Method and apparatus for controlling mobile body, mobile body, and storage medium

Abstract

The application provides a mobile body control method and device, a mobile body and a storage medium. The method comprises: when detecting that the distance between a target mobile body and a user equipment of a preset person is not less than a first preset distance, controlling an image acquisition component of the target mobile body to capture the surrounding environment of the target mobile body to obtain a corresponding environment image; detecting whether a bound person corresponding to the target mobile body exists in the environment image, and if so, sending position prompt information to the user equipment, wherein the position prompt information is used to indicate the position information of the target mobile body; and in response to a return request sent by the user equipment, planning a driving path of the target mobile body based on the position information of the target mobile body and the position information of the user equipment, so that the target mobile body drives along the driving path to the direction of approaching the user equipment. The child is automatically guided to return to the vicinity of the user equipment, and the child is prevented from getting lost.

Description

Technical Field

[0001] This application relates to the fields of teaching aids, toys, and educational games, and in particular to control methods, devices, moving objects, and storage media for moving objects. Background Technology

[0002] With the increasing popularity of mobile devices (such as smart cars), entertainment scenarios for children are becoming more and more diverse. Smart cars have excellent battery life and portability, allowing children to take them outdoors to play. However, children may inadvertently enter unfamiliar environments while playing with smart cars, and if parents or guardians are not with the children in time, the children may get lost.

[0003] Therefore, there is an urgent need to provide a control method, device, mobile body, and storage medium for a mobile body to improve the existing technology. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, mobile body, and storage medium for controlling a mobile body, which automatically guides the child back to the vicinity of the user equipment after determining that the child is around the mobile body, thereby preventing the child from getting lost.

[0005] The objective of this application is achieved through the following technical solution:

[0006] In a first aspect, this application provides a method for controlling a moving body, for controlling one or more moving bodies, the method comprising:

[0007] When the distance between the target moving body and the user equipment of the preset personnel is not less than the first preset distance, the image acquisition component of the target moving body is controlled to capture the surrounding environment of the target moving body to obtain the corresponding environmental image;

[0008] The system detects whether there is a bound person corresponding to the target moving body in the environmental image. If there is, it sends a location prompt information to the user equipment. The location prompt information is used to indicate the location information of the target moving body.

[0009] In response to a return request sent by the user equipment, a travel path for the target mobile body is planned based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the travel path in a direction closer to the user equipment.

[0010] The beneficial effects of this technical solution are as follows: when the distance between the target mobile body and the user's device is not less than a first preset distance, the surrounding environment is captured by the image acquisition component to obtain an environmental image. The presence of a bound person (e.g., a child, autistic, depressed, or bipolar patient) is detected in the environmental image. If the bound person is near the mobile body, a location prompt message is sent to the user's device to indicate the location of the mobile body. When the user's device requests the mobile body to return, the travel path of the mobile body is automatically planned so that the mobile body travels in a direction closer to the user's device.

[0011] This application takes into account that when children play with a mobile device (such as a smart car), their attention is entirely focused on the mobile device. Once the child and the mobile device are far away from the user device of a preset person (such as the child's parent), the mobile device can determine whether the child is nearby through visual detection, thereby quickly locating the child's position. If the child is determined to be around the mobile device, the mobile device can automatically guide the child back to the vicinity of the user device based on the user device's return request, thus preventing the child from getting lost.

[0012] In some optional embodiments, the method further includes:

[0013] Based on the age and gender of the person being bound, a preset audio is configured for that person. The preset audio includes at least one of the following: synthesized audio, songs, film and television works, folk tales, and white noise.

[0014] Detect whether a preset event has occurred. If it has, control the audio playback component of the target moving body to play the corresponding preset audio.

[0015] The beneficial effects of this technical solution are as follows: people of different ages and genders have different preferences for music or sound. Preset audio can be configured according to the age and gender of the bound person. When a preset event occurs, the audio playback component is controlled to play the corresponding preset audio, thereby providing customized sound services for different bound persons and better enhancing the fun and user experience of the mobile device.

[0016] In some optional embodiments, the preset audio includes synthesized audio, and the process of configuring the synthesized audio includes:

[0017] The user equipment is used to obtain the voice information of the preset person, who is a relative or caregiver of the bound person;

[0018] The voice information is processed by speech synthesis to generate the synthesized audio, which is then sent to the target mobile body. The synthesized audio is used to adjust the emotions of the bound person.

[0019] The beneficial effects of this technical solution are as follows: the preset audio can include synthesized audio. For some bonded individuals who are prone to emotional instability (children, autistic, depressed, or bipolar patients), the user device can be used to collect the voice information of the preset individuals (relatives or caregivers) in advance. When different preset events occur, the voice information is synthesized in real time to generate corresponding synthesized audio, making the bonded individuals feel that the preset individuals are by their side, thereby quickly adjusting the bonded individuals' emotions and reflecting the application of humanistic care.

[0020] In some optional embodiments, the preset event includes at least one of the following: the person being bound is crying; the person being bound is drowsy; the person being bound is behaving abnormally;

[0021] The detection of whether a preset event has occurred includes:

[0022] The image acquisition component is used to capture images of the bound personnel to obtain corresponding personnel images;

[0023] Based on the person's image, obtain the status information of the bound person, and detect whether the preset event has occurred based on the status information.

[0024] The beneficial effects of this technical solution are as follows: It can use an image acquisition component to capture images of the bound person, obtain the person's image, and use visual detection to obtain the state information of the bound person, thereby determining whether a preset event has occurred. The preset event may be that the bound person is crying or drowsy, or that the bound person is behaving abnormally (such as self-harm, suicide, attacking others, or damaging property). In this way, when the preset event occurs, the corresponding synthesized audio can be used in a timely manner to soothe the bound person's emotions, allowing the bound person to calm down quickly and preventing injury to the bound person or property damage.

[0025] In some optional embodiments, obtaining the status information of the bound person based on the person image includes:

[0026] The person image is input into the state detection model to output the state information of the bound person;

[0027] The training process of the state detection model includes:

[0028] Obtain a training set, which includes multiple training data, each of which includes a sample person image and labeled data of the state information corresponding to the sample person image;

[0029] For each training data point in the training set, the following processing is performed:

[0030] The sample personnel images in the training data are input into a preset deep learning model to obtain predicted data of the state information corresponding to the sample personnel images.

[0031] Based on the predicted and labeled data of the state information corresponding to the sample personnel images, the model parameters of the deep learning model are updated.

[0032] The system checks whether the preset training termination condition is met; if so, the trained deep learning model is used as the state detection model; if not, the system continues to train the deep learning model using the next set of training data.

[0033] The beneficial effects of this technical solution are as follows: by designing and establishing an appropriate number of neural computing nodes and a multi-layered computational hierarchy, and by selecting suitable input and output layers, a preset deep learning model can be obtained. Through the learning and optimization of this preset deep learning model, a functional relationship from input to output can be established. Although it is not possible to find a 100% functional relationship between input and output, it can approximate the real-world correlation as closely as possible. The state detection model trained in this way can analyze the state information of the bound personnel based on personnel images, and the analysis results are highly accurate and reliable.

[0034] In some optional embodiments, the method further includes:

[0035] When the distance between the target moving body and any other moving body is detected to be no greater than a second preset distance, the number of moving bodies in a group of moving bodies within a preset area is detected. The group of moving bodies includes the target moving body itself and other moving bodies within the preset area.

[0036] Based on the number of moving bodies, an assembly strategy corresponding to the group of moving bodies is obtained, and the assembly strategy includes at least one of the following: assembly shape and assembly order;

[0037] In response to an assembly request sent by the user equipment, the mobile body group is controlled to assemble according to the assembly strategy.

[0038] The beneficial effect of this technical solution is that when the distance between the target moving body and any other moving body is not greater than the second preset distance, that is, when there are multiple moving bodies in the preset area, the corresponding assembly strategy can be determined according to the number of moving bodies. After receiving the assembly request from the user device, the moving bodies are controlled to assemble according to the assembly strategy. In this way, multiple moving bodies can be assembled into different shapes, further enhancing the fun of the moving bodies and the user experience.

[0039] In some optional embodiments, the method further includes:

[0040] Based on the assembled shape and driving direction of the assembled mobile body group, select one mobile body from the mobile body group as the powered mobile body;

[0041] Control the other mobile bodies in the mobile body group, excluding the powered mobile body, to shut off their power.

[0042] The beneficial effects of this technical solution are: based on the assembly shape and driving direction of the mobile body group, one of the mobile bodies can be determined as the powered mobile body, and the power of the other mobile bodies can be turned off. Only the powered mobile body needs to provide power to support the movement of the mobile body group, which plays a role in energy conservation and environmental protection.

[0043] Secondly, this application provides a control device for a moving body, used to control one or more moving bodies, the device comprising:

[0044] An environmental detection module is used to control the image acquisition component of the target mobile body to capture the surrounding environment of the target mobile body when the distance between the target mobile body and the user equipment of the preset personnel is not less than a first preset distance, so as to obtain a corresponding environmental image.

[0045] The location prompting module is used to detect whether there is a bound person corresponding to the target moving body in the environmental image. If there is, it sends location prompting information to the user equipment. The location prompting information is used to indicate the location information of the target moving body.

[0046] The return planning module is used to respond to the return request sent by the user equipment and plan the driving path of the target mobile body based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the driving path in a direction closer to the user equipment.

[0047] In some optional embodiments, the control device further includes:

[0048] An audio configuration module is used to configure a preset audio for the bound person based on the age and gender of the bound person. The preset audio includes at least one of the following: synthesized audio, songs, film and television works, folk tales, and white noise.

[0049] The audio playback module is used to detect whether a preset event has occurred. If it has, the module controls the audio playback component of the target moving body to play the corresponding preset audio.

[0050] In some optional embodiments, the preset audio includes synthesized audio, which is configured using the following units:

[0051] A voice acquisition unit is used to acquire the voice information of the preset person using the user equipment, wherein the preset person is a relative or caregiver of the bound person;

[0052] A speech synthesis unit is used to synthesize the speech information to generate the synthesized audio and send the synthesized audio to the target mobile body. The synthesized audio is used to adjust the emotions of the bound person.

[0053] In some optional embodiments, the preset event includes at least one of the following: the person being bound is crying; the person being bound is drowsy; the person being bound is behaving abnormally;

[0054] The audio playback module includes:

[0055] The personnel shooting unit is used to capture images of the bound personnel using the image acquisition component to obtain corresponding personnel images;

[0056] An event detection unit is used to obtain the status information of the bound person based on the person image, and to detect whether the preset event has occurred based on the status information.

[0057] In some optional embodiments, the event detection unit is used to:

[0058] The person image is input into the state detection model to output the state information of the bound person;

[0059] The training process of the state detection model includes:

[0060] Obtain a training set, which includes multiple training data, each of which includes a sample person image and labeled data of the state information corresponding to the sample person image;

[0061] For each training data point in the training set, the following processing is performed:

[0062] The sample personnel images in the training data are input into a preset deep learning model to obtain predicted data of the state information corresponding to the sample personnel images.

[0063] Based on the predicted and labeled data of the state information corresponding to the sample personnel images, the model parameters of the deep learning model are updated.

[0064] The system checks whether the preset training termination condition is met; if so, the trained deep learning model is used as the state detection model; if not, the system continues to train the deep learning model using the next set of training data.

[0065] In some optional embodiments, the control device further includes:

[0066] The quantity detection module is used to detect the number of mobile bodies in a preset area when the distance between the target mobile body and any other mobile body is not greater than a second preset distance. The mobile body group includes the target mobile body itself and other mobile bodies in the preset area.

[0067] Based on the number of moving bodies, an assembly strategy corresponding to the group of moving bodies is obtained, and the assembly strategy includes at least one of the following: assembly shape and assembly order;

[0068] In response to an assembly request sent by the user equipment, the mobile body group is controlled to assemble according to the assembly strategy.

[0069] In some optional embodiments, the control device further includes:

[0070] A power selection unit is used to select a mobile body from the mobile body group as a powered mobile body based on the assembled shape and driving direction of the assembled mobile body group;

[0071] A power shut-off unit is used to control the other mobile bodies in the mobile body group, excluding the powered mobile body, to shut off their power.

[0072] Thirdly, this application provides a mobile body, the mobile body including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the above methods.

[0073] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the above methods. Attached Figure Description

[0074] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0075] Figure 1 This is a flowchart illustrating a control method for a moving body provided in an embodiment of this application.

[0076] Figure 2 This is a flowchart illustrating another method for controlling a moving body provided in an embodiment of this application.

[0077] Figure 3 This is a schematic diagram of a configuration and synthesis audio flow provided in an embodiment of this application.

[0078] Figure 4 This is a flowchart illustrating a method for detecting preset events, as provided in an embodiment of this application.

[0079] Figure 5 This is a flowchart illustrating another method for controlling a moving body provided in an embodiment of this application.

[0080] Figure 6 This is a schematic diagram illustrating the effect of assembling a mobile body according to an embodiment of this application.

[0081] Figure 7 This is a structural block diagram of a mobile body provided in an embodiment of this application.

[0082] Figure 8 This is a structural block diagram of a control device for a moving body provided in an embodiment of this application.

[0083] Figure 9 This is a structural block diagram of another movable body provided in the embodiments of this application.

[0084] Figure 10 This is a schematic diagram of the structure of a program product provided in an embodiment of this application. Detailed Implementation

[0085] The present application will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0086] The features described herein may be implemented in different forms and should not be construed as being limited to the examples described herein. Rather, the examples described herein have been provided merely to illustrate some of the many feasible ways of implementing the methods, apparatus, and / or systems described herein that will be apparent upon understanding the disclosure of this application.

[0087] Throughout the specification, when an element (such as a layer, region, or substrate) is described as being "on" another element, "connected to" another element, "bonded to" another element, "on" another element, or "covering" another element, it may be directly "on" another element, "connected to" another element, "bonded to" another element, "on" another element, or "covering" another element, or there may be one or more other elements in between. In contrast, when an element is described as being "directly on" another element, "directly connected to" another element, "directly bonded to" another element, "directly on" another element, or "directly covering" another element, there may be no other elements in between.

[0088] As used herein, the term “and / or” includes any one of the relevant items listed and any combination of any two or more items.

[0089] Although terms such as “first,” “second,” and “third” may be used herein to describe individual components, assemblies, regions, layers, or parts, these components, assemblies, regions, layers, or parts are not limited by these terms. Rather, these terms are used only to distinguish one component, assembly, region, layer, or part from another. Therefore, without departing from the teachings of the examples described herein, the first component, assembly, region, layer, or part referred to as the second component, assembly, region, layer, or part may also be referred to as the second component, assembly, region, layer, or part.

[0090] For ease of description, spatial relation terms such as “above,” “upper,” “below,” and “lower” are used herein to describe the relationship between one element and another, as shown in the accompanying drawings. Such spatial relation terms are intended to include not only the orientation depicted in the drawings but also different orientations of the device during use or operation. For example, if the device in the drawings is flipped, an element described as being “above” or “upper” relative to another element will subsequently be “below” or “lower” relative to that other element. Therefore, the term “above” includes both “above” and “below” orientations depending on the spatial orientation of the device. The device may also be positioned in other ways (e.g., rotated 90 degrees or in other orientations), and the spatial relation terms used herein will be interpreted accordingly.

[0091] The terminology used herein is for the purpose of describing various examples only and is not intended to limit this disclosure. Unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. The terms “comprising,” “including,” and “having” enumerate the stated features, quantities, operations, components, elements, and / or combinations thereof, but do not exclude the presence or addition of one or more other features, quantities, operations, components, elements, and / or combinations thereof.

[0092] Variations in the shapes shown in the accompanying drawings may occur due to manufacturing techniques and / or tolerances. Therefore, the examples described herein are not limited to the specific shapes shown in the accompanying drawings, but include changes in shape that may occur during manufacturing.

[0093] The features of the examples described herein can be combined in various ways that will be apparent upon understanding the disclosure of this application. Furthermore, although the examples described herein have a wide variety of constructions, other constructions are possible, as will be apparent upon understanding the disclosure of this application.

[0094] A mobile body refers to a mobile device (such as a smart car or an emotional companion robot) that obtains hidden information from an information medium. The information medium refers to the medium carrier containing the hidden information. The mobile body is equipped with a host (including a memory and a processor). The host can process the parsed hidden information and coordinate and control one or more mobile bodies.

[0095] Currently, toys on the market with the function of recognizing hidden information basically fall into two categories:

[0096] (1) Color recognition toys: include a single moving body that uses a limited number of colors and color combinations as an information medium to obtain hidden information and uses a color sensor to obtain hidden information. That is, after the moving body obtains hidden information on the information medium, the moving body processes the obtained hidden information and feeds it back to the moving body's own motion function.

[0097] (2) Code pattern recognition toys: include multiple mobile bodies that use predefined code patterns as information mediums to hide information and use optical reading terminals to acquire the hidden information, and a host responsible for information processing and control units. That is, the multiple mobile bodies parse and process the acquired hidden information into basic information and send it to the host. The host receives the basic information and performs corresponding feedback control on the multiple mobile bodies.

[0098] The following drawbacks were found in the application of color recognition toys:

[0099] 1. Color as a storage method for hidden information is limited in terms of content types. The limited types and combinations of colors can only store simple hidden information and cannot store information such as the position or angle of a moving object.

[0100] 2. Color recognition is easily affected by factors such as light, medium material, and background color, which in turn affects the movement function and stability of the moving object.

[0101] The following drawbacks were found in the application of code pattern recognition toys:

[0102] 1. The device cannot be separated from the host. The host sends coordination and control commands via Bluetooth, so the mobile device cannot move far away from the host or play in the scene without the host. In addition, the host requires a wired power supply, which also limits the user's playing environment.

[0103] 2. Scene cartridges are required. When playing different scenes, it is necessary to switch cartridges. The small size of the cartridges makes them easy to lose when storing, which increases the user's usage cost.

[0104] 3. The moving objects only have buzzers and can only play simple tones. When playing in the scene, all audio needs to be played through the host's speakers. Therefore, when multiple moving objects are played, the moving objects and their corresponding audio will be confused.

[0105] 4. To play a scene with moving objects, the host computer needs to connect to at least two moving objects. Even if a sub-scene only requires one moving object, the host computer still needs to connect to two moving objects to play the sub-scene.

[0106] The following section will introduce a control method, apparatus, mobile body, and storage medium for a mobile body, in order to improve upon the prior art.

[0107] Method Implementation Examples

[0108] See Figure 1 , Figure 1 This is a flowchart illustrating a control method for a moving body provided in an embodiment of this application.

[0109] This application provides a method for controlling a moving body, which is used to control one or more moving bodies, the method including steps S101 to S103.

[0110] Step S101: When the distance between the target moving body and the user equipment of the preset personnel is not less than the first preset distance, the image acquisition component of the target moving body is controlled to capture the surrounding environment of the target moving body to obtain the corresponding environmental image.

[0111] In the embodiments of this application, the mobile body may be, for example, a smart car or an emotional companion robot.

[0112] User equipment can be, for example, a mobile phone, tablet computer, laptop computer, desktop computer, smart wearable device or other smart terminal device, or a workstation or console.

[0113] The user equipment can communicate with one or more mobile bodies using any of the following methods: Bluetooth, WiFi, ZigBee, WiGig, microwave, satellite, and atmospheric laser. The target mobile body is any mobile body that maintains a communication connection with the user equipment.

[0114] The first preset distance can be, for example, 100 meters, 200 meters, 300 meters, 500 meters, or 1000 meters.

[0115] Both the target moving object and the user equipment can be equipped with positioning modules, and the distance can be determined through the positioning modules of both.

[0116] The positioning module may include, for example, a GPS positioning unit, BeiDou, Galileo, or GLONASS; it can also be an indoor positioning unit. Both the target mobile object and the user equipment utilize indoor positioning technology to obtain their current positions.

[0117] The target mobile body and user equipment can also obtain the distance directly based on the strength of the communication signal.

[0118] The image acquisition component can be, for example, a camera, and the surrounding environment of the moving target can be, for example, an area with the moving target as the center and a radius of a preset length. The preset length can be, for example, 0.5 meters, 0.8 meters, 1.2 meters, 1.5 meters, or 2 meters.

[0119] Step S102: Detect whether there is a bound person corresponding to the target mobile body in the environmental image. If there is, send location prompt information to the user equipment. The location prompt information is used to indicate the location information of the target mobile body.

[0120] In this embodiment, the bound person is a person who has pre-registered to use the mobile device, such as a child, autistic, depressed, or bipolar disorder patient. The pre-registered person can be a relative or caregiver of the bound person.

[0121] The method may further include:

[0122] Every preset time interval, the system checks whether the bound person exists in the environmental image. If not, it sends the location and time information corresponding to the last appearance of the bound person to the user equipment.

[0123] The system uses an image acquisition component of the target moving object to monitor the bound personnel in real time. Once it is found that the bound personnel are no longer near the target moving object, the location and time of the last appearance of the bound personnel are immediately reported to the user equipment, so that the pre-set personnel can take appropriate measures (such as rushing to the vicinity of the location immediately).

[0124] The preset duration can be, for example, 1 minute, 3 minutes, 5 minutes or 10 minutes.

[0125] In a specific application, an environmental image is collected every minute for a total of 9 times. The first 8 environmental images all contain the bound personnel (in the 8th environmental image, the collection time is 12:45, and the location information of the target moving object is A). In the 9th environmental image, there is no bound personnel, so the time "12:45" and the location "A" are reported to the user equipment.

[0126] Step S103: In response to the return request sent by the user equipment, plan the driving path of the target mobile body based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the driving path in a direction closer to the user equipment.

[0127] Therefore, when the distance between the target mobile body and the user's device is not less than the first preset distance, the surrounding environment is captured by the image acquisition component to obtain an environmental image. The system detects whether there is a bound person (e.g., a child, autistic, depressed, or bipolar disorder patient) in the environmental image. If the bound person is near the mobile body, the system sends a location prompt to the user's device to indicate the location of the mobile body. When the user's device requests the mobile body to return, the system automatically plans the travel path of the mobile body so that the mobile body travels in a direction closer to the user's device.

[0128] This application embodiment takes into account that when children are playing with a mobile device (such as a smart car), their attention is entirely focused on the mobile device. Once the child and the mobile device are far away from the user device of a preset person (such as the child's parent), the mobile device can determine whether the child is nearby through visual detection, thereby quickly locating the child's position. If it is determined that the child is around the mobile device, the mobile device can automatically guide the child back to the vicinity of the user device according to the return request from the user device, so as to prevent the child from getting lost.

[0129] See Figure 2 , Figure 2 This is a flowchart illustrating another method for controlling a moving body provided in an embodiment of this application.

[0130] In some optional embodiments, the method may further include steps S104 to S105.

[0131] Step S104: Based on the age and gender of the bound person, configure the preset audio corresponding to the bound person. The preset audio includes at least one of the following: synthesized audio, songs, film and television works, folk tales, and white noise.

[0132] In one specific application, the person being bound is 3 years old and female, and the corresponding preset audio could be the song "Only Mother is Good in the World".

[0133] The person being bound is 5 years old and male, and the corresponding preset audio can be the original soundtrack of the animated series "Calabash Brothers".

[0134] Step S105: Detect whether a preset event has occurred. If it has, control the audio playback component of the target moving body to play the corresponding preset audio.

[0135] Therefore, people of different ages and genders have different preferences for music or sound. Preset audio can be configured according to the age and gender of the bound person. When a preset event occurs, the audio playback component is controlled to play the corresponding preset audio, thereby providing customized sound services for different bound people and better enhancing the fun and user experience of the mobile device.

[0136] In some implementations, the preset event may include: receiving a voice control command from a bound person or a preset person; the OID (Optical Identification) reader of the target moving object recognizing the code pattern of the preset object.

[0137] For example, the voice recognition component of the target moving body can be used to recognize the voice information of the bound person or the preset person. The voice recognition component may include a microphone and a voice recognition chip. When the voice information of the bound person or the preset person is recognized, including content such as "play a song" or "play music", the audio playback component is controlled to play audio.

[0138] For example, the preset items may include cards or maps, and the code pattern may be a QR code. The hidden information in the QR code may include at least one of the following: Chinese characters, letters, biographical information, folk customs, electronic sound effects, etc.

[0139] When the moving target comes into contact with the target object (such as a card), the OID reader recognizes the QR code (corresponding to Chinese characters or letters) on the card, and can act as a reading pen to play the pronunciation of Chinese characters or letters.

[0140] See Figure 3 , Figure 3 This is a schematic diagram of a configuration process for synthesized audio provided in an embodiment of this application.

[0141] In some optional embodiments, the preset audio includes synthesized audio, and the process of configuring the synthesized audio in step S104 includes steps S201 to S202.

[0142] Step S201: Use the user equipment to obtain the voice information of the preset person, where the preset person is a relative or caregiver of the bound person.

[0143] Step S202: Perform speech synthesis on the voice information to generate the synthesized audio and send the synthesized audio to the target mobile body. The synthesized audio is used to adjust the emotions of the bound person.

[0144] Therefore, the preset audio can include synthesized audio. For some bonded individuals who are prone to emotional instability (children, autistic patients, patients with depression or bipolar disorder), the voice information of the preset individuals (relatives or caregivers) can be collected in advance using the user's device. When different preset events occur, the voice information is synthesized in real time to generate corresponding synthesized audio, making the bonded individuals feel that the preset individuals are by their side, thereby quickly adjusting the bonded individuals' emotions and reflecting the application of humanistic care.

[0145] In some implementations, step S202 may include: performing speech synthesis on the voice information based on the event type of the preset event to generate the synthesized audio and sending the synthesized audio to the target mobile body.

[0146] For example, the preset event type could be: the bound person (child) is crying. The mother's voice information (audio of some Chinese characters) can be pre-recorded using her mobile phone. When the child is found to be crying, the voice is synthesized in real time to generate synthesized audio such as "Baby, don't cry, Mommy is here" or "Baby, don't be afraid, Mommy is here".

[0147] For example, the event type of the preset event could be: the person being bound (a person with depression) is self-harming. The voice information (audio of some Chinese characters) of the patient's relatives can be recorded in advance using the patient's relatives' mobile phones. When the patient is found to be harming himself, the voice is synthesized in real time to generate synthesized audio such as "I need you" or "I love you, please love yourself too".

[0148] In some optional embodiments, the preset event includes at least one of the following: the person being bound is crying; the person being bound is drowsy; the person being bound is behaving abnormally.

[0149] Abnormal behavior refers to the bound person engaging in at least one of the following behaviors: self-harm, suicide, attacking others, or damaging property.

[0150] See Figure 4 , Figure 4 This is a flowchart illustrating a method for detecting preset events, as provided in an embodiment of this application.

[0151] The step S105, which detects whether a preset event has occurred, may include steps S301 to S302.

[0152] Step S301: Use the image acquisition component to capture images of the bound personnel to obtain corresponding personnel images;

[0153] Step S302: Based on the person image, obtain the status information of the bound person, and detect whether the preset event has occurred based on the status information.

[0154] Therefore, an image acquisition component can be used to capture images of the bound person, and visual detection methods can be used to obtain the state information of the bound person, thereby determining whether a preset event has occurred. The preset event could be that the bound person is crying or drowsy, or that the bound person is behaving abnormally (such as self-harm, suicide, attacking others, or damaging property). In this way, when the preset event occurs, the corresponding synthesized audio can be used in a timely manner to soothe the bound person's emotions, allowing the bound person to calm down quickly and preventing injury or property damage.

[0155] In some optional embodiments, obtaining the status information of the bound person based on the person image in step S302 may include:

[0156] The person image is input into the state detection model to output the state information of the bound person;

[0157] The training process of the state detection model includes:

[0158] Obtain a training set, which includes multiple training data, each of which includes a sample person image and labeled data of the state information corresponding to the sample person image;

[0159] For each training data point in the training set, the following processing is performed:

[0160] The sample personnel images in the training data are input into a preset deep learning model to obtain predicted data of the state information corresponding to the sample personnel images.

[0161] Based on the predicted and labeled data of the state information corresponding to the sample personnel images, the model parameters of the deep learning model are updated.

[0162] The system checks whether the preset training termination condition is met; if so, the trained deep learning model is used as the state detection model; if not, the system continues to train the deep learning model using the next set of training data.

[0163] Therefore, by designing and establishing an appropriate number of neural computing nodes and a multi-layered computational hierarchy, and selecting suitable input and output layers, a pre-defined deep learning model can be obtained. Through the learning and optimization of this pre-defined deep learning model, a functional relationship from input to output can be established. Although it is not possible to find a 100% accurate functional relationship between input and output, it can approximate the real-world correlation as closely as possible. The state detection model trained in this way can analyze the state information of the bound personnel based on personnel images, and the analysis results are highly accurate and reliable.

[0164] This application does not limit the method of obtaining the annotation data of the status information. For example, it can be done by manual annotation, automatic annotation, or semi-automatic annotation.

[0165] In some implementations, each sample person image is either actually captured or generated using a generative network of a GAN model.

[0166] Generative Adversarial Networks (GANs) are a novel framework for estimating generative models through an adversarial process. The framework trains two models simultaneously: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that samples originate from the training data. The training procedure for G is to maximize the probability that D is wrong. It can be proven that in the space of any functions G and D, there exists a unique solution such that G reproduces the training data distribution, while D = 0.5 (D cannot determine whether a sample is true or false, with a 50% probability, similar to a coin toss). When G and D are defined by a multilayer perceptron, they can be trained using backpropagation.

[0167] The embodiments of this application do not limit the training process of the state detection model. For example, it can adopt the supervised learning training method described above, or the semi-supervised learning training method, or the unsupervised learning training method.

[0168] The embodiments of this application do not limit the preset training termination conditions. For example, it may be that the number of training sessions reaches a preset number (the preset number of training sessions is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), or it may be that the training data in the training set has completed one or more training sessions, or it may be that the total loss value obtained in this training is not greater than the preset loss value.

[0169] See Figure 5 , Figure 5 This is a flowchart illustrating another method for controlling a moving body provided in an embodiment of this application.

[0170] In some optional embodiments, the method may further include steps S106 to S108.

[0171] Step S106: When it is detected that the distance between the target moving body and any other moving body is not greater than the second preset distance, the number of moving bodies in the moving body group within the preset area is detected. The moving body group includes the target moving body itself and other moving bodies within the preset area.

[0172] In this embodiment, the second preset distance can be, for example, 2 cm, 5 cm, 8 cm, 10 cm, 20 cm, or 50 cm. The preset area can be, for example, an area with a radius of 5 meters centered on the moving target.

[0173] Step S107: Based on the number of moving bodies, obtain the assembly strategy corresponding to the moving body group, wherein the assembly strategy includes at least one of the following: assembly shape and assembly order.

[0174] The shape of the movable object can be a cube, cuboid, triangular prism, cylinder, cone, or hexagonal prism.

[0175] Accordingly, the assembly shape can be a long strip with the movable bodies arranged in a line, a honeycomb shape, or a closed ring structure.

[0176] The assembly order can be determined based on the identifiers of the mobile objects. For example, if the number of mobile objects in a mobile object group is 5, the identifiers of each mobile object are: A02, A03, A05, A01 and A04.

[0177] The mobile units can be assembled into a long strip in a row. The assembly order can be arranged in ascending order of the labels. The mobile units are positioned according to the labels A01, A02, A03, A04 and A05, and then assembled in sequence.

[0178] The assembly method between two adjacent moving bodies may include at least one of the following: snap-fit, magnetic attraction and vacuum adsorption, and the embodiments of this application do not limit this.

[0179] See Figure 6 , Figure 6 This is a schematic diagram illustrating the effect of assembling the mobile body according to an embodiment of this application.

[0180] Taking the snap-fit ​​as an example, each movable body has at least one side with an outwardly protruding snap post and at least one telescopic block. The outwardly protruding end of the snap post has at least one groove. Each telescopic block is telescopically mounted in its corresponding groove. In addition, each movable body has a positioning hole on the side without snap posts and telescopic blocks.

[0181] When mobile body A in the mobile body assembly is to be assembled with mobile body B, the side of mobile body B with the positioning hole is aligned with the side of mobile body A with the locking post and telescopic block. The telescopic block of mobile body A is then retracted into the groove so that the locking post of mobile body A is inserted into the positioning hole of mobile body B. After mobile body A and mobile body B are in place, the telescopic block of mobile body A is extended from the corresponding groove, thereby realizing the assembly of mobile body A and mobile body B.

[0182] When mobile body A in the mobile body assembly needs to be disassembled from mobile body B, the telescopic block of mobile body A is controlled to retract into the groove so that the locking pin of mobile body A is moved out of the positioning hole of mobile body B. Then, the telescopic block of mobile body A is controlled to extend out from the corresponding groove, thereby disassembling the assembly of mobile body A and mobile body B.

[0183] Step S108: In response to the assembly request sent by the user equipment, control the mobile body group to assemble according to the assembly strategy.

[0184] Therefore, when the distance between the target mobile body and any other mobile body is no greater than the second preset distance, that is, when there are multiple mobile bodies in the preset area, the corresponding assembly strategy can be determined according to the number of mobile bodies. After receiving the assembly request from the user device, the mobile bodies are controlled to assemble according to the assembly strategy. In this way, multiple mobile bodies can be assembled into different shapes, further enhancing the fun of the mobile bodies and the user experience.

[0185] In some optional embodiments, the method further includes:

[0186] Based on the assembled shape and driving direction of the assembled mobile body group, select one mobile body from the mobile body group as the powered mobile body;

[0187] Control the other mobile bodies in the mobile body group, excluding the powered mobile body, to shut off their power.

[0188] Therefore, based on the assembly shape and driving direction of the mobile body group, one of the mobile bodies can be designated as the powered mobile body, and the other mobile bodies can be controlled to shut off their power. Only the powered mobile body needs to provide power to support the movement of the mobile body group, which plays a role in energy conservation and environmental protection.

[0189] In some implementations, the selection of the powered moving body may include any of the following:

[0190] Based on the direction of travel of the mobile body group, the mobile body at the foremost position is designated as the powered mobile body;

[0191] The largest moving body in the moving body group is designated as the powered moving body;

[0192] The mobile body with the largest mass (weight) in the mobile body group is designated as the powered mobile body.

[0193] Turning off the power means stopping the drive components that control the movement of the device. These drive components can be, for example, a motor, an air pump, or a hydraulic pump.

[0194] To address the shortcomings of traditional color recognition toys and code pattern recognition toys, this application provides a mobile object that can be used as a toy.

[0195] Compared to color recognition toys, this mobile device uses a better information medium (code pattern), which can store more and more complex hidden information. It is minimally affected by factors such as light, medium material, and medium background color, which greatly improves the movement function and stability of the mobile device.

[0196] Compared to code and pattern recognition toys, this mobile device eliminates the physical host and uses a mobile APP as a virtual host for one or more mobile devices, solving the space limitation problem and power safety problem caused by the need for a host with a power supply in the play scene;

[0197] In addition, the mobile unit has been equipped with speakers, which also allows audio to be played when it is detached from the main unit.

[0198] In the scene switching function, clicking to identify the information medium replaces the traditional cartridge switching, greatly reducing the operational threshold.

[0199] The aforementioned mobile device utilizes a code pattern as an information medium, solving the following problems inherent in existing technologies that use color as an information medium: 1. Limitations on the complexity of stored information; 2. The impact of environmental factors on the movement and stability of the mobile device; 3. Spatial limitations imposed by the host on the mobile device; 4. Limitations imposed by the host on the number of mobile devices; 5. Insufficient control methods for the mobile device; 6. Low hardware functional expansion capabilities of the mobile device.

[0200] Specifically, this mobile device uses a code pattern as the information medium instead of color, solving two problems: the limitation of information storage complexity when using color as the storage medium, and the impact of environmental factors on the movement function and stability of the mobile device when using color as the storage medium. In addition, this patent is mainly for a single mobile device play scenario, so eliminating the host can effectively solve the problems of the host's spatial limitation on the mobile device and the host's limitation on the number of mobile devices. Furthermore, this mobile device also increases the interaction methods between the user and the mobile device by adding voice recognition, and uses expansion pins to allow the mobile device to add more hardware peripherals, improving the mobile device's expandability and fun.

[0201] This mobile device abandons the traditional use of color as an information medium and master-slave hardware combination, avoiding the technical shortcomings of traditional color recognition toys and code pattern recognition toys, lowering the operation threshold of code pattern recognition toys, and providing a simple, integrated, scientific, convenient, and portable toy.

[0202] The mobile object can be shaped like a small car with grooves and protrusions on its back, allowing it to be combined with building blocks to form various shapes, making it highly expandable. It can be used not only directly via mobile phone remote control, but also with cards and maps, and can be programmed for diverse gameplay.

[0203] Furthermore, the car has its own CPU, meaning the brain and the mobile unit (master and slave) are integrated; the speaker is not an ordinary horn, but can emit a variety of sounds, making it an audio player; in addition, it contains an optical read terminal (OID read head).

[0204] This mobile device uses QR codes as the information medium, is a master-slave integrated device, is easy to operate, and is small in size, avoiding the technical shortcomings of traditional color recognition toys and QR code recognition toys; in addition, it is equipped with a speaker and can produce a variety of sounds.

[0205] See Figure 7 , Figure 7 This is a structural block diagram of a mobile body provided in an embodiment of this application.

[0206] The components and functions of the mobile body 10 are described below. The mobile body 10 includes a main control module 11, function buttons 12, information reading module 13, motion detection module 14, walking mechanism 15, speaker 16, and LED light 17.

[0207] Among them, the main control module 11 performs IO control; it has two communication methods, Wi-Fi and Bluetooth, and can perform wireless communication, such as communication with the mobile APP 20.

[0208] Function key 12: Power on / off and trigger functions.

[0209] Information reading module 13: Composed of an optical ID reader, it can perform location and identifier detection. Essentially, it reads QR codes on a map to determine coordinates, which is a key feature, similar to a reading pen.

[0210] Motion detection module 14: Composed of an accelerometer, it has a monitoring function to monitor whether the moving body 10 touches other objects, etc.

[0211] Walking mechanism 15: It consists of left and right motors and two wheels, which complete the walking function of the moving body 10.

[0212] Speaker 16: Plays audio.

[0213] LED light 17: Used for information indication.

[0214] See Figure 8 , Figure 8 This is a structural block diagram of a control device for a moving body provided in an embodiment of this application. Its specific implementation method is consistent with the implementation method and the technical effects achieved in the above method embodiment, and some contents will not be repeated.

[0215] The device is used to control one or more moving bodies, and the device includes:

[0216] The environmental detection module 101 is used to control the image acquisition component of the target mobile body to capture the surrounding environment of the target mobile body when the distance between the target mobile body and the user equipment of the preset personnel is not less than a first preset distance, so as to obtain the corresponding environmental image.

[0217] Location prompting module 102 is used to detect whether there is a bound person corresponding to the target moving body in the environmental image. If there is, it sends location prompting information to the user equipment. The location prompting information is used to indicate the location information of the target moving body.

[0218] The return planning module 103 is used to respond to the return request sent by the user equipment and plan the driving path of the target mobile body based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the driving path in a direction closer to the user equipment.

[0219] In some optional embodiments, the control device further includes:

[0220] An audio configuration module is used to configure a preset audio for the bound person based on the age and gender of the bound person. The preset audio includes at least one of the following: synthesized audio, songs, film and television works, folk tales, and white noise.

[0221] The audio playback module is used to detect whether a preset event has occurred. If it has, the module controls the audio playback component of the target moving body to play the corresponding preset audio.

[0222] In some optional embodiments, the preset audio includes synthesized audio, which is configured using the following units:

[0223] A voice acquisition unit is used to acquire the voice information of the preset person using the user equipment, wherein the preset person is a relative or caregiver of the bound person;

[0224] A speech synthesis unit is used to synthesize the speech information to generate the synthesized audio and send the synthesized audio to the target mobile body. The synthesized audio is used to adjust the emotions of the bound person.

[0225] In some optional embodiments, the preset event includes at least one of the following: the person being bound is crying; the person being bound is drowsy; the person being bound is behaving abnormally;

[0226] The audio playback module includes:

[0227] The personnel shooting unit is used to capture images of the bound personnel using the image acquisition component to obtain corresponding personnel images;

[0228] An event detection unit is used to obtain the status information of the bound person based on the person image, and to detect whether the preset event has occurred based on the status information.

[0229] In some optional embodiments, the event detection unit is used to:

[0230] The person image is input into the state detection model to output the state information of the bound person;

[0231] The training process of the state detection model includes:

[0232] Obtain a training set, which includes multiple training data, each of which includes a sample person image and labeled data of the state information corresponding to the sample person image;

[0233] For each training data point in the training set, the following processing is performed:

[0234] The sample personnel images in the training data are input into a preset deep learning model to obtain predicted data of the state information corresponding to the sample personnel images.

[0235] Based on the predicted and labeled data of the state information corresponding to the sample personnel images, the model parameters of the deep learning model are updated.

[0236] The system checks whether the preset training termination condition is met; if so, the trained deep learning model is used as the state detection model; if not, the system continues to train the deep learning model using the next set of training data.

[0237] In some optional embodiments, the control device further includes:

[0238] The quantity detection module is used to detect the number of mobile bodies in a preset area when the distance between the target mobile body and any other mobile body is not greater than a second preset distance. The mobile body group includes the target mobile body itself and other mobile bodies in the preset area.

[0239] Based on the number of moving bodies, an assembly strategy corresponding to the group of moving bodies is obtained, and the assembly strategy includes at least one of the following: assembly shape and assembly order;

[0240] In response to an assembly request sent by the user equipment, the mobile body group is controlled to assemble according to the assembly strategy.

[0241] In some optional embodiments, the control device further includes:

[0242] A power selection unit is used to select a mobile body from the mobile body group as a powered mobile body based on the assembled shape and driving direction of the assembled mobile body group;

[0243] A power shut-off unit is used to control the other mobile bodies in the mobile body group, excluding the powered mobile body, to shut off their power.

[0244] See Figure 9 , Figure 9 This is a structural block diagram of another movable body provided in the embodiments of this application.

[0245] This application also provides a mobile body, which includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0246] The memory 210 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 211 and / or cache memory 212, and may further include read-only memory (ROM) 213.

[0247] The memory 210 also stores a computer program, which can be executed by the processor 220, causing the processor 220 to perform the steps of the method described in the embodiments of this application. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above method embodiments, and some contents will not be repeated.

[0248] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0249] Accordingly, processor 220 can execute the aforementioned computer program, and can also execute utility 214.

[0250] Bus 230 can represent one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any of the various bus structures.

[0251] The mobile device can also communicate with one or more external devices 240, such as a keyboard, pointing device, Bluetooth device, etc., and with one or more devices capable of interacting with the mobile device, and / or with any device that enables the mobile device to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can be performed via input / output interface 250. Furthermore, the mobile device can communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of the mobile device via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the mobile device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0252] This application also provides a computer-readable storage medium, the specific implementation of which is consistent with the implementation methods and technical effects achieved in the above method embodiments, and some contents will not be repeated.

[0253] The computer-readable storage medium is used to store a computer program; when the computer program is executed, it implements the steps of the method described in the embodiments of this application.

[0254] Figure 10 This embodiment illustrates a program product for implementing the above-described method, which may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of this invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0255] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0256] This application elaborates on the purpose of use, effectiveness, progress, and novelty. Its practical progress meets the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings are only preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar to or identical to those of this application, i.e., all equivalent substitutions or modifications made in accordance with the scope of this patent application, shall fall within the scope of protection of this patent application.

Claims

1. A method for controlling a moving body, characterized in that, The method for controlling one or more moving bodies includes: When the distance between the target moving body and the user equipment of the preset personnel is not less than the first preset distance, the image acquisition component of the target moving body is controlled to capture the surrounding environment of the target moving body to obtain the corresponding environmental image; The system detects whether there is a bound person corresponding to the target moving body in the environmental image. If there is, it sends a location prompt information to the user equipment. The location prompt information is used to indicate the location information of the target moving body. In response to a return request sent by the user equipment, a travel path for the target mobile body is planned based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the travel path in a direction closer to the user equipment; The method further includes: Every preset time interval, the system checks whether the bound person exists in the environmental image. If not, it sends the location and time information corresponding to the last appearance of the bound person to the user equipment.

2. The control method according to claim 1, characterized in that, The method further includes: Based on the age and gender of the person being bound, a preset audio is configured for that person. The preset audio includes at least one of the following: synthesized audio, songs, film and television works, folk tales, and white noise. Detect whether a preset event has occurred. If it has, control the audio playback component of the target moving body to play the corresponding preset audio.

3. The control method according to claim 2, characterized in that, The preset audio includes synthesized audio, and the process of configuring the synthesized audio includes: The user equipment is used to obtain the voice information of the preset person, who is a relative or caregiver of the bound person; The voice information is processed by speech synthesis to generate the synthesized audio, which is then sent to the target mobile body. The synthesized audio is used to adjust the emotions of the bound person.

4. The control method according to claim 3, characterized in that, The preset event includes at least one of the following: the bound person is crying; The person being bound was drowsy; The bound personnel are behaving abnormally; The detection of whether a preset event has occurred includes: The image acquisition component is used to capture images of the bound personnel to obtain corresponding personnel images; Based on the person's image, obtain the status information of the bound person, and detect whether the preset event has occurred based on the status information.

5. The control method according to claim 4, characterized in that, The step of obtaining the status information of the bound person based on the person image includes: The person image is input into the state detection model to output the state information of the bound person; The training process of the state detection model includes: Obtain a training set, which includes multiple training data, each of which includes a sample person image and labeled data of the state information corresponding to the sample person image; For each training data point in the training set, the following processing is performed: The sample personnel images in the training data are input into a preset deep learning model to obtain predicted data of the state information corresponding to the sample personnel images. Based on the predicted and labeled data of the state information corresponding to the sample personnel images, the model parameters of the deep learning model are updated. The system checks whether the preset training termination condition is met; if so, the trained deep learning model is used as the state detection model; if not, the system continues to train the deep learning model using the next set of training data.

6. The control method according to claim 1, characterized in that, The method further includes: When the distance between the target moving body and any other moving body is detected to be no greater than a second preset distance, the number of moving bodies in a group of moving bodies within a preset area is detected. The group of moving bodies includes the target moving body itself and other moving bodies within the preset area. Based on the number of moving bodies, an assembly strategy corresponding to the group of moving bodies is obtained, and the assembly strategy includes at least one of the following: assembly shape and assembly order; In response to an assembly request sent by the user equipment, the mobile body group is controlled to assemble according to the assembly strategy.

7. The control method according to claim 6, characterized in that, The method further includes: Based on the assembled shape and driving direction of the assembled mobile body group, select one mobile body from the mobile body group as the powered mobile body; Control the other mobile bodies in the mobile body group, excluding the powered mobile body, to shut off their power.

8. A control device for a moving body, characterized in that, The device for controlling one or more moving bodies includes: An environmental detection module is used to control the image acquisition component of the target mobile body to capture the surrounding environment of the target mobile body when the distance between the target mobile body and the user equipment of the preset personnel is not less than a first preset distance, so as to obtain a corresponding environmental image. The location prompting module is used to detect whether there is a bound person corresponding to the target moving body in the environmental image. If there is, it sends location prompting information to the user equipment. The location prompting information is used to indicate the location information of the target moving body. The return planning module is used to respond to the return request sent by the user equipment and plan the driving path of the target mobile body based on the location information of the target mobile body and the location information of the user equipment, so that the target mobile body travels along the driving path in a direction closer to the user equipment; The device is also used for: Every preset time interval, the system checks whether the bound person exists in the environmental image. If not, it sends the location and time information corresponding to the last appearance of the bound person to the user equipment.

9. A mobile body, characterized in that, The mobile body includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-7.

Images