discloses a humanoid robot control method based on clothing storage and related products, the method comprising: obtaining clothing detection data of target clothing in a target area through a visual component; determining a target available storage area in a target storage space according to the clothing detection data; obtaining attribute information of the target available storage area; obtaining storage features corresponding to the target available storage area; determining a first storage action corresponding to a hand component based on the attribute information and the storage features, the first storage action being used to perform a target operation on the target clothing; obtaining a target storage height corresponding to the target available storage area; determining a second storage action corresponding to a foot component based on a first current height and a target storage height of the humanoid robot, the second storage action being used to adjust the height of the center of gravity of the humanoid robot; and controlling the humanoid robot to store the target clothing in the target available storage area based on the first storage action and the second storage action.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a humanoid robot control method based on clothing storage and related products. Background Art

[0002] As living standards continue to improve, people's pursuit of living environment and quality of life is increasing. In daily life, clothing is an important element, and clothing storage is particularly important for improving the cleanliness and comfort of the home. As people's spending power continues to increase, the number of clothes they buy is increasing. Clothes for different seasons and occasions need to be stored to prevent the accumulation of clothes.

[0003] However, there are many types and materials of clothing, and different types of clothing require different storage methods and storage locations. For example, silk clothing, wool clothing, dresses and other special materials or styles of clothing require special storage methods, otherwise they are easily damaged, which makes people spend a lot of time and energy on clothing storage.

[0004] Therefore, there is an urgent need for a humanoid robot control method based on clothing storage, so that the user's clothing can be stored in daily life, saving the user's time and energy spent on clothing storage. Summary of the invention

[0005] In order to solve the above problems, the embodiments of the present invention provide a humanoid robot control method based on clothing storage and related products, which can control the humanoid robot to store various clothes of the user, so as to save the user's time and energy spent on clothing storage.

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling a humanoid robot based on clothing storage, the method being applied to a controller of a humanoid robot, the humanoid robot comprising a visual component, a foot component and a hand component; the method comprising:

[0007] Acquiring clothing detection data of target clothing in a target area through the visual component;

[0008] determining a target available storage area in a target storage space according to the clothing detection data;

[0009] Acquire attribute information of the target available storage area;

[0010] Acquire a storage feature corresponding to the target available storage area, wherein the storage feature includes one of the following: folding, hanging, and placing;

[0011] Determining a first storage action corresponding to the hand component based on the attribute information and the storage feature, wherein the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: a folding operation, a hanging operation, and a placing operation;

[0012] Obtaining a target storage height corresponding to the target available storage area;

[0013] Determining a second storage action corresponding to the foot assembly based on a first current height of the humanoid robot and the target storage height, wherein the second storage action is used to adjust the center of gravity height of the humanoid robot;

[0014] The humanoid robot is controlled to store the target clothing in the target available storage area based on the first storage action and the second storage action.

[0015] In a second aspect, an embodiment of the present invention provides a humanoid robot control device based on clothing storage, the device is applied to a humanoid robot, the humanoid robot includes a visual component, a foot component and a hand component; the device includes an acquisition unit and a processing unit;

[0016] The acquisition unit is used to acquire clothing detection data of target clothing in a target area through the visual component;

[0017] The processing unit is used to determine a target available storage area in a target storage space according to the clothing detection data;

[0018] Acquire attribute information of the target available storage area;

[0019] Acquire a storage feature corresponding to the target available storage area, wherein the storage feature includes one of the following: folding, hanging, and placing;

[0020] Determining a first storage action corresponding to the hand component based on the attribute information and the storage feature, wherein the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: a folding operation, a hanging operation, and a placing operation;

[0021] Obtaining a target storage height corresponding to the target available storage area;

[0022] Determining a second storage action corresponding to the foot assembly based on a first current height of the humanoid robot and the target storage height, wherein the second storage action is used to adjust the center of gravity height of the humanoid robot;

[0023] The humanoid robot is controlled to store the target clothing in the target available storage area based on the first storage action and the second storage action.

[0024] In a third aspect, an embodiment of the present invention provides a humanoid robot, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the humanoid robot performs the method described in the first aspect.

[0025] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0026] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method described in the first aspect.

[0027] Implementing the embodiments of the present application has the following beneficial effects:

[0028] In an embodiment of the present application, clothing detection data of target clothing in a target area is first obtained through a visual component, and then a target available storage area in a target storage space is determined according to the clothing detection data, and attribute information of the target available storage area is obtained, as well as storage features corresponding to the target available storage area are obtained, and the storage features include one of the following: folding, hanging, and placing. Then, a first storage action corresponding to a hand component is determined based on the attribute information and the storage features, and the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: folding operation, hanging operation, and placing operation, and a target storage height corresponding to the target available storage area is obtained, and a second storage action corresponding to a foot component is determined based on a first current height and a target storage height of the humanoid robot, and the second storage action is used to adjust the height of the center of gravity of the humanoid robot. Finally, based on the first storage action and the second storage action, the humanoid robot is controlled to store the target clothing in the target available storage area. Therefore, the target available storage area is determined according to the clothing detection data of the target clothing, and the first storage action and the second storage action of the humanoid robot are determined by acquiring the attribute information and storage characteristics of the storage area. The humanoid robot can be controlled to store the target clothing, saving the user's time and energy spent on clothing storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 is a schematic structural diagram of a humanoid robot provided in an embodiment of the present application;

[0031] Figure 2 is a flow chart of a humanoid robot control method based on clothing storage provided by an embodiment of the present application;

[0032] Figure 3 is a schematic diagram of a clothing storage action of a humanoid robot provided in an embodiment of the present application;

[0033] Figure 4 is a schematic diagram of the positions of a first garment and a second garment in a target area provided by an embodiment of the present application;

[0034] Figure 5 is a schematic diagram of a clothing stacking relationship provided in an embodiment of the present application;

[0035] Figure 6 It is a structural schematic diagram of a humanoid robot control device based on clothing storage provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other steps or modules inherent to these processes, methods, products or devices.

[0038] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] The humanoid robot control method based on clothing storage provided in the embodiment of the present application is applied to the controller of the humanoid robot, see Figure 1 , Figure 1 is a schematic diagram of the structure of a humanoid robot provided in an embodiment of the present application, such as Figure 1As shown, the humanoid robot includes a visual component 11, a hand component 12 and a foot component 13. Among them, the visual component 11 can identify clothes and storage areas, detect the state of clothes and plan the storage path. The visual component 11 of the humanoid robot can scan and identify the surrounding environment. In the process of storing clothes, the visual component 11 can accurately identify different types of clothes, as well as the colors, patterns and materials of various clothes. At the same time, the visual component 11 can also identify different storage areas, such as wardrobes, drawers, storage boxes, etc., and determine their position, size and shape and other information. The visual component 11 can also detect the state of clothes, such as cleanliness, wrinkles, whether there is damage, etc. After determining the clothes and storage areas, the visual component 11 can combine other sensor information, such as distance sensors, position sensors, etc., to plan the best storage path. The visual component 11 ensures that the humanoid robot can move safely and efficiently during the storage process based on factors such as obstacles in the surrounding environment, the size and weight of clothes. The hand assembly 12 can be used to grab and carry clothes, fold and organize clothes, and operate storage tools. The hand assembly 12 of the humanoid robot is usually composed of mechanical fingers and palms, which can simulate human hand movements to achieve the grabbing and carrying of clothes. In the process of clothing storage, the hand assembly 12 can accurately grab clothes of different types and sizes according to the recognition results of the visual assembly 11, and carry them to the designated storage area. In the process of clothing storage, the hand assembly 12 can also operate various storage tools, such as hangers, storage box lids, drawer handles, etc. The foot component 13 can be used for movement and positioning as well as adjusting the height and angle. The foot component 13 of the humanoid robot is usually composed of mechanical legs and soles, which can realize the movement and positioning of the humanoid robot. In the process of storing clothes, the foot component 13 can move the humanoid robot to a designated position according to the storage path planned by the visual component 11, so as to grab, carry and store clothes. The foot component 13 can also adjust the height and angle of the humanoid robot to better store clothes. For example, when the humanoid robot needs to put a piece of clothing into a high wardrobe, the foot component 13 can raise the center of gravity of the humanoid robot so that the hand component 12 can easily reach the high part of the wardrobe. When it is necessary to put clothes into a low drawer, the foot component 13 can bend the legs to lower the center of gravity of the humanoid robot, so as to facilitate the operation of the hand component 12.

[0040] See also Figure 2 , Figure 2 1 is a flow chart of a method for controlling a humanoid robot based on clothing storage provided by an embodiment of the present application. Figure 2 As shown, the method includes but is not limited to the following steps:

[0041] Step S101: obtaining clothing detection data of target clothing in a target area through a visual component;

[0042] Step S102: determining a target available storage area in a target storage space according to clothing detection data;

[0043] Step S103: Acquire the attribute information of the target available storage area;

[0044] Step S104: obtaining a storage feature corresponding to the target available storage area, the storage feature including one of the following: folding, hanging, and placing;

[0045] Step S105: determining a first storage action corresponding to the hand component based on the attribute information and the storage feature, the first storage action being used to perform a target operation on the target clothing, the target operation including one of the following: a folding operation, a hanging operation, and a placing operation;

[0046] Step S106: Obtaining a target storage height corresponding to the target available storage area;

[0047] Step S107: determining a second storage action corresponding to the foot assembly based on the first current height and the target storage height of the humanoid robot, where the second storage action is used to adjust the center of gravity height of the humanoid robot;

[0048] Step S108: Based on the first storage action and the second storage action, the humanoid robot is controlled to store the target clothing in the target available storage area.

[0049] The humanoid robot control method based on clothing storage provided in the embodiment of the present application can be applied to daily clothing arrangement, seasonal clothing storage, home space optimization, etc. in home storage scenarios. The method can also be applied to luggage arrangement and hotel clothing arrangement in travel storage scenarios. The method can also be applied to business trip clothing storage, office clothing storage, sports and fitness clothing storage, outdoor activity clothing storage, shopping mall clothing storage, etc. in special storage scenarios. The humanoid robot control method based on clothing storage provided in the embodiment of the present application is described by taking the home storage scenario as an example.

[0050] In a possible embodiment, for a home storage scene, the target house can be divided into one or more areas according to the house layout data of the target house. For different areas, the method of storing clothes may be different. For example, for clothes in the balcony area of ​​the target house, it may be necessary to determine whether the dryness of the clothes meets the first storage condition, and store them in the corresponding wardrobe when the first storage condition is met. For clothes in the living room area of ​​the target house, it may be necessary to determine whether the cleanliness of the clothes meets the second storage condition, so as to store them in the secondary clean clothes area or the dirty clothes area, etc. Therefore, according to the target area type corresponding to the target area, the clothing detection data of the target clothes in the target area can be obtained through the visual component, and the target available storage area in the target storage space can be determined according to the clothing detection data. For example, the target area type can be a drying area type, a multi-functional activity area type, or a clean clothes storage area type. If the target area is a balcony area, then the target area type is a drying area type. If the target area is a living room area, then the target area type is a multi-functional activity area type. If the target area is a user-preset area for temporarily storing clean clothes to be stored, then the target area type is a clean clothes storage area type. If the target area type is a drying area type, then the clothing detection data corresponding to the target clothing may include the humidity data of the target clothing. If the target area type is a multifunctional activity area type, then the clothing detection data corresponding to the target clothing may include the cleanliness detection data of the target clothing. If the target area type is a clean clothing storage area type, the clothing detection data may include data related to the inherent characteristics of the clothing. The holder of the target clothing can be determined based on the data related to the inherent characteristics of the clothing in the clothing detection data, and then the target storage space of the holder can be determined, and further based on the clothing detection data, the target available storage area corresponding to the target clothing can be determined in the target storage space, wherein the target available storage area is used to store the target clothing.

[0051] In a possible embodiment, the attribute information of the target available storage area is obtained, wherein the attribute information of the target available storage area may be appearance features such as shape, color, and size of the target available storage area, or may be spatial dimension information such as depth and height of each part inside the target available storage area. When obtaining the storage features corresponding to the target available storage area, the image corresponding to the target storage space may be segmented and recognized through visual components and image processing algorithms. For example, the hanging area, drawer area, and shelf area in the wardrobe may be distinguished, the placement area of ​​the dirty clothes area may be distinguished, and so on, and then the storage features corresponding to the target available storage area may be determined. The storage features include one of the following: folding, hanging, and placement. Exemplarily, according to the pre-set storage feature rules and knowledge base, the target available storage area is feature identified. If the storage area has a hanging rod and the height is suitable for hanging clothes, its storage feature is marked as hanging. For example, for the hanging area in an ordinary wardrobe, its height is usually between 1.5 meters and 1.8 meters, which is suitable for hanging long clothes such as coats and dresses. If the storage area is a flat layer structure and has a large space, it is suitable for placing stacked clothes or items, or for some areas with special folding structures or designs, such as storage boxes or drawers with folding partitions, it is marked as folding. For example, the layer area in the wardrobe can be used to place folded sweaters, pants, etc. Then, the identified storage features are associated and matched with specific storage areas to ensure that each storage area has a clear storage feature identification. In the database or memory of the humanoid robot, a corresponding relationship table between the storage area and the storage feature is established. For example, taking the wardrobe as an example, each compartment or area of ​​the wardrobe is respectively corresponded to the storage features such as hanging, placing, and folding, so as to facilitate subsequent rapid query and use.

[0052] In a possible embodiment, a first storage action corresponding to the hand component is determined based on the attribute information and the storage feature, the first storage action is used to perform a target operation on the target clothing, the target operation includes one of the following: a folding operation, a hanging operation, a placement operation, and a target storage height corresponding to the target available storage area is obtained, and a second storage action corresponding to the foot component is determined based on the first current height and the target storage height of the humanoid robot, the second storage action is used to adjust the center of gravity height of the humanoid robot, the target center of gravity height of the humanoid robot can be higher than the initial center of gravity height of the humanoid robot, and can also be lower than the initial center of gravity height of the humanoid robot. Finally, based on the first storage action and the second storage action, the humanoid robot is controlled to store the target clothing in the target available storage area, see Figure 3 , Figure 3 is a schematic diagram of a clothing storage action of a humanoid robot provided in an embodiment of the present application, such as Figure 3As shown, when the humanoid robot stores the target clothes in the figure, the target operation first performed on the target clothes is a folding operation. When placing the target clothes, the center of gravity height of the humanoid robot is adjusted to be lower than the initial center of gravity height of the humanoid robot according to the target storage height corresponding to the target available storage area, so as to store the target clothes.

[0053] Exemplarily, a decision logic algorithm of a humanoid robot is determined, through which the corresponding storage action of the hand component can be determined according to the attribute information and storage characteristics of the target available storage area. For example, if the target clothing is a long coat, and the attribute information of the target storage area shows that it has a hanging rod of suitable height, and the storage characteristic is hanging, then the target operation is determined to be a hanging operation. For some soft and wrinkle-prone clothing, such as silk shirts, if the attribute information of the storage area shows that it is a flat shelf, and the storage characteristic is folding, then the target operation is determined to be a folding operation, so that the clothing can be folded neatly and placed on the shelf to avoid wrinkles. According to the determined first storage action, the corresponding action parameters of the hand component of the humanoid robot are determined. For the hanging operation, the grasping force, grasping position, and the height and angle of the hanging of the hand component are set. In the folding operation, the steps and sequence of the folding, as well as the angle and force of each folding are determined. For the placement operation, the moving path, placement position, and placement method of the hand component are set. The hand component is controlled to execute the first storage action according to the action parameters. During the execution of the action, the action state of the hand component and the interaction with the surrounding environment are monitored in real time. For example, the force condition of the hand component when grabbing the target clothing is detected by the force sensor, and the position and posture of the target clothing during hanging, folding or placement are determined by the visual component. If problems such as clothing slipping, uneven folding or inaccurate placement occur during the execution of the action, the action parameters are adjusted in time according to the information fed back by the visual component, and the storage action is re-executed until the target operation is completed.

[0054] In the embodiment of the present application, by obtaining the attribute information and storage characteristics of the storage area, the most suitable position for placing the target clothing can be quickly found, avoiding unnecessary searching and trying time, thereby greatly improving the overall efficiency of storage. Determining the first storage action of the hand component allows the clothing to be stored in the most appropriate way, reducing the time for repeated operations and adjustments. Selecting the appropriate storage action according to the characteristics of the clothing and the characteristics of the storage area can effectively protect the clothing. Accurately setting the action parameters of the hand component, such as grasping force, hanging height, etc., can prevent the clothing from being pulled and damaged during the storage process, thereby extending the service life of the clothing. Determining the attribute information of the storage area, including size, shape structure, etc., helps to better plan the placement of clothing and make full use of the storage space. Carrying out targeted storage operations for different storage characteristics can make the clothing in the storage area more neat and orderly, improve the utilization rate and aesthetics of the space, for example, placing the folded clothing on the shelf according to category and color, or arranging the hanging clothing according to length and style, not only facilitates searching and taking, but also makes the storage space look more tidy and comfortable. Intelligent storage is performed based on the actual situation of the storage area and the characteristics of the clothes, making the storage results more in line with the user's expectations and habits.

[0055] Optionally, step S101, obtaining clothing detection data of target clothing in a target area through a visual component, may include the following steps:

[0056] Step S201: obtaining at least one relevant person associated with the target area;

[0057] Step S202: acquiring historical behavior data of each of at least one relevant person in the target area, the historical behavior data including at least one of the following: clothing changing and washing data, clothing storage times;

[0058] Step S203: Acquire visit schedule data of the target area;

[0059] Step S204: determining the target detection frequency and target detection time period of the target area according to the historical behavior data and the visit schedule data;

[0060] Step S205: Acquire spatial layout data of the target area, where the spatial layout data is used to reflect the distribution of multiple objects in the target area;

[0061] Step S206: determining a detection path and a target detection range of the humanoid robot in the target area based on the spatial layout data;

[0062] Step S207: controlling the humanoid robot to move along the detection path, and adjusting the initial detection angle and the initial detection distance of the visual component based on the first current position of the humanoid robot and the target detection range to obtain the target detection angle and the target detection distance;

[0063] Step S208: Based on the target detection frequency and the target detection time period, control the visual component to detect the clothes within the target detection range based on the target detection angle and the target detection distance to obtain regional detection data;

[0064] Step S209: obtaining the target area type of the target area;

[0065] Step S210: determining whether there is a storage demand in the target area based on the area detection data and the target area type;

[0066] Step S211: when there is a storage demand in the target area, determining the target clothing in the target area according to the area detection data;

[0067] Step S212: Acquire clothing detection data of the target clothing through the visual component according to the target area type.

[0068] In a possible embodiment, at least one relevant person associated with the target area is obtained. For example, at least one relevant person associated with the target area is determined based on the main purpose of the target area. For example, for a home storage scenario, when the target area is a living room area, at least one relevant person may be all residents of the target house. When the target area is a bedroom area, at least one relevant person may be the resident corresponding to the bedroom area. The association degree of multiple historical persons in the target area may be evaluated. For example, the association degree of each historical person with the target area is determined based on the activity time and activity frequency of multiple historical persons in the target area, and the historical person whose association degree is higher than a preset association degree threshold is taken as at least one relevant person. Then, the historical behavior data of each relevant person in the at least one relevant person in the target area is obtained. The historical behavior data includes at least one of the following: clothing changing and washing data, clothing storage times, and the visiting schedule data of the target area is obtained. Then, the target detection frequency and target detection time period of the target area are determined based on the historical behavior data and the visiting schedule data. Acquire spatial layout data of a target area, the spatial layout data is used to reflect the distribution of multiple objects in the target area, determine a detection path and a target detection range of a humanoid robot in the target area based on the spatial layout data, control the humanoid robot to move along the detection path, and adjust an initial detection angle and an initial detection distance of a visual component based on a first current position of the humanoid robot and a target detection range to obtain a target detection angle and a target detection distance, control the visual component to detect clothing within a target detection range based on a target detection angle and a target detection distance based on a target detection frequency and a target detection time period to obtain regional detection data, acquire a target area type of the target area, determine whether there is a storage demand in the target area based on the regional detection data and the target area type, when there is a storage demand in the target area, determine target clothing in the target area according to the regional detection data, and obtain clothing detection data of the target clothing through the visual component according to the target area type.

[0069] In a possible embodiment, a target detection frequency and a target detection time period of a target area are determined based on historical behavior data and visit schedule data. A reference detection frequency and a reference detection time period corresponding to the target area can be obtained, and whether there is at least one visitor is determined based on the visit schedule data. If there is no at least one visitor, a historical time period corresponding to the historical behavior data is determined, and a clothing storage frequency is determined based on the historical time period and the number of clothing storage times. A frequency difference between the clothing storage frequency and the reference detection frequency is determined to obtain a target frequency difference. The reference detection frequency is adjusted based on the target frequency difference to obtain a target detection frequency, and the time of each clothing change in the clothing change data is determined. time, obtain multiple clothing changing and washing times, determine the number of multiple clothing changing and washing times within the reference detection time period, obtain the target number, determine the first adjustment coefficient corresponding to the target number, adjust the reference detection time period according to the first adjustment coefficient, obtain the target detection time period, if there is at least one visitor, determine at least one visitor type, at least one visit time period and at least one visit frequency corresponding to at least one visitor based on the visit schedule data, determine the target detection frequency based on at least one visitor type, the reference detection frequency and at least one visit frequency, and determine the target detection time period based on at least one visitor type, the reference detection time period and at least one visit time period. When there are no visitors, determine the target detection frequency and target detection time period according to the historical behavior data. When there are visitors, it is necessary to ensure that the target area is already in a well-stored state before the visitor arrives. Therefore, the target detection frequency and target detection time period are determined according to the visitor type, the visit frequency and the visit time period of the visitor.

[0070] In the embodiment of the present application, the target area is detected according to the target detection frequency and target detection time period of the target area to obtain the area detection data, which saves the energy consumption of frequent detection of the humanoid robot. The humanoid robot detects different target areas according to the corresponding target detection frequency and target detection time period to determine whether there is a storage demand, and provides a storage method that detects and stores only after receiving the storage instruction, which improves the intelligence of the humanoid robot in clothing storage, and can realize adaptive storage and sorting of different target areas to improve the utilization efficiency of the humanoid robot.

[0071] Optionally, step S210, determining whether there is a storage demand in the target area based on the area detection data and the target area type, may include the following steps:

[0072] Step S301: when the target area type is a drying area type, obtaining meteorological data and determining a weather trend corresponding to the meteorological data;

[0073] Step S302: if the weather trend is consistent with the preset first trend, determining whether there is at least one first clothing item in the target area based on the area detection data;

[0074] Step S303: if there is at least one first clothing item in the target area, determining that there is a storage demand in the target area;

[0075] Step S304: if the weather trend is consistent with the preset second trend, determining whether there is at least one second clothing item in the target area based on the area detection data;

[0076] Step S305: if the quantity of at least one second clothing item is higher than a preset first quantity threshold, determining that there is a storage demand in the target area;

[0077] Step S306: when the target area type is a multi-functional activity area type, m candidate clothing sets are determined based on the area detection data, where m is a positive integer;

[0078] Step S307: obtaining the position and volume of each candidate clothing set in the m candidate clothing sets, and obtaining the positions of m clothing sets and the volumes of m clothing sets;

[0079] Step S308: determining a first score of the target area based on the m clothing set positions and the m clothing set volumes, where the first score is used to reflect the cleanliness of the target area;

[0080] Step S309: Obtaining a reference score threshold of the target area;

[0081] Step S310: determining a target score threshold of a target area based on a reference score threshold and visit schedule data;

[0082] Step S311: when the first score is lower than the target score threshold, it is determined that there is a storage demand in the target area;

[0083] Step S312: when the target area type is a clean clothes storage area type, determining whether there is at least one third clothing item in the third area;

[0084] Step S313: If the quantity of at least one third clothing item is higher than a preset second quantity threshold, it is determined that there is a storage demand in the target area.

[0085] In a possible embodiment, when the target area type is a drying area type, meteorological data is obtained, and a weather trend corresponding to the meteorological data is determined. The preset first trend is a trend that will have an obstructive effect on the drying of clothes. The preset first trend may be rainfall, snowfall, showers, etc. If the weather trend is consistent with the preset first trend, it is determined based on the area detection data whether there is at least one first clothing in the target area. The first clothing is clothing that will be affected by the first trend. For example, the first clothing may be clothing that will be rained on when the weather trend is a rainfall trend. See FIG. Figure 4 , Figure 4 is a schematic diagram of the positions of a first garment and a second garment in a target area provided by an embodiment of the present application, such as Figure 4 As shown, the first clothing may be clothing in an open-air drying area. If there is at least one first clothing in the target area, it is determined that there is a storage demand in the target area. The preset second trend is a trend that will promote the drying of clothing. The preset second trend may be sunny, cloudy, overcast, etc. If the weather trend is consistent with the preset second trend, it is determined based on the regional detection data whether there is at least one second clothing in the target area. The second clothing may be clothing in an indoor drying area, or the second clothing may be dry clothing in an indoor drying area. If the number of at least one second clothing is higher than the preset first quantity threshold, it is determined that there is a storage demand in the target area. The preset first trend or the preset second trend can be understood as the specified weather that occurs within a preset time period.

[0086] In a possible embodiment, when the target area type is a multi-functional activity area type, m candidate clothing sets are determined based on the area detection data, each candidate clothing set contains at least one piece of clothing, and m is a positive integer. The position and volume of each of the m candidate clothing sets are obtained to obtain m clothing set positions and m clothing set volumes. A first score of the target area is determined based on the m clothing set positions and the m clothing set volumes, and the first score is used to reflect the cleanliness of the target area. A reference score threshold of the target area is obtained, and a target score threshold of the target area is determined based on the reference score threshold and the visiting schedule data. When the first score is lower than the target score threshold, it is determined that there is a storage demand in the target area. Among them, different target areas correspond to different reference score thresholds. Further, the target score threshold of the target area is determined based on the reference score threshold and the visiting schedule data. It can be determined whether there is a visitor according to the visiting schedule data, and when there is a visitor, the degree of closeness between the visitor and the target-related person is determined based on the person type of the visitor, and the adjustment value is determined according to the degree of closeness, and the target score threshold is determined in combination with the reference score threshold. For example, if the person type of the visitor is a direct relative of the target-related person, then the first adjustment value is determined, and the target score threshold is the sum of the reference score threshold and the first adjustment value. If the person type of the visitor is a colleague of the target person type, then the second adjustment value is determined, and the target score threshold is the sum of the reference score threshold and the second adjustment value, and the first adjustment value is less than the second adjustment value. If there is no visitor, the reference score threshold is used as the target score threshold.

[0087] In a possible embodiment, when the target area type is a clean clothes storage area type, it is determined whether there is at least one third clothing in the third area, and the third clothing is the clothing in the target area. If the quantity of at least one third clothing is higher than a preset second quantity threshold, it is determined that there is a storage demand in the target area.

[0088] In the embodiment of the present application, different target area types have different functions and storage requirements. Whether the target area has storage requirements is determined based on the area detection data and different target area types, and storage is performed when there is a storage requirement. This saves energy consumption in storing clothes of the humanoid robot and can meet personalized storage of different area types as needed.

[0089] Optionally, when the target area type is a multifunctional activity area type, in step S211, determining the target clothing in the target area according to the area detection data may include the following steps:

[0090] Step S401: determining a second score of each of the m candidate clothing sets based on the m clothing set positions and the m clothing set volumes obtained from the region detection data, and obtaining m second scores, wherein the m second scores are used to reflect the neatness of each of the m candidate clothing sets;

[0091] Step S402: determining the storage priority of each of the m candidate clothing sets based on the m second scores, and obtaining m storage priorities;

[0092] Step S403: determining a storage order based on the m storage priorities, the second current position of the humanoid robot and the m clothing positions;

[0093] Step S404: determining a target candidate clothing set based on the storage order, wherein the target candidate clothing set contains at least one candidate clothing;

[0094] Step S405: determining a first stop position of the humanoid robot based on the clothing set position corresponding to the target candidate clothing set;

[0095] Step S406: determining a first moving path of the humanoid robot based on the first stop position and the second current position;

[0096] Step S407: controlling the humanoid robot to move along the first moving path to a first stop position;

[0097] Step S408: when the humanoid robot is located at the first stop position, obtaining a stacking relationship of at least one candidate clothing item in the target candidate clothing set through a visual component;

[0098] Step S409: determining the difficulty of picking up at least one candidate clothing item based on the stacking relationship, and obtaining at least one picking up difficulty item;

[0099] Step S410: Based on at least one difficulty of picking up, select the candidate clothing with the lowest difficulty of picking up among at least one candidate clothing as the target clothing.

[0100] In a possible embodiment, the second score of each candidate clothing set in the m candidate clothing sets is determined based on the m clothing set positions and the m clothing set volumes obtained from the area detection data, and m second scores are obtained. The m second scores are used to reflect the neatness of each candidate clothing set in the m candidate clothing sets. The storage priority of each candidate clothing set in the m candidate clothing sets is determined based on the m second scores, and m storage priorities are obtained. The m second scores are sorted in order from high to low, and the storage priorities are determined according to the order of sorting. The storage order is determined based on the m storage priorities, the second current position of the humanoid robot, and the m clothing positions. For multiple candidate clothing sets with the same storage priority, the storage order is determined according to the second current position and the clothing positions corresponding to the multiple candidate clothing sets with the same storage priority, and the storage order is determined according to the distance between the clothing positions in the multiple candidate clothing sets with the same storage priority and the second current position.

[0101] In a possible embodiment, a target candidate clothing set is determined based on a storage order, there is at least one candidate clothing in the target candidate clothing set, a first stop position of a humanoid robot is determined based on the clothing set position corresponding to the target candidate clothing set, a first moving path of the humanoid robot is determined based on the first stop position and the second current position, the humanoid robot is controlled to move to the first stop position along the first moving path, when the humanoid robot is at the first stop position, the stacking relationship of at least one candidate clothing in the target candidate clothing set is obtained through a visual component, the difficulty of picking up at least one candidate clothing in the target candidate clothing set is determined based on the stacking relationship, at least one picking difficulty is obtained, and based on the at least one picking difficulty, the candidate clothing with the lowest picking difficulty among the at least one candidate clothing is used as the target clothing. In the embodiment of the present application, by using the clothing with the lowest picking difficulty as the target clothing, the possible damage to the clothing during the storage process is reduced.

[0102] For example, see Figure 5 , Figure 5 Schematic diagram of a clothing stacking relationship provided in an embodiment of the present application. Figure 5 As shown, Figure 5 There are three clothes in the candidate clothes set: clothes A, clothes B and clothes C. The stacking relationship between the three is as follows: Figure 5 As shown, it can be determined that the clothing C is the easiest to pick up based on this stacking relationship, and clothing C is taken as the target clothing to control the humanoid robot to store clothing C.

[0103] Optionally, step S102, determining a target available storage area in a target storage space according to clothing detection data, may include the following steps:

[0104] Step S501: determining a target related person corresponding to a target piece of clothing among at least one related person according to clothing detection data;

[0105] Step S502: determining a target storage space corresponding to the target-related person, the target storage space including at least one of the following: a first storage space, a second storage space, and a third storage space, the first storage space is used to store clean clothes, the second storage space is used to store second-clean clothes, and the third storage space is used to store dirty clothes;

[0106] Step S503: when the target area type is a drying area type, obtaining a first clothing state of the target clothing according to the clothing detection data, the first clothing state being used to reflect the dryness of the target clothing;

[0107] Step S504: Acquire the environmental humidity data of the target area;

[0108] Step S505: determining a first clothing storage condition based on the environmental humidity data;

[0109] Step S506: when the first clothing state meets the first clothing storage condition, or when the target area type is a clean clothing storage area type, determining a target available storage area in the first storage space;

[0110] Step S507: when the target area type is a multi-functional activity area type, obtaining a second clothing state of the target clothing according to the clothing detection data, the second clothing state is used to reflect the cleanliness of the target candidate clothing;

[0111] Step S508: Acquire historical dressing data of the target-related person, where the historical dressing data is used to reflect the dressing habits of the target-related person;

[0112] Step S509: determining a second clothing storage condition based on historical clothing data;

[0113] Step S510: When the second clothing state meets the second clothing storage condition, a target available storage area is determined in the second storage space; otherwise, a target available storage area is determined in the third storage space.

[0114] In a possible embodiment, a target-related person corresponding to the target clothing among at least one related person is determined based on the clothing detection data, the target-related person is the holder of the target clothing, and a target storage space corresponding to the target-related person is determined, the target storage space is the storage space available to the target person, and the target storage space includes at least one of the following: a first storage space, a second storage space, and a third storage space, the first storage space is used to store clean clothes, the second storage space is used to store sub-clean clothes, and the third storage space is used to store dirty clothes.

[0115] In a possible embodiment, when the target area type is a drying area type, the clothing detection data includes clothing humidity data of the target clothing, and the clothing humidity data can be acquired by detecting the target clothing in the drying according to the humidity sensor device equipped by the humanoid robot, and the first clothing state of the target clothing is acquired according to the clothing humidity data in the clothing detection data, and the first clothing state is used to reflect the dryness of the target clothing. The environmental humidity data of the target area is acquired, and the environmental humidity data can be acquired after the humanoid robot establishes a connection with the environmental humidity monitoring device set in the drying area, and the first clothing storage condition is determined based on the environmental humidity data, and the first clothing storage condition can include a clothing humidity range. When the first clothing state meets the first clothing storage condition, or when the target area type is a clean clothing storage area type, the target available storage area is determined in the first storage space.

[0116] In a possible embodiment, when acquiring clothing humidity data, a humanoid robot can determine, based on clothing characteristics of the target clothing, the part that is most difficult to dry when the target clothing is in the current drying posture. For example, this may be the part where the target clothing is thickest when the clothing is in the current drying posture, and this part can be used as the detection part. The clothing humidity data can be obtained by only acquiring the humidity of the detection part through the humanoid robot. There is no need to perform detection at multiple detection parts, thereby saving energy consumption of the humanoid robot.

[0117] In a possible embodiment, when the target area type of the target area is a drying area type, the laundry washing and drying data within a preset time is obtained, and the washing and drying batches of all the laundry in the target area are determined according to the laundry washing and drying data. The drying difficulty of at least one laundry in each batch can be determined according to the time sequence of the washing and drying batches, and the laundry with the lowest drying difficulty is taken as the target batch, and the target laundry is determined in the target batch. Furthermore, the laundry with the greatest drying difficulty can be determined in the target batch as the target laundry, and the laundry humidity data of the target laundry is obtained. If the laundry humidity data meets the first laundry storage condition, then for other target laundry in the same batch, the step of obtaining the laundry humidity data can be omitted, and it is determined that they all meet the first laundry storage condition, further saving the energy consumption of the humanoid robot.

[0118] In a possible embodiment, when the target area type is a multi-functional activity area type, the clothing detection data includes cleanliness detection data of the target clothing. The cleanliness detection data can be obtained according to a clothing picture of the target clothing after the humanoid robot flattens the target clothing, or can be obtained according to the wearing time of the target clothing. A second clothing state of the target clothing is obtained according to the clothing detection data, and the second clothing state is used to reflect the cleanliness of the target candidate clothing. Historical clothing data of target-related persons is obtained, and the historical clothing data is used to reflect the dressing habits of target-related persons. The second clothing storage condition is determined based on the historical clothing data. For example, the second clothing storage condition is determined according to information such as the wearing frequency, wearing time and washing interval after wearing of different types of clothing in the historical clothing data. The second clothing storage condition may include a cleanliness range. When the second clothing state meets the second clothing storage condition, the target available storage area is determined in the second storage space; otherwise, the target available storage area is determined in the third storage space. For example, when the target-related person has the habit of washing the target clothing after wearing it for two days, if it is determined in the current detection that the current wearing time of the target clothing is one day, it is judged to be clean clothing and stored in the second storage space; if it is determined in the current detection that the current wearing time of the target clothing is two days, it is judged to be dirty clothing and stored in the third storage space.

[0119] In the embodiment of the present application, the storage conditions of clothes are reasonably determined according to the ambient humidity, which can avoid the clothes from retaining moisture due to premature storage, thereby reducing the occurrence of problems such as mold and odor, and extending the service life of clothes. By automatically monitoring the dryness of clothes and the ambient humidity, the storage operation is automatically performed when the clothes meet the storage conditions, saving the energy consumption of frequently checking whether the clothes are dry. By analyzing the cleanliness of clothes and the dressing habits of people, clothes can be accurately classified and stored in different spaces, avoiding the confusion of clean clothes and dirty clothes, and the chaotic placement of clothes with different wearing frequencies and cleanliness requirements. Everyone's dressing habits are different. By obtaining the historical dressing data of the target-related personnel and determining the storage conditions accordingly, the personalized needs of users can be better met.

[0120] Optionally, the first storage space includes at least one storage subspace, and in step S506, determining the target available storage area in the first storage space may include the following steps:

[0121] Step S601: acquiring a first image of a target garment through a visual component;

[0122] Step S602: determining the recognition degree of the target clothing based on the first image;

[0123] Step S603: when the recognition degree is higher than or equal to the preset recognition degree threshold, the first image is compared with the preset clothing database to obtain a first comparison result, and the first comparison result is used as a target comparison result;

[0124] Step S604: when the recognition degree is lower than the recognition degree threshold, obtaining the flatness of the target clothing;

[0125] Step S605: If the flattening degree is lower than a preset flattening degree threshold, control the hand component to perform a flattening operation on the target clothing;

[0126] Step S606: when the flatness is greater than or equal to the flatness threshold, obtaining a second image of the target clothing through a visual component;

[0127] Step S607: Compare the second image with the clothing database to obtain a second comparison result, and use the second comparison result as a target comparison result;

[0128] Step S608: determining a clothing feature label of the target clothing based on the target comparison result;

[0129] Step S609: determining the folding times of the target clothing and the candidate storage subspace of the target clothing in at least one storage subspace based on the clothing feature tag, and obtaining at least one candidate storage subspace;

[0130] Step S610: determining a second moving path and a second staying position of the humanoid robot based on the third current position of the humanoid robot and each candidate storage subspace in at least one candidate storage subspace, to obtain at least one second moving path and at least one second staying position;

[0131] Step S611: controlling the humanoid robot to move along at least one second moving path to a corresponding second stop position;

[0132] Step S612: when the humanoid robot is located at at least one second stop position, obtaining remaining space data of at least one candidate storage subspace through a visual component to obtain at least one remaining space data;

[0133] Step S613: determining a target storage subspace based on the number of folding times and at least one remaining space data;

[0134] Step S614: obtaining clothing storage characteristics of the target storage subspace;

[0135] Step S615: Determine a target available storage area based on the clothing storage characteristics and clothing characteristic tags.

[0136] In a possible embodiment, a first image of the target clothing is obtained through a visual component, and the recognition of the target clothing is determined based on the first image. The recognition is used to reflect the recognition difficulty of the target clothing. The higher the recognition, the lower the recognition difficulty. High recognition can enable the humanoid robot to quickly distinguish different types of clothing. For example, tops, pants, etc. can be classified by features with high recognition such as color, pattern, style, etc., which helps to improve storage efficiency. When the recognition is higher than or equal to a preset recognition threshold, the first image is compared with a preset clothing database to obtain a first comparison result, and the first comparison result is used as the target comparison result. When the recognition is lower than the recognition threshold, the flatness of the target clothing is obtained. The flatness reflects the flatness of the target clothing. The higher the flatness, the more clothing features of the target clothing that the visual component can obtain. If the target clothing is in a folded state, its flatness may be low. If the flattening degree is lower than the preset flattening degree threshold, the hand component is controlled to perform a flattening operation on the target clothing. When the flattening degree is higher than or equal to the flattening degree threshold, a second image of the target clothing is obtained through the visual component, and the second image is compared with the clothing database to obtain a second comparison result. The second comparison result is used as the target comparison result. The target comparison result is the clothing with the highest similarity corresponding to the target clothing in the preset clothing database. The clothing feature label of the target clothing is determined based on the target comparison result, and the number of folding times of the target clothing and the candidate storage subspace of the target clothing in at least one storage subspace are determined based on the clothing feature label to obtain at least one candidate storage subspace. The clothing feature label is used to reflect the appropriate storage method of the target clothing. The number of folding times of the target clothing can be zero, one or more times. When the number of folding times is zero, the best storage method corresponding to the target clothing is hanging storage, or no hanging and folding are required, and only placement is required. When the number of folding times is one or more times, the best storage method corresponding to the target clothing is folding storage. The candidate storage subspace is a space in the subspace where the storage method is consistent with the storage method corresponding to the number of folding times. Based on the third current position of the humanoid robot and each candidate storage subspace in at least one candidate storage subspace, the second moving path and the second staying position of the humanoid robot are determined, at least one second moving path and at least one second staying position are obtained, and the humanoid robot is controlled to move along at least one second moving path to the corresponding second staying position.

[0137] In a possible embodiment, when the humanoid robot is located at at least one second stop position, the remaining space data of at least one candidate storage subspace is obtained through a visual component to obtain at least one remaining space data, and a target storage subspace is determined based on the number of folding times and the at least one remaining space data. The remaining space data is used to reflect the size of the remaining space in the candidate storage subspace. If the number of folding times of the target clothing can be zero or one or more times, then there are multiple suitable storage methods for the target clothing, which also correspond to different candidate storage subspaces. At this time, the target storage method of the target clothing can be determined according to the remaining space data of each candidate storage subspace, and the target storage subspace corresponding to the target storage method is determined in at least one candidate storage subspace according to the target storage method. For example, if the target clothing is a shirt, the number of folding times of the shirt can be zero or more times, and the corresponding storage method can be hanging or folding, but the remaining space data shows that the remaining space in the candidate storage subspace corresponding to the folding is insufficient to store the shirt, then the candidate storage subspace corresponding to the hanging is used as the target storage subspace. The clothing storage characteristics of the target storage subspace are obtained, and the target available storage area is determined based on the clothing storage characteristics and the clothing feature tags. The clothing storage characteristics can reflect the clothing storage characteristics of multiple clothes in the target storage subspace, for example, storage according to clothing color, storage according to clothing length, storage according to clothing thickness, etc. According to the clothing feature tags of the target clothes, the area in the clothing storage characteristics corresponding to the clothing feature tags is determined in the target storage subspace as the target available storage area.

[0138] In the embodiment of the present application, when the current picture of the clothing is not sufficient to obtain the characteristics of the clothing, the clothing is flattened to determine the clothing characteristic label of the target clothing, thereby improving the decision efficiency and accuracy of the humanoid robot. By determining the target storage subspace based on the number of folds and at least one remaining space data, the storage space is optimized and the flexibility of storing the target clothing is improved. By determining the target available storage area based on the storage characteristics of the clothing and the clothing characteristic label, the neatness of clothing storage is increased and the clutter caused by blind storage is avoided.

[0139] Optionally, in step S605, controlling the hand component to perform a flattening operation on the target clothing may include the following steps:

[0140] Step S701: obtaining an initial clothing shape and an initial clothing position of a target clothing;

[0141] Step S702: determining the picking height of the humanoid robot based on the initial clothing position;

[0142] Step S703: adjusting the current posture of the humanoid robot based on the picking height to obtain a target posture;

[0143] Step S704: Control the humanoid robot to adjust to the target posture;

[0144] Step S705: determining at least one picking point based on the initial clothing shape;

[0145] Step S706: when the humanoid robot is in the target posture, the relative position relationship between the hand assembly and at least one picking point is obtained to obtain at least one relative position relationship;

[0146] Step S707: determining a picking direction of each picking point in at least one picking point based on at least one relative position relationship to obtain at least one picking direction;

[0147] Step S708: predicting a first weight of the target clothing;

[0148] Step S709: determining an initial picking force corresponding to at least one picking point based on the first weight, and obtaining at least one initial picking force;

[0149] Step S710: performing a picking operation on the target clothing based on at least one initial picking force, and if the picking speed of the target clothing is less than a preset speed threshold, obtaining a second weight of the target clothing;

[0150] Step S711: adjusting at least one initial picking force based on the second weight to determine at least one target picking force;

[0151] Step S712: Flatten the target clothing based on at least one target picking force and at least one picking direction until the flattening degree is higher than or equal to a flattening degree threshold, and determine that the flattening operation is completed.

[0152] In a possible embodiment, an initial clothing shape and an initial clothing position of a target clothing are obtained, a picking height of a humanoid robot is determined based on the initial clothing position, a current posture of the humanoid robot is adjusted based on the picking height to obtain a target posture, the humanoid robot is controlled to adjust to the target posture, at least one picking point is determined based on the initial clothing shape, when the humanoid robot is in the target posture, a relative position relationship between a hand assembly and at least one picking point is obtained to obtain at least one relative position relationship, a picking direction of each picking point in at least one picking point is determined based on at least one relative position relationship to obtain at least one picking direction, a first weight of the target clothing is predicted, an initial picking force corresponding to at least one picking point is determined based on the first weight to obtain at least one initial picking force, and a picking operation is performed on the target clothing based on the at least one initial picking force.

[0153] In a possible embodiment, if the picking speed of the target clothing is less than a preset speed threshold, it means that the initial picking force is insufficient to pick up the target clothing. At this time, the second weight of the target clothing is obtained, and at least one initial picking force is adjusted based on the second weight. The weight adjustment value is determined based on the difference between the second weight and the first weight. At least one target picking force is determined based on the sum of the weight adjustment value and at least one initial picking force. The target clothing is flattened based on at least one target picking force and at least one picking direction until the flattening degree is higher than or equal to the flattening degree threshold, and it is determined that the flattening operation is completed.

[0154] In the embodiment of the present application, the clothing is flattened to improve the decision-making accuracy of the humanoid robot, and it is also convenient for the humanoid robot to subsequently store the target clothing.

[0155] To summarize, in an embodiment of the present application, clothing detection data of target clothing in a target area is first obtained through a visual component, and then, a target available storage area in a target storage space is determined according to the clothing detection data, and attribute information of the target available storage area is obtained, as well as storage features corresponding to the target available storage area, the storage features including one of the following: folding, hanging, and placing, and then, a first storage action corresponding to a hand component is determined based on the attribute information and the storage features, the first storage action being used to perform a target operation on the target clothing, the target operation including one of the following: folding operation, hanging operation, and placing operation, and a target storage height corresponding to the target available storage area is obtained, and a second storage action corresponding to a foot component is determined based on a first current height and a target storage height of the humanoid robot, the second storage action being used to adjust the height of the center of gravity of the humanoid robot, and finally, based on the first storage action and the second storage action, the humanoid robot is controlled to store the target clothing in the target available storage area. Therefore, the target available storage area is determined according to the clothing detection data of the target clothing, and the first storage action and the second storage action of the humanoid robot are determined by acquiring the attribute information and storage characteristics of the storage area. The humanoid robot can be controlled to store the target clothing, saving the user's time and energy spent on clothing storage.

[0156] The method of the embodiment of the present invention is described in detail above, and the device of the embodiment of the present invention is provided below.

[0157] See also Figure 6 , Figure 6 800 is a schematic diagram of a humanoid robot control device based on clothing storage provided in an embodiment of the present application. The humanoid robot control device based on clothing storage 800 is applied to a humanoid robot, the humanoid robot includes a visual component, a foot component and a hand component, and the humanoid robot control device based on clothing storage 800 includes an acquisition unit 801 and a processing unit 802;

[0158] An acquisition unit 801 is used to acquire clothing detection data of target clothing in a target area through a visual component;

[0159] A processing unit 802 is used to determine a target available storage area in a target storage space according to the clothing detection data;

[0160] Obtaining the attribute information of the target available storage area;

[0161] Obtaining a storage feature corresponding to a target available storage area, where the storage feature includes one of the following: folding, hanging, and placing;

[0162] Determine a first storage action corresponding to the hand component based on the attribute information and the storage feature, the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: a folding operation, a hanging operation, and a placing operation;

[0163] Obtain the target storage height corresponding to the target available storage area;

[0164] Determining a second storage action corresponding to the foot assembly based on a first current height and a target storage height of the humanoid robot, wherein the second storage action is used to adjust the center of gravity height of the humanoid robot;

[0165] Based on the first storage action and the second storage action, the humanoid robot is controlled to store the target clothing in the target available storage area.

[0166] In a possible embodiment, in acquiring clothing detection data of target clothing in a target area through a visual component, the acquiring unit 801 is specifically configured to:

[0167] Acquire at least one relevant person associated with the target area;

[0168] Acquire historical behavior data of each of at least one relevant person in the target area, where the historical behavior data includes at least one of the following: clothing changing and washing data, and clothing storage times;

[0169] Get visit schedule data for the target area;

[0170] Determine the target detection frequency and target detection time period in the target area based on historical behavior data and visit schedule data;

[0171] Acquire spatial layout data of the target area, where the spatial layout data is used to reflect the distribution of multiple objects in the target area;

[0172] Determine the detection path and target detection range of the humanoid robot in the target area based on the spatial layout data;

[0173] Controlling the humanoid robot to move along the detection path, and adjusting the initial detection angle and the initial detection distance of the visual component based on the first current position of the humanoid robot and the target detection range to obtain the target detection angle and the target detection distance;

[0174] Based on the target detection frequency and the target detection time period, the visual component is controlled to detect the clothes within the target detection range based on the target detection angle and the target detection distance to obtain the regional detection data;

[0175] Get the target area type of the target area;

[0176] Determine whether there is storage demand in the target area based on the area detection data and the target area type;

[0177] When there is a storage demand in the target area, the target clothing in the target area is determined according to the area detection data;

[0178] According to the target area type, clothing detection data of the target clothing is obtained through the visual component.

[0179] In a possible embodiment, in determining whether a target area has a storage demand based on the area detection data and the target area type, the acquisition unit 801 is specifically configured to:

[0180] When the target area type is a drying area type, obtaining meteorological data and determining a weather trend corresponding to the meteorological data;

[0181] If the weather trend is consistent with the preset first trend, determining whether there is at least one first clothing item in the target area based on the area detection data;

[0182] If there is at least one first clothing item in the target area, determining that there is a storage demand in the target area;

[0183] If the weather trend is consistent with the preset second trend, determining whether there is at least one second clothing item in the target area based on the area detection data;

[0184] If the quantity of at least one second clothing item is higher than a preset first quantity threshold, determining that the target area has a storage demand;

[0185] When the target area type is a multifunctional activity area type, m candidate clothing sets are determined based on the area detection data, where m is a positive integer;

[0186] Obtain the position and volume of each candidate clothing set in the m candidate clothing sets, and obtain the positions of m clothing sets and the volumes of m clothing sets;

[0187] Determine a first score of the target area based on the m clothing set positions and the m clothing set volumes, where the first score is used to reflect the cleanliness of the target area;

[0188] Obtain the reference score threshold of the target area;

[0189] Determine a target score threshold for the target area based on the reference score threshold and the visit schedule data;

[0190] When the first score is lower than the target score threshold, it is determined that there is a storage demand in the target area;

[0191] When the target area type is a clean clothes storage area type, determining whether there is at least one third clothing item in the third area;

[0192] If the quantity of at least one third clothing item is higher than a preset second quantity threshold, it is determined that there is a storage demand in the target area.

[0193] In a possible embodiment, when the target area type is a multifunctional activity area type, in determining the target clothing in the target area according to the area detection data, the acquisition unit 801 is specifically configured to:

[0194] Determine a second score of each of the m candidate clothing sets based on the m clothing set positions and the m clothing set volumes obtained from the region detection data, and obtain m second scores, wherein the m second scores are used to reflect the neatness of each of the m candidate clothing sets;

[0195] Determine the storage priority of each candidate clothing set in the m candidate clothing sets based on the m second scores, and obtain m storage priorities;

[0196] determining a storage order based on the m storage priorities, the second current position of the humanoid robot, and the m clothing positions;

[0197] Determine a target candidate clothing set based on the storage order, where there is at least one candidate clothing in the target candidate clothing set;

[0198] Determine a first stop position of the humanoid robot based on a clothing set position corresponding to the target candidate clothing set;

[0199] determining a first movement path of the humanoid robot based on the first rest position and the second current position;

[0200] Controlling the humanoid robot to move along a first moving path to a first stop position;

[0201] When the humanoid robot is located at the first stop position, obtaining a stacking relationship of at least one candidate clothing item in the target candidate clothing set through a visual component;

[0202] Determine the difficulty of picking up at least one candidate clothing item based on the stacking relationship, and obtain at least one picking up difficulty item;

[0203] Based on at least one difficulty of picking up, a candidate clothing item with the lowest difficulty of picking up among the at least one candidate clothing item is selected as a target clothing item.

[0204] In a possible embodiment, in determining the target available storage area in the target storage space according to the clothing detection data, the processing unit 802 is specifically configured to:

[0205] Determine a target related person corresponding to the target clothing among at least one related person according to the clothing detection data;

[0206] Determine a target storage space corresponding to the target-related person, the target storage space includes at least one of the following: a first storage space, a second storage space, and a third storage space, the first storage space is used to store clean clothes, the second storage space is used to store second-clean clothes, and the third storage space is used to store dirty clothes;

[0207] When the target area type is a drying area type, obtaining a first clothing state of the target clothing according to the clothing detection data, the first clothing state being used to reflect the dryness of the target clothing;

[0208] Obtain the environmental humidity data of the target area;

[0209] determining a first clothing storage condition based on the environmental humidity data;

[0210] When the first clothing state meets the first clothing storage condition, or when the target area type is a clean clothing storage area type, determining a target available storage area in the first storage space;

[0211] When the target area type is a multifunctional activity area type, a second clothing state of the target clothing is obtained according to the clothing detection data, and the second clothing state is used to reflect the cleanliness of the target candidate clothing;

[0212] Obtain the historical dressing data of the target-related personnel, which is used to reflect the dressing habits of the target-related personnel;

[0213] determining a second clothing storage condition based on historical clothing data;

[0214] When the second clothing state meets the second clothing storage condition, a target available storage area is determined in the second storage space, otherwise, a target available storage area is determined in the third storage space.

[0215] In a possible embodiment, the first storage space includes at least one storage subspace, and the target available storage area is determined in the first storage space. The processing unit 802 is specifically configured to:

[0216] Acquire a first image of the target clothing through a visual component;

[0217] Determining the recognition degree of the target clothing based on the first image;

[0218] When the recognition degree is higher than or equal to a preset recognition degree threshold, the first image is compared with a preset clothing database to obtain a first comparison result, and the first comparison result is used as a target comparison result;

[0219] When the recognition degree is lower than the recognition degree threshold, the flatness of the target clothing is obtained;

[0220] If the flattening degree is lower than a preset flattening degree threshold, the hand component is controlled to perform a flattening operation on the target clothing;

[0221] When the flattening degree is greater than or equal to the flattening degree threshold, acquiring a second image of the target clothing through the visual component;

[0222] Compare the second image with the clothing database to obtain a second comparison result, and use the second comparison result as a target comparison result;

[0223] Determine a clothing feature label of the target clothing based on the target comparison result;

[0224] Determine the folding times of the target clothing and the candidate storage subspace of the target clothing in at least one storage subspace based on the clothing feature tag, and obtain at least one candidate storage subspace;

[0225] Determine a second moving path and a second staying position of the humanoid robot based on a third current position of the humanoid robot and each candidate storage subspace in at least one candidate storage subspace, and obtain at least one second moving path and at least one second staying position;

[0226] Controlling the humanoid robot to move along at least one second moving path to a corresponding second stop position;

[0227] When the humanoid robot is located at at least one second stop position, acquiring remaining space data of at least one candidate storage subspace through a visual component to obtain at least one remaining space data;

[0228] determining a target storage subspace based on the number of folding times and at least one remaining space data;

[0229] Obtaining clothing storage characteristics of the target storage subspace;

[0230] A target available storage area is determined based on clothing storage characteristics and clothing characteristic tags.

[0231] In a possible embodiment, in controlling the hand assembly to perform a flattening operation on the target clothing, the processing unit 802 is specifically configured to:

[0232] Obtaining an initial clothing shape and an initial clothing position of the target clothing;

[0233] Determining a picking height of the humanoid robot based on an initial clothing position;

[0234] Adjust the current posture of the humanoid robot based on the picking height to obtain the target posture;

[0235] Control the humanoid robot to adjust to the target posture;

[0236] determining at least one pick-up point based on the initial garment shape;

[0237] When the humanoid robot is in a target posture, a relative position relationship between the hand component and at least one picking point is acquired to obtain at least one relative position relationship;

[0238] Determine a picking direction of each picking point in at least one picking point based on at least one relative position relationship to obtain at least one picking direction;

[0239] predicting a first weight of the target clothing;

[0240] Determine an initial picking force corresponding to at least one picking point based on the first weight to obtain at least one initial picking force;

[0241] performing a picking operation on the target clothing based on at least one initial picking force, and obtaining a second weight of the target clothing if a picking speed of the target clothing is less than a preset speed threshold;

[0242] Adjusting at least one initial picking force based on the second weight to determine at least one target picking force;

[0243] The target clothing is flattened based on at least one target picking force and at least one picking direction until the flattening degree is higher than or equal to a flattening degree threshold, and it is determined that the flattening operation is completed.

[0244] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any method for controlling a humanoid robot based on clothing storage as recorded in the above method embodiments.

[0245] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the humanoid robot control methods based on clothing storage as recorded in the above method embodiments.

[0246] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0247] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0248] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the modules, which is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or module can be electrical or other forms.

[0249] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0250] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software program modules.

[0251] If the integrated module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0252] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for controlling a humanoid robot based on clothing storage, characterized in that: A controller applied to a humanoid robot, the humanoid robot comprising a visual component, a foot component and a hand component; the method comprising: Acquiring clothing detection data for target clothing in a target area through the visual component specifically includes: acquiring at least one relevant person associated with the target area; acquiring historical behavior data of each of the at least one relevant person in the target area, the historical behavior data including at least one of the following: clothing changing data, clothing storage times; acquiring visiting schedule data of the target area; determining a target detection frequency and a target detection time period of the target area according to the historical behavior data and the visiting schedule data; acquiring spatial layout data of the target area, the spatial layout data being used to reflect the distribution of multiple objects in the target area; determining a detection path and a target detection range of the humanoid robot in the target area based on the spatial layout data; and controlling the humanoid robot to move along the detection path. The method comprises the steps of: moving along a detection path, and adjusting an initial detection angle and an initial detection distance of a visual component based on a first current position of the humanoid robot and the target detection range to obtain a target detection angle and a target detection distance; controlling the visual component to detect clothing within the target detection range based on the target detection angle and the target detection distance based on the target detection frequency and the target detection time period to obtain area detection data; obtaining a target area type of the target area; determining whether the target area has a storage demand based on the area detection data and the target area type; when the target area has the storage demand, determining the target clothing within the target area according to the area detection data; and obtaining clothing detection data of the target clothing through the visual component according to the target area type; determining a target available storage area in a target storage space according to the clothing detection data; Acquire attribute information of the target available storage area; Acquire a storage feature corresponding to the target available storage area, wherein the storage feature includes one of the following: folding, hanging, and placing; Determining a first storage action corresponding to the hand component based on the attribute information and the storage feature, wherein the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: a folding operation, a hanging operation, and a placing operation; Obtaining a target storage height corresponding to the target available storage area; Determining a second storage action corresponding to the foot assembly based on a first current height of the humanoid robot and the target storage height, wherein the second storage action is used to adjust the center of gravity height of the humanoid robot; The humanoid robot is controlled to store the target clothing in the target available storage area based on the first storage action and the second storage action.

2. The method according to claim 1, characterized in that The determining whether the target area has a storage demand based on the area detection data and the target area type includes: When the target area type is a drying area type, obtaining meteorological data, and determining a weather trend corresponding to the meteorological data; If the weather trend is consistent with a preset first trend, determining whether there is at least one first clothing item in the target area based on the area detection data; If the at least one first clothing item exists in the target area, determining that the target area has the storage demand; If the weather trend is consistent with a preset second trend, determining whether there is at least one second clothing item in the target area based on the area detection data; If the quantity of the at least one second clothing item is higher than a preset first quantity threshold, determining that the target area has the storage demand; When the target area type is a multifunctional activity area type, m candidate clothing sets are determined based on the area detection data, where m is a positive integer; Obtaining the position and volume of each candidate clothing set in the m candidate clothing sets, to obtain m clothing set positions and m clothing set volumes; determining a first score of the target area based on the m clothing set positions and the m clothing set volumes, wherein the first score is used to reflect the cleanliness of the target area; Obtaining a reference score threshold for the target area; Determine a target score threshold for the target area based on the reference score threshold and the visit schedule data; When the first score is lower than the target score threshold, determining that the target area has the storage demand; When the target area type is a clean clothes storage area type, determining whether there is at least one third clothing item in the target area; If the quantity of the at least one third clothing item is higher than a preset second quantity threshold, it is determined that the target area has the storage demand.

3. The method according to claim 2, characterized in that When the target area type is the multifunctional activity area type, determining the target clothing in the target area according to the area detection data includes: determining a second score of each of the m candidate clothing sets based on the positions of the m clothing sets and the volumes of the m clothing sets obtained from the region detection data, and obtaining m second scores, wherein the m second scores are used to reflect the neatness of each of the m candidate clothing sets; determining the storage priority of each of the m candidate clothing sets based on the m second scores, to obtain m storage priorities; determining a storage order based on the m storage priorities, the second current position of the humanoid robot, and the m clothing positions; determining a target candidate clothing set based on the storage order, wherein the target candidate clothing set contains at least one candidate clothing; Determining a first stop position of the humanoid robot based on a clothing set position corresponding to the target candidate clothing set; determining a first moving path of the humanoid robot based on the first rest position and the second current position; Controlling the humanoid robot to move along the first moving path to the first stopping position; When the humanoid robot is located at the first stop position, acquiring a stacking relationship of at least one candidate clothing item in the target candidate clothing set through the visual component; Determine the difficulty of picking up the at least one candidate clothing item based on the stacking relationship to obtain at least one picking up difficulty item; Based on the at least one picking-up difficulty, the candidate clothing item with the lowest picking-up difficulty among the at least one candidate clothing item is selected as the target clothing item.

4. The method according to claim 3, characterized in that The determining a target available storage area in a target storage space according to the clothing detection data includes: Determine, according to the clothing detection data, a target related person corresponding to the target clothing among the at least one related person; Determine a target storage space corresponding to the target-related person, the target storage space comprising at least one of the following: a first storage space, a second storage space, and a third storage space, the first storage space being used to store clean clothes, the second storage space being used to store second-clean clothes, and the third storage space being used to store dirty clothes; When the target area type is the drying area type, acquiring a first clothing state of the target clothing according to the clothing detection data, where the first clothing state is used to reflect the dryness of the target clothing; Acquiring environmental humidity data of the target area; determining a first clothing storage condition based on the environmental humidity data; When the first clothing state meets the first clothing storage condition, or when the target area type is the clean clothing storage area type, determining the target available storage area in the first storage space; When the target area type is the multifunctional activity area type, obtaining a second clothing state of the target clothing according to the clothing detection data, wherein the second clothing state is used to reflect the cleanliness of the target candidate clothing; Acquire historical dressing data of the target-related person, where the historical dressing data is used to reflect the dressing habits of the target-related person; determining a second clothing storage condition based on the historical clothing data; When the second clothing state meets the second clothing storage condition, the target available storage area is determined in the second storage space; otherwise, the target available storage area is determined in the third storage space.

5. The method according to claim 4, characterized in that The first storage space includes at least one storage subspace, and determining the target available storage area in the first storage space includes: Acquire a first image of the target clothing through the visual component; determining the recognition degree of the target clothing based on the first image; When the recognition degree is higher than or equal to a preset recognition degree threshold, the first image is compared with a preset clothing database to obtain a first comparison result, and the first comparison result is used as a target comparison result; When the recognition degree is lower than the recognition degree threshold, obtaining the flatness degree of the target clothing; If the flattening degree is lower than a preset flattening degree threshold, controlling the hand component to perform a flattening operation on the target clothing; When the flattening degree is greater than or equal to the flattening degree threshold, acquiring a second image of the target clothing through the visual component; Comparing the second image with the clothing database to obtain a second comparison result, and using the second comparison result as the target comparison result; Determining a clothing feature tag of the target clothing based on the target comparison result; Determine the folding times of the target clothing and the candidate storage subspace of the target clothing in the at least one storage subspace based on the clothing feature tag, and obtain at least one candidate storage subspace; Determining a second moving path and a second staying position of the humanoid robot based on a third current position of the humanoid robot and each candidate storage subspace in the at least one candidate storage subspace, to obtain at least one second moving path and at least one second staying position; Controlling the humanoid robot to move along the at least one second moving path to a corresponding second stop position; When the humanoid robot is located at the at least one second stop position, acquiring the remaining space data of the at least one candidate storage subspace through the visual component to obtain at least one remaining space data; determining a target storage subspace based on the folding number and the at least one remaining space data; Acquiring clothing storage characteristics of the target storage subspace; The target available storage area is determined based on the clothing storage characteristics and the clothing characteristic tags.

6. The method according to claim 5, characterized in that The controlling the hand assembly to perform a flattening operation on the target clothing includes: Acquiring an initial clothing shape and an initial clothing position of the target clothing; Determining a picking height of the humanoid robot based on the initial clothing position; Adjusting the current posture of the humanoid robot based on the picking height to obtain a target posture; Controlling the humanoid robot to adjust to the target posture; determining at least one pick-up point based on the initial garment shape; When the humanoid robot is in the target posture, acquiring a relative position relationship between the hand assembly and the at least one picking point to obtain at least one relative position relationship; Determine a picking direction of each picking point in the at least one picking point based on the at least one relative position relationship to obtain at least one picking direction; predicting a first weight of the target clothing; Determine an initial picking force corresponding to the at least one picking point based on the first weight to obtain at least one initial picking force; performing a picking operation on the target clothing based on the at least one initial picking force, and obtaining a second weight of the target clothing if a picking speed of the target clothing is less than a preset speed threshold; Adjusting the at least one initial picking force based on the second weight to determine at least one target picking force; The target clothing is flattened based on the at least one target picking force and the at least one picking direction until the flattening degree is higher than or equal to the flattening degree threshold, and it is determined that the flattening operation is completed.

7. A humanoid robot control device based on clothing storage, characterized in that: Applied to a humanoid robot, the humanoid robot comprises a visual component, a foot component and a hand component; the device comprises an acquisition unit and a processing unit; The acquisition unit is used to acquire clothing detection data for target clothing in a target area through the visual component, specifically including: acquiring at least one relevant person associated with the target area; acquiring historical behavior data of each of the at least one relevant person in the target area, the historical behavior data including at least one of the following: clothing changing data, clothing storage times; acquiring visit schedule data of the target area; determining the target detection frequency and target detection time period of the target area according to the historical behavior data and the visit schedule data; acquiring spatial layout data of the target area, the spatial layout data being used to reflect the distribution of multiple objects in the target area; determining the detection path and target detection range of the humanoid robot in the target area based on the spatial layout data; and controlling the humanoid robot Move along the detection path, and adjust the initial detection angle and initial detection distance of the visual component based on the first current position of the humanoid robot and the target detection range to obtain a target detection angle and a target detection distance; based on the target detection frequency and the target detection time period, control the visual component to detect the clothes within the target detection range based on the target detection angle and the target detection distance to obtain area detection data; obtain the target area type of the target area; determine whether the target area has a storage demand based on the area detection data and the target area type; when the target area has the storage demand, determine the target clothes within the target area according to the area detection data; according to the target area type, obtain the clothes detection data of the target clothes through the visual component; The processing unit is used to determine a target available storage area in a target storage space according to the clothing detection data; Acquire attribute information of the target available storage area; Acquire a storage feature corresponding to the target available storage area, wherein the storage feature includes one of the following: folding, hanging, and placing; Determining a first storage action corresponding to the hand component based on the attribute information and the storage feature, wherein the first storage action is used to perform a target operation on the target clothing, and the target operation includes one of the following: a folding operation, a hanging operation, and a placing operation; Obtaining a target storage height corresponding to the target available storage area; Determining a second storage action corresponding to the foot assembly based on a first current height of the humanoid robot and the target storage height, wherein the second storage action is used to adjust the center of gravity height of the humanoid robot; The humanoid robot is controlled to store the target clothing in the target available storage area based on the first storage action and the second storage action.

8. A humanoid robot, characterized in that: include: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the humanoid robot executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images