Robot control method and device, robot and readable storage medium

Abstract

The application provides a robot control method and device, a robot and a readable storage medium. The robot control method comprises the following steps: acquiring scene information of a target scene; determining a target region where a target object is located according to the scene information; acquiring at least one target image of the target region, the target image containing the target object; determining behavior information of the target object according to the at least one target image; and controlling the robot to work according to the behavior information.

Description

Technical Field

[0001] This application relates to the field of robotics, and more specifically, to a robot control method and apparatus, a robot, and a readable storage medium. Background Technology

[0002] Currently, with the development of robotics technology, the application of home service robots is becoming increasingly widespread. However, the functions of existing home service robots are not yet perfect, and they cannot autonomously perform targeted tasks in certain special home scenarios. For example, in the case of pets fighting at home, users not only need to personally stop the fighting, but also need to clean up the pet hair shed during the fight. This easily interrupts the user's process and fails to meet the user's needs. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art or related technologies.

[0004] Therefore, the first aspect of this application is to propose a robot control method.

[0005] The second aspect of this application is to provide a robot control device.

[0006] The third aspect of this application is to propose another robot control device.

[0007] The fourth aspect of this application is to propose a robot.

[0008] The fifth aspect of this application is to propose a readable storage medium.

[0009] In view of this, according to one aspect of this application, a robot control method is proposed, the method comprising: acquiring scene information of a target scene; determining a target area where a target object is located based on the scene information; acquiring at least one target image of the target area, the target image containing the target object; determining behavioral information of the target object based on the at least one target image; and controlling the robot to work based on the behavioral information.

[0010] The robot control method provided in this application can be implemented by a robot, a robot control device, or, depending on the actual application requirements, without specific limitations. To more clearly describe the robot control method provided in this application, the following explanation will focus on the robot control device as the implementing entity.

[0011] The robot control method provided in this application is used to control the operation of a robot, so as to analyze and identify the behavior of a target object in a target scene and perform targeted work, thereby realizing the robot's monitoring operation of the target object.

[0012] Specifically, in the robot control method provided in this application, during the robot's operation in a target scene, the robot control device acquires scene information of the target scene collected by the robot, and then, based on the acquired scene information, identifies and analyzes target objects within the target scene to determine the target area where the target object is located within the target scene. Furthermore, the robot control device acquires at least one target image collected by the robot at at least one location within the target area, wherein each target image contains the target object. Further, based on the acquired at least one target image including the target object, the robot control device analyzes and identifies the target object's actions within the target area to obtain the target object's behavioral information. Based on this, the robot control device controls the robot to perform corresponding tasks based on the target object's behavioral information. Thus, based on the scene information of the target scene collected by the robot, the robot analyzes and identifies the target object's actions within the target scene, thereby controlling the robot to perform targeted work based on the target object's actions. In this way, the robot can autonomously monitor the behavior of the target object, enrich the robot's functional modes, and increase the robot's application scenarios. In certain special application scenarios, such as pet fighting scenarios, it frees up the user's hands, thereby avoiding interruption of the user's task processing process and meeting the user's needs.

[0013] The robot control method described above in this application may also have the following additional technical features:

[0014] In the above technical solution, the scene information includes sound information. Determining the target area where the target object is located based on the scene information includes: performing spectrum recognition on the sound information to determine the target sound in the sound information, and the target sound corresponds to the target object; determining the target area based on the target sound.

[0015] In this technical solution, the robot is equipped with sound acquisition devices such as recording devices and radios, and the scene information includes the sound information of the target scene.

[0016] Based on this, during the process of the robot control device determining the target area where the target object is located, specifically, during the robot's operation, the robot control device controls the sound acquisition device on the robot to collect various sound information within the target scene. The robot control device acquires the sound information within the target scene collected by the sound acquisition device in real time and performs spectrum recognition on the acquired sound information to detect whether there is a target sound corresponding to the target object among the multiple sounds in the target scene. If a target sound is detected, the robot control device determines that a target object exists within the target scene and determines the location of the detected target sound source. Then, based on the determined sound source location, it determines the location information of the target object within the target scene, thereby determining the target area where the target object is located. In this way, by performing spectrum analysis on the sound information within the target scene, identifying the target object, and determining the location information of the target object within the target scene, the accuracy of the target area determination is ensured, thereby improving the accuracy of subsequent robot operation control.

[0017] In any of the above technical solutions, the scene information includes image information. Determining the target area where the target object is located based on the scene information includes: performing target detection on the image information to determine the target object image in the image information, wherein the target object image corresponds to the target object; and determining the target area based on the target object image.

[0018] In this technical solution, the robot is equipped with an image acquisition device such as a camera, and the scene information includes image information of the target scene.

[0019] Based on this, during the process of the robot control device determining the target area where the target object is located, specifically, during the robot's operation, the robot control device controls the image acquisition device on the robot to acquire image information within the target scene. The robot control device acquires the image information within the target scene acquired by the image acquisition device in real time, and based on the acquired scene image information, performs target detection on the target scene to detect whether there are target objects such as cats or dogs within the target scene. If a target object is detected, the robot control device determines the corresponding position information of the target object within the target scene based on the position information of the target object in the scene image, thereby determining the target area where the target object is located. In this way, target detection based on the image information within the target scene to determine the position information of the target object within the target scene ensures the accuracy of the target area determination, thereby improving the accuracy of subsequent robot operation control.

[0020] In any of the above technical solutions, determining the behavioral information of a target object based on at least one target image includes: performing image segmentation on at least one target image to determine the target object image in the target image; extracting feature point information of the target object image; determining the pose information and feature point position information of the target object based on the feature point information; and determining the behavioral information based on the pose information and feature point position information.

[0021] In this technical solution, during the process of the robot control device analyzing and recognizing the behavior of the target object within the target area, the robot control device specifically performs segmentation processing on each acquired target image to segment the object contour in each target image, thereby obtaining the target object image corresponding to the target object in each target image. Based on this, the robot control device performs feature extraction on each determined target object image to obtain the feature point information of the target object in each target object image. Further, based on the feature point information of the target object in each target object image, the robot control device determines the feature point position information and posture information of the target object in each target object image, thereby determining the posture changes and position changes of the target object in each target object image. Further, based on the posture changes and position changes of the target object in each target object image, the robot control device determines the posture type and quantity information of the target object, thereby determining the behavior of the target object and obtaining the behavior information of the target object. In this way, by analyzing and recognizing the behavior of the target object based on the feature point information of the target object in at least one target image, the accuracy of determining the behavior information of the target object is ensured, thereby ensuring the accuracy of subsequent robot control based on this behavior information.

[0022] In any of the above technical solutions, determining behavior information based on posture information and feature point location information includes: when the posture information indicates that there are at least two target objects, and the feature point location information indicates that at least two target objects have overlapping areas in at least one target image, the behavior information is determined to be target behavior information.

[0023] In this technical solution, during the process of the robot control device analyzing and recognizing the behavior of the target object based on its feature point position information and posture information, specifically, the robot control device determines the number of target objects in the target area based on the posture information of the target object. Further, when the posture information of the target object indicates the presence of at least two target objects in the target area, the robot control device determines the image overlap of the at least two target objects in each target image based on the feature point position information of the target objects, thereby determining the posture type of the at least two target objects. Based on this, when at least two target objects have overlapping feature points in each target image, that is, when the images of at least two target objects have overlapping areas in each target image, the robot control device determines that the target object exhibits a target posture, that is, determines the behavior information of the target object as target behavior information. In this way, by determining the number and posture type of the target objects based on their feature point position information and posture information, and thus determining the behavior information of the target objects, the robot achieves behavior monitoring of the target objects, enriches the robot's functional modes, and expands the robot's application scenarios.

[0024] In any of the above technical solutions, controlling the robot to work based on behavioral information includes: when the behavioral information is target behavioral information, controlling the robot to move to the target location where the target object is located; controlling the robot to perform the target task to drive the target object out of the target area; and controlling the robot to clean the target area.

[0025] In this technical solution, when the robot control device determines that the behavior information of the target object is target behavior information, that is, when the robot control device determines that at least two target objects are entangled with each other, that is, when the robot control device determines that at least two target objects are fighting in the target area, the robot control device controls the robot to move to the target location where the target object is located, and controls the robot to perform the corresponding target task to release the entanglement between the at least two target objects, so that the at least two target objects are separated from each other, and so that the at least two target objects are driven out of the target area.

[0026] Furthermore, in practical applications, the robot can be equipped with a cleaning device. After the robot control device drives the target object out of the target area, it can also control the robot to clean the target area using the cleaning device to remove any residue such as hair left by the target object. In this way, if the target object engages in fighting, the robot can drive it away and clean up its residue, achieving autonomous monitoring of the target object's behavior. This enriches the robot's functional modes, expands its application scenarios, frees up the user's hands, avoids interrupting the user's work, and meets the user's needs.

[0027] In any of the above technical solutions, after determining the target area where the target object is located based on the scene information, the robot control method further includes: when the target area is a set area, or when the target area is a set area and the system time is within a set time period, controlling the robot to move to the target area and perform the target task to drive away the target object; wherein, the number of set areas and set time periods is one or more, and one set area corresponds to one or more set time periods.

[0028] In this technical solution, the user can set a restricted area for the target object by inputting operations on the robot. Based on this, after the robot control device determines that the target object is located in the target area of ​​the target scene based on the scene information, the robot control device can compare the target area with the user-defined restricted area, and if it determines that the target object is currently located in the user-defined restricted area, it controls the robot to move to the restricted area and execute the corresponding target task to drive away the target object.

[0029] In this technical solution, furthermore, while the user sets the restricted areas for the target object, the restricted time for each restricted area can also be set. Based on this, after the robot control device determines that the target object is located in the target area of ​​the target scene, the robot control device can compare this target area with the user-set restricted areas (i.e., the aforementioned set areas), and compare the robot's current system time with the user-set restricted time (i.e., the aforementioned set time period). Further, if the robot control device determines that the target object is currently in a restricted area and the current time is the restricted time for that area, the robot control device controls the robot to move to the restricted area and execute the corresponding target task to drive away the target object. However, if the robot control device determines that the target object is currently in a restricted area but the current time is not the restricted time for that area, the robot control device will not control the robot to perform the driving-away operation.

[0030] In this way, the robot can flexibly drive away target objects based on the user-defined restricted areas and restricted times, realizing the robot's autonomous monitoring of the target object's behavior, enriching the robot's functional modes, increasing the robot's application scenarios, and freeing up the user's hands, thereby avoiding interruptions to the user's task processing process and meeting the user's needs.

[0031] The number of designated areas and designated time periods mentioned above can be one or more, with one designated area corresponding to one or more designated time periods. In other words, the robot control method proposed in this invention supports setting one or more restricted areas, and for each restricted area, it supports setting one or more pet restricted time periods. For example, a user can set the kitchen and bedroom as restricted areas. For the kitchen, the user can set three restricted time periods: breakfast, lunch, and dinner. For the bedroom, the user can set only one restricted time period: evening rest.

[0032] In any of the above technical solutions, after determining the behavioral information of the target object based on at least one target image, the robot control method further includes: determining at least one first region in the target scene based on the historical behavioral information of the target object and the historical cleaning data of the robot, wherein the first region is a high-frequency gathering area of ​​the target object or a key cleaning area of ​​the robot; and controlling the robot to perform target detection or cleaning work on at least one first region according to the target frequency.

[0033] In this technical solution, after the robot control device determines the behavioral information of the target object, the robot can save this information. Simultaneously, after completing the cleaning task, the robot can also save cleaning data such as the cleaning area and cleaning time. Based on this, the robot control device can retrieve historical cleaning data stored in the robot and historical behavioral information of the target object to determine the key cleaning areas of the target scene and the high-frequency gathering areas of the target object within the target scene—that is, to determine the aforementioned first area. Furthermore, the robot control device increases the monitoring frequency of the first area, controlling the robot to monitor and detect the first area at a target frequency to detect the presence of the target object within the first area and to detect the target object's actions within the first area, and to promptly clean the first area. In this way, by increasing the monitoring and cleaning frequency of key cleaning areas and high-frequency gathering areas of the target object within the target scene based on the robot's historical cleaning data and the target object's historical behavioral information, it is possible to promptly stop fighting or destructive behavior by the target object and to promptly clean dirty areas of the target scene, improving the reliability of the robot's operation and meeting user needs.

[0034] According to a second aspect of this application, a robot control device is proposed, the device comprising: an acquisition unit for acquiring scene information of a target scene; a processing unit for determining a target area where a target object is located based on the scene information; the acquisition unit is further configured to acquire at least one target image of the target area, the target image containing the target object; the processing unit is further configured to determine behavioral information of the target object based on the at least one target image; and a control unit for controlling the robot to work based on the behavioral information.

[0035] The robot control device provided in this application is used to control the operation of a robot, so as to analyze and identify the behavior of a target object in a target scene and perform targeted work, thereby realizing the robot's monitoring operation of the target object.

[0036] Specifically, the robot control device provided in this application includes an acquisition unit, a processing unit, and a control unit. During the robot's operation in a target scene, the acquisition unit acquires scene information of the target scene collected by the robot. The processing unit then identifies and analyzes target objects within the target scene based on the acquired scene information, thereby determining the target area where the target object is located within the target scene. Furthermore, the acquisition unit acquires at least one target image collected by the robot at at least one location within the target area, wherein each target image contains the target object. Further, the processing unit analyzes and identifies the target object's actions within the target area based on the acquired at least one target image containing the target object, thereby obtaining the target object's behavioral information. Based on this, the control unit controls the robot to perform corresponding tasks based on the target object's behavioral information. Thus, by analyzing and identifying the target object's actions within the target scene based on the scene information collected by the robot, the robot is controlled to perform targeted work based on the target object's actions. In this way, the robot can autonomously monitor the behavior of the target object, enrich the robot's functional modes, and increase the robot's application scenarios. In certain special application scenarios, such as pet fighting scenarios, it frees up the user's hands, thereby avoiding interruption of the user's task processing process and meeting the user's needs.

[0037] According to a third aspect of this application, another robot control device is proposed, comprising: a memory storing a program or instructions; and a processor that, when executing the program or instructions, implements the steps of the robot control method as described in any of the above-described technical solutions. Therefore, the robot control device proposed in the third aspect of this application possesses all the beneficial effects of the robot control method in any of the technical solutions of the first aspect, which will not be elaborated further here.

[0038] According to a fourth aspect of this application, a robot is proposed, comprising the robot control device described in the third aspect above. The robot proposed in this fourth aspect includes the robot control device described in the third aspect above. Therefore, the robot proposed in this fourth aspect possesses all the beneficial effects of the robot control device described in the third aspect above, which will not be elaborated further here.

[0039] According to the fifth aspect of this application, a readable storage medium is proposed, on which a program or instructions are stored, which, when executed by a processor, implement the robot control method as described in any of the above-described technical solutions. Therefore, the readable storage medium proposed in the fifth aspect of this application possesses all the beneficial effects of the robot control method in any of the technical solutions of the first aspect, and will not be elaborated further here.

[0040] Additional aspects and advantages of this application will become apparent in the following description or may be learned by practice of this application. Attached Figure Description

[0041] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0042] Figure 1 One of the flowcharts of the robot control method according to an embodiment of this application is shown;

[0043] Figure 2 A second schematic flowchart of a robot control method according to an embodiment of this application is shown;

[0044] Figure 3 The third schematic flowchart of the robot control method according to an embodiment of this application is shown;

[0045] Figure 4 The fourth schematic flowchart of the robot control method according to an embodiment of this application is shown;

[0046] Figure 5 The fifth schematic flowchart of the robot control method according to an embodiment of this application is shown;

[0047] Figure 6 The sixth illustration shows a flowchart of a robot control method according to an embodiment of this application;

[0048] Figure 7 One of the structural block diagrams of the robot control device according to an embodiment of this application is shown;

[0049] Figure 8 A second structural block diagram of a robot control device according to an embodiment of this application is shown;

[0050] Figure 9 A structural block diagram of a robot according to an embodiment of this application is shown. Detailed Implementation

[0051] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below.

[0053] The following is combined with Figures 1 to 9 The robot control method and device, robot and readable storage medium provided in this application will be described in detail through specific embodiments and application scenarios.

[0054] In one embodiment of this application, such as Figure 1 As shown, the robot control method may specifically include the following steps 102 to 110:

[0055] Step 102: Obtain scene information for the target scene;

[0056] Step 104: Determine the target area where the target object is located based on the scene information;

[0057] Step 106: Obtain at least one target image of the target region;

[0058] Step 108: Determine the behavioral information of the target object based on at least one target image;

[0059] Step 110: Control the robot to work based on behavioral information;

[0060] The target image contains the target object.

[0061] The robot control method provided in this application can be executed by a robot, a robot control device, or, depending on the actual application requirements, without specific limitations. To more clearly describe the robot control method provided in this application, the following explanation will focus on the robot control device as the executing entity.

[0062] The robot control method provided in this application is used to control the operation of a robot, so as to analyze and identify the behavior of a target object in a target scene and perform targeted work, thereby realizing the robot's monitoring operation of the target object.

[0063] In practical applications, the aforementioned robots can specifically be intelligent robots with autonomous mobility, such as cleaning robots, photography robots, children's companion robots, and question-and-answer robots, without any specific restrictions.

[0064] Specifically, in the robot control method provided in this application, during the robot's operation in a target scene, the robot control device acquires scene information of the target scene collected by the robot, and then, based on the acquired scene information, identifies and analyzes target objects within the target scene to determine the target area where the target object is located within the target scene. Furthermore, the robot control device acquires at least one target image collected by the robot at at least one location within the target area, wherein each target image contains the target object. Further, based on the acquired at least one target image including the target object, the robot control device analyzes and identifies the target object's actions within the target area to obtain the target object's behavioral information. Based on this, the robot control device controls the robot to perform corresponding tasks based on the target object's behavioral information. Thus, based on the scene information of the target scene collected by the robot, the robot analyzes and identifies the target object's actions within the target scene, thereby controlling the robot to perform targeted work based on the target object's actions. In this way, the robot can autonomously monitor the behavior of the target object, enrich the robot's functional modes, and increase the robot's application scenarios. In certain special application scenarios, such as pet fighting scenarios, it frees up the user's hands, thereby avoiding interruption of the user's task processing process and meeting the user's needs.

[0065] Specifically, the target scene can be a room scene or a house scene, and the target object can be an animal object such as a cat or a dog.

[0066] Furthermore, in practical applications, the robot can be equipped with an image acquisition device such as a camera. During the process of the robot control device acquiring scene information of the target scene, the robot control device can specifically control the image acquisition device on the robot to acquire scene image information of the target scene.

[0067] Based on this, during the process of the robot control device identifying and analyzing target objects in the target scene, the robot control device can specifically perform target detection on the target objects in the target scene based on the scene image information collected by the robot, so as to identify whether there are target objects such as cats and dogs in the target scene.

[0068] Specifically, during the process of the robot control device detecting target objects in the target scene, the robot control device can use AI (Artificial Intelligence) recognition algorithms to detect whether there are animal facial features in the target scene, and determine that there are target objects in the target scene if animal facial features are detected.

[0069] Furthermore, in practical applications, the robot can also pre-store the target object image. During the target detection process of the robot control device, the robot control device can specifically retrieve the pre-stored target object image in the robot, match and compare the target object image with the acquired scene image, and determine that there is a target object in the target scene if the target object image and the scene image are successfully matched.

[0070] Based on this, in the process of the robot control device determining the target area where the target object is located in the target scene, specifically, after the robot control device determines that there is a target object in the target scene based on the scene image information, the robot control device can determine the corresponding position information of the target object in the target scene based on the position information of the target object in the scene image, thereby determining the target area where the target object is located.

[0071] Furthermore, in practical applications, the aforementioned robot can also be equipped with sound acquisition devices such as recording devices and radios. During the process of the robot control device acquiring scene information of the target scene, the robot control device can specifically control the sound acquisition device on the robot to acquire scene sound information of the target scene.

[0072] Based on this, during the process of the robot control device identifying and analyzing the target object in the target scene, the robot control device can specifically perform spectrum recognition on the sound information in the target scene based on the scene sound information collected by the robot, so as to detect whether there are target sounds such as cat meows or dog barks that correspond to the target object among multiple sounds in the target scene, and determine that there is a target object in the target scene when the target sound is detected.

[0073] Based on this, in the process of the robot control device determining the target area where the target object is located in the target scene, specifically, after the robot control device determines that there is a target object in the target scene based on the scene sound information, the robot control device can determine the location of the sound source of the detected target sound, and then determine the location information of the target object in the target scene based on the determined sound source location, thereby determining the target area where the target object is located.

[0074] Furthermore, in the robot control method proposed in this application, the robot may also be equipped with a moving mechanism such as wheels, which enables the robot to move autonomously. Furthermore, the robot may also pre-store a scene map of the target scene.

[0075] Based on this, during the process of the robot control device acquiring at least one target image of the target area collected by the robot, specifically, the robot control device controls the robot to move to the target area via its moving mechanism based on the scene map. Further, the robot control device then controls the robot to move to at least one location within the target area, and at each location, controls the image acquisition device on the robot to capture images of the target object, thereby obtaining at least one target image including the target object.

[0076] Furthermore, during the process of the robot control device analyzing and recognizing the behavior of the target object within the target area, the robot control device can specifically analyze and process at least one target image to determine the position information and feature point information of the target object in each target image. Then, based on the determined position information and feature point information, the number of target objects and the posture changes of each target object are determined to obtain the behavior information of the target object.

[0077] In this embodiment of the application, the scene information further includes sound information, and based on this, such as Figure 2 As shown, step 104 above may specifically include steps 104a and 104b as follows:

[0078] Step 104a: Perform spectrum recognition on the sound information to determine the target sound in the sound information;

[0079] Step 104b: Determine the target area based on the target sound;

[0080] In this context, the target sound corresponds to the target object.

[0081] In this embodiment, the robot is equipped with a sound acquisition device such as a recording device or a receiver, and the scene information includes the sound information of the target scene.

[0082] Based on this, during the process of the robot control device determining the target area where the target object is located, specifically, during the robot's operation, the robot control device controls the sound acquisition device on the robot to collect various sound information within the target scene. The robot control device acquires the sound information within the target scene collected by the sound acquisition device in real time and performs spectrum recognition on the acquired sound information to detect whether there is a target sound corresponding to the target object among the multiple sounds in the target scene. If a target sound is detected, the robot control device determines that a target object exists within the target scene and determines the location of the detected target sound source. Then, based on the determined sound source location, it determines the location information of the target object within the target scene, thereby determining the target area where the target object is located. In this way, by performing spectrum analysis on the sound information within the target scene, identifying the target object, and determining the location information of the target object within the target scene, the accuracy of the target area determination is ensured, thereby improving the accuracy of subsequent robot operation control.

[0083] During the process of the robot control device detecting the target sound, the device can specifically identify the spectral range of each sound in the target scene, and then compare the spectral range of each sound with a preset spectral range, which is the animal spectral range. If the spectral range of a sound falls within the preset spectral range, the robot control device identifies that sound as the target sound.

[0084] Furthermore, in practical applications, the robot can also pre-store the target audio of the target object. During the process of the robot control device detecting the target sound, the robot control device can specifically retrieve the pre-stored target audio in the robot, match and compare the target audio with various sound information of the target scene, and if a certain sound information is successfully matched with the target audio, the sound information is identified as the target sound.

[0085] In this embodiment of the application, the scene information further includes image information, and based on this, such as Figure 3 As shown, step 104 above may specifically include steps 104c and 104d as follows:

[0086] Step 104c: Perform target detection on the image information to determine the target object image in the image information;

[0087] Step 104d: Determine the target region based on the target object image;

[0088] Among them, the target object image corresponds to the target object.

[0089] In this embodiment, the robot is equipped with an image acquisition device such as a camera, and the scene information includes image information of the target scene.

[0090] Based on this, during the process of the robot control device determining the target area where the target object is located, specifically, during the robot's operation, the robot control device controls the image acquisition device on the robot to acquire image information within the target scene. The robot control device acquires the image information within the target scene acquired by the image acquisition device in real time, and based on the acquired scene image information, performs target detection on the target scene to detect whether there are target objects such as cats or dogs within the target scene. If a target object is detected, the robot control device determines the corresponding position information of the target object within the target scene based on the position information of the target object in the scene image, thereby determining the target area where the target object is located. In this way, target detection based on the image information within the target scene to determine the position information of the target object within the target scene ensures the accuracy of the target area determination, thereby improving the accuracy of subsequent robot operation control.

[0091] Specifically, during the process of target detection in the target scene by the robot control device, the robot control device can detect whether there are animal facial features in the target scene based on AI recognition algorithms, and determine that there is a target object in the target scene if animal facial features are detected.

[0092] Furthermore, in practical applications, the robot can also pre-store the target object image. During the target scene detection process of the robot control device, the robot control device can specifically retrieve the pre-stored target object image in the robot, match and compare the target object image with the acquired scene image information, and determine that there is a target object in the target scene if the target object image and the scene image information are successfully matched.

[0093] In the embodiments of this application, further, as Figure 4 As shown, step 108 above may specifically include steps 108a to 108d as follows:

[0094] Step 108a: Perform image segmentation on at least one target image to determine the target object image in the target image;

[0095] Step 108b: Extract feature point information from the target object image;

[0096] Step 108c: Determine the feature point location information and pose information of the target object based on the feature point information;

[0097] Step 108d: Determine the behavior information of the target object based on the feature point location information and pose information.

[0098] In this embodiment, during the process of the robot control device analyzing and recognizing the behavior of the target object within the target area, the robot control device specifically performs segmentation processing on each acquired target image to segment the object contour of the target object in each target image, thereby obtaining the target object image corresponding to the target object in each target image. Based on this, the robot control device performs feature extraction on each determined target object image to obtain the feature point information of the target object in each target object image. Further, based on the feature point information of the target object in each target object image, the robot control device determines the feature point position information and posture information of the target object in each target object image, thereby determining the posture changes and position changes of the target object in each target object image. Further, based on the posture changes and position changes of the target object in each target object image, the robot control device determines the posture type and quantity information of the target object, thereby determining the behavior of the target object and obtaining the behavior information of the target object. In this way, by analyzing and recognizing the behavior of the target object based on the feature point information of the target object in at least one target image, the accuracy of determining the behavior information of the target object is ensured, thereby ensuring the accuracy of subsequent robot control based on this behavior information.

[0099] Specifically, the aforementioned feature point information may include facial feature point information of the target object, such as the feature information of key facial points like the mouth, eyes, and nose. It may also include limb feature point information of the target object, such as the feature information of key limb points like the elbow joint and claws. In practical applications, those skilled in the art can set the specific content of the aforementioned feature point information according to the actual situation, and no specific limitations are imposed here.

[0100] Furthermore, the aforementioned feature point information can specifically be the skeletal keypoint information of the target object. After obtaining the target object image, skeletal keypoint detection processing is performed on each target object image to extract the skeletal keypoint information in each target object image. Specifically, the aforementioned skeletal keypoint information may include the positional information and connectivity information of the skeletal keypoints. By analyzing the skeletal keypoint information of the target object, the pose changes and positional changes of the target object are determined, thereby obtaining the behavioral information of the target object.

[0101] In addition, it should be noted that in the robot control method proposed in this application, the number of target objects in the target area can also be determined during the process of detecting target objects through scene image information or scene sound information, without any specific limitations.

[0102] In the embodiments of this application, further, as Figure 5 As shown, step 108d above may specifically include the following step 108d1:

[0103] Step 108d1: If the pose information indicates that there are at least two target objects within the target area, and the feature point position information indicates that at least two target objects have overlapping areas in each target image, then the behavior information is determined to be the target behavior information.

[0104] In this embodiment, during the process of the robot control device analyzing and recognizing the behavior of the target object based on its feature point position information and posture information, specifically, the robot control device determines the number of target objects in the target area based on the posture information of the target object. Further, when the posture information of the target object indicates the presence of at least two target objects in the target area, the robot control device determines the image overlap of the at least two target objects in each target image based on the feature point position information of the target objects, thereby determining the posture type of the at least two target objects. Based on this, when at least two target objects have overlapping feature points in each target image, that is, when the images of at least two target objects have overlapping areas in each target image, the robot control device determines that the target object exhibits a target posture, that is, determines the behavior information of the target object as target behavior information. In this way, by determining the number and posture type of the target objects based on their feature point position information and posture information, and thus determining the behavior information of the target objects, the robot achieves behavior monitoring of the target objects, enriches the robot's functional modes, and expands the robot's application scenarios.

[0105] The aforementioned target behavior information is used to indicate that at least two target objects are entangled with each other, that is, the aforementioned target posture represents that the target objects are engaging in fighting behavior.

[0106] Furthermore, in the process of determining the number of target objects in the target area by the robot control device, the robot control device can specifically determine the number of limbs of the target object in the target object image based on the posture information of the target object, and thus determine the quantity information of the target object.

[0107] Furthermore, the robot control device determines the number of target objects based on the number of the same feature points, such as the number of mouths, in each target object image.

[0108] Furthermore, in the robot control method proposed in this application, the robot control device can also determine the number of target objects within the target area during the process of detecting target objects through scene image information or scene sound information, without making specific limitations.

[0109] Furthermore, in practical applications, the robot can pre-store posture images of the target object under different posture types, such as a target object sleeping alone, two target objects sleeping together, or two target objects fighting. Based on this, during the process of determining the posture type of the target object, the robot control device can specifically retrieve the pre-stored posture images, match and compare the target object's posture information with these images, determine the target object's posture type based on the matching result, and update the posture images stored in the robot.

[0110] In the embodiments of this application, further, as Figure 6 As shown, step 110 above may specifically include the following steps 110a to 110c:

[0111] Step 110a: If the behavior information is the target behavior information, control the robot to move to the target position;

[0112] Step 110b: Control the robot to perform the target task;

[0113] Step 110c: Control the robot to clean the target area.

[0114] In this embodiment, when the robot control device determines that the behavior information of the target object is target behavior information, that is, when the robot control device determines that at least two target objects are entangled with each other, that is, when the robot control device determines that at least two target objects are fighting in the target area, the robot control device controls the robot to move to the target location where the target object is located, and controls the robot to perform the corresponding target task to release the entanglement between the at least two target objects, so that the at least two target objects are separated from each other, and so that the at least two target objects are driven out of the target area.

[0115] Furthermore, in practical applications, the robot can be equipped with a cleaning device. After the robot control device drives the target object out of the target area, it can also control the robot to clean the target area using the cleaning device to remove any residue such as hair left by the target object. In this way, if the target object engages in fighting, the robot can drive it away and clean up its residue, achieving autonomous monitoring of the target object's behavior. This enriches the robot's functional modes, expands its application scenarios, frees up the user's hands, avoids interrupting the user's work, and meets the user's needs.

[0116] Specifically, during the process of the robot control device controlling the robot to perform the corresponding target task in order to drive away the target object, the robot control device can control the robot to move between at least two target objects and track the target objects to move until the target objects are driven out of the target area.

[0117] Furthermore, the robot may also be equipped with a sound playback device such as a speaker. During the process of the robot control device controlling the robot to drive away the target object, the robot control device can specifically control the robot to move to the target position and then play a set audio through the sound playback device on it, so as to drive the target object out of the target area by emitting sound.

[0118] The audio set mentioned above can be either the system audio stored in the robot or user-defined audio, without any specific restrictions.

[0119] In this embodiment of the application, after step 104, the robot control method may further include the following step 112:

[0120] Step 112: If the target area is a set area, or if the system time is within a set time period and the target area is a set area, control the robot to move to the target area and then control the robot to perform the target task.

[0121] The number of set areas and set time periods can be one or more, with one set area corresponding to one or more set time periods.

[0122] In this embodiment, the user can set a restricted area for a target object by inputting commands to the robot. For example, the user can set rooms such as the kitchen, study, and bathroom as restricted areas for the target object. Based on this, after the robot control device determines that the target object is located in the target area of ​​the target scene based on the scene information, the robot control device can compare the target area with the user-set restricted area. If it is determined that the target object is currently located in the user-set restricted area, the robot control device will move to the restricted area and execute the corresponding target task to drive away the target object.

[0123] In this embodiment, furthermore, while the user sets the restricted areas for the target object, the restricted time for each restricted area can also be set. For example, the user can set the restricted time for the kitchen to breakfast, lunch, and dinner time periods; the restricted time for the study to work time periods; the restricted time for the bathroom to rest time periods; and the restricted time for the bedroom to pet shedding time periods, etc. Based on this, after the robot control device determines that the target object is located in the target area of ​​the target scene, the robot control device can compare the target area with the user-set restricted areas (i.e., the aforementioned set areas), and compare the robot's current system time with the user-set restricted time periods (i.e., the aforementioned set time periods). Further, if the robot control device determines that the target object is currently in a restricted area and the current time is the restricted time for that area, the robot control device controls the robot to move to the restricted area and execute the corresponding target task to drive away the target object. However, if the robot control device determines that the target object is currently in a restricted area but the current time is not the restricted time for that area, the robot control device will not control the robot to perform the driving-away operation.

[0124] In this way, the robot can flexibly drive away target objects based on the user-defined restricted areas and restricted times, realizing the robot's autonomous monitoring of the target object's behavior, enriching the robot's functional modes, increasing the robot's application scenarios, and freeing up the user's hands, thereby avoiding interruptions to the user's task processing process and meeting the user's needs.

[0125] The number of designated areas and designated time periods mentioned above can be one or more, with one designated area corresponding to one or more designated time periods. In other words, the robot control method proposed in this invention supports setting one or more restricted areas, and for each restricted area, it supports setting one or more pet restricted time periods. For example, a user can set the kitchen and bedroom as restricted areas. For the kitchen, the user can set three restricted time periods: breakfast, lunch, and dinner. For the bedroom, the user can set one restricted time period: evening rest.

[0126] In practical applications, users can set the restricted areas and restricted times using an application installed on electronic devices such as mobile phones and tablets. This application is associated with the robot and stores a scene map of the target environment.

[0127] Building upon this foundation, during the process of setting up restricted areas for pets through the application, users can specifically select one or more rooms as restricted areas for their pets. Users can also use touch controls on the application interface to define one or more rectangular, square, circular, or other shaped areas within the target scene as restricted areas for their pets. Furthermore, after setting up at least one restricted area for their pet, users can also configure parameters such as the number of times the robot cleans each restricted area after the pet is successfully driven away, and the cleaning duration.

[0128] Furthermore, during the process of the robot control device controlling the robot to drive away the target object, the robot control device can specifically control the robot to track the target object and move it until the target object is driven out of the restricted area. Furthermore, the robot control device can also control the robot to play a preset audio through its sound playback device, thereby driving the target object out of the restricted area by emitting sound.

[0129] Specifically, when the robot drives away pets by playing audio, it can play high-frequency ultrasonic waves to further enhance the effect of driving away pets.

[0130] Furthermore, the robot can also be equipped with at least one light-emitting device, such as an LED light, and the robot control device can also control the light-emitting device on the robot to flash at a specific frequency and with a specific light color, thereby driving away pets.

[0131] In practical applications, the robot can use any one of the above-mentioned driving-away operations to drive away the pet, or it can use a combination of two or more driving-away operations to drive away the pet; no specific restrictions are imposed here. For example, while controlling the robot to play a set audio through its sound playback device, the robot's control device can also control the robot's light-emitting device to flash at a high frequency to further enhance the driving-away effect on the pet.

[0132] In this embodiment of the application, after step 108, the robot control method may further include steps 114 and 116 as follows:

[0133] Step 114: Based on the robot's historical cleaning data and the target object's historical behavior information, determine at least one first area in the target scene;

[0134] Step 116: Control the robot to perform cleaning or target detection work on at least one first area according to the target frequency;

[0135] The first area is the robot's key cleaning area or the area where target objects frequently gather.

[0136] In this embodiment, after the robot control device determines the behavioral information of the target object, the robot can save this information. Simultaneously, after completing the cleaning task, the robot can also save cleaning data such as the cleaning area and cleaning time. Based on this, the robot control device can retrieve historical cleaning data stored in the robot and historical behavioral information of the target object to determine the key cleaning areas of the target scene and the high-frequency gathering areas of the target object within the target scene—that is, to determine the aforementioned first area. Furthermore, the robot control device increases the monitoring frequency of the first area, controlling the robot to monitor and detect the first area at a target frequency to detect the presence of the target object within the first area and to detect the target object's actions within the first area, and to promptly clean the first area. Thus, by increasing the monitoring and cleaning frequency of key cleaning areas and high-frequency gathering areas of the target object within the target scene based on the robot's historical cleaning data and the target object's historical behavioral information, it is possible to promptly stop fighting or destructive behavior by the target object and to promptly clean dirty areas of the target scene, improving the reliability of the robot's operation and meeting user needs.

[0137] In one embodiment of this application, a robot control device is also proposed. For example... Figure 7 As shown, Figure 7 A structural block diagram of a robot control device 700 according to an embodiment of this application is shown. Specifically, the robot control device 700 may include an acquisition unit 702, a processing unit 704, and a control unit 706.

[0138] Acquisition unit 702 is used to acquire scene information of the target scene;

[0139] Processing unit 704 is used to determine the target area where the target object is located based on scene information;

[0140] The acquisition unit 702 is also configured to acquire at least one target image of the target region, wherein the target image contains a target object;

[0141] The processing unit 704 is also configured to determine the behavioral information of the target object based on at least one target image;

[0142] Control unit 706 is used to control the robot's operation based on behavioral information.

[0143] The robot control device 700 provided in this application embodiment is used to control the operation of a robot, so as to analyze and identify the behavior of a target object in a target scene through the robot, and perform targeted work, thereby realizing the robot's monitoring operation of the target object.

[0144] In practical applications, the aforementioned robots can specifically be intelligent robots with autonomous mobility, such as cleaning robots, photography robots, children's companion robots, and question-and-answer robots, without any specific restrictions.

[0145] Specifically, the robot control device 700 provided in this application includes an acquisition unit 702, a processing unit 704, and a control unit 706. During the robot's operation in a target scene, the acquisition unit 702 acquires scene information of the target scene collected by the robot. The processing unit 704 then identifies and analyzes target objects within the target scene based on the acquired scene information, thereby determining the target area where the target object is located within the target scene. Furthermore, the acquisition unit 702 acquires at least one target image collected by the robot at at least one location within the target area, wherein each target image contains a target object. Further, the processing unit 704 analyzes and identifies the behavior of the target object within the target area based on the acquired at least one target image containing the target object, thereby obtaining the target object's behavior information. Based on this, the control unit 706 controls the robot to perform corresponding tasks based on the target object's behavior information. Thus, based on the scene information of the target scene collected by the robot, the robot analyzes and identifies the behavior of the target object within the target scene, thereby controlling the robot to perform targeted work based on the target object's behavior. In this way, the robot can autonomously monitor the behavior of the target object, enrich the robot's functional modes, and increase the robot's application scenarios. In certain special application scenarios, such as pet fighting scenarios, it frees up the user's hands, thereby avoiding interruption of the user's task processing process and meeting the user's needs.

[0146] Specifically, the target scene can be a room scene or a house scene, and the target object can be an animal object such as a cat or a dog.

[0147] Furthermore, in practical applications, the robot can be equipped with an image acquisition device such as a camera. During the process of acquiring scene information of the target scene by the acquisition unit 702, the acquisition unit 702 specifically acquires scene image information of the target scene captured by the image acquisition device on the robot.

[0148] Based on this, during the process of the processing unit 704 identifying and analyzing target objects in the target scene, the processing unit 704 can specifically perform target detection on the target objects in the target scene based on the scene image information collected by the robot, so as to identify whether there are target objects such as cats and dogs in the target scene.

[0149] Specifically, during the target detection process of the processing unit 704 on the target object in the target scene, the processing unit 704 can detect whether there are animal facial features in the target scene based on AI recognition algorithms, and determine that there is a target object in the target scene if animal facial features are detected.

[0150] Furthermore, in practical applications, the robot can also pre-store the target object image. During the target detection process of the processing unit 704 on the target object in the target scene, the processing unit 704 can specifically retrieve the pre-stored target object image in the robot, match and compare the target object image with the acquired scene image, and determine that there is a target object in the target scene if the target object image and the scene image are successfully matched.

[0151] Based on this, during the process of determining the target area where the target object is located in the target scene by the processing unit 704, specifically, after the processing unit 704 determines that there is a target object in the target scene based on the scene image information, the processing unit 704 can determine the corresponding position information of the target object in the target scene based on the position information of the target object in the scene image, thereby determining the target area where the target object is located.

[0152] Furthermore, in practical applications, the robot can also be equipped with sound acquisition devices such as recording devices and radios. During the process of acquiring scene information of the target scene by the acquisition unit 702, the acquisition unit 702 specifically acquires the scene sound information of the target scene collected by the sound acquisition device on the robot.

[0153] Based on this, during the process of the processing unit 704 identifying and analyzing the target object in the target scene, the processing unit 704 can specifically perform spectrum recognition on the sound information in the target scene based on the scene sound information collected by the robot, so as to detect whether there are target sounds such as cat meows or dog barks that correspond to the target object among multiple sounds in the target scene, and determine that there is a target object in the target scene when the target sound is detected.

[0154] Based on this, during the process of determining the target area where the target object is located in the target scene by the processing unit 704, specifically, after the processing unit 704 determines that there is a target object in the target scene based on the scene sound information, the processing unit 704 can determine the sound source location of the detected target sound, and then determine the position information of the target object in the target scene based on the determined sound source location, thereby determining the target area where the target object is located.

[0155] In practical applications, the robot can also be equipped with a movement mechanism such as wheels, which enables autonomous movement. Furthermore, the robot can pre-store a scene map of the target environment.

[0156] Based on this, in the process of acquiring at least one target image of the target area collected by the robot, specifically, the control unit 706 can control the robot to move to the target area via its moving mechanism based on the scene map. Further, the control unit 706 then controls the robot to move to at least one location within the target area, and at each location, controls the image acquisition device on the robot to capture images of the target object, thereby obtaining at least one target image including the target object.

[0157] Furthermore, during the process of the processing unit 704 analyzing and recognizing the behavior of the target object within the target area, the processing unit 704 can specifically analyze and process at least one target image to determine the position information and feature point information of the target object in each target image. Then, based on the determined position information and feature point information, the number of target objects and the posture changes of each target object are determined to obtain the behavior information of the target object.

[0158] In this embodiment, the processing unit 704 is further configured to: perform spectrum recognition on the sound information to determine the target sound in the sound information; determine the target region based on the target sound; wherein the target sound corresponds to the target object.

[0159] Furthermore, the processing unit 704 is specifically used for: performing target detection on the image information to determine the target object image in the image information; determining the target region based on the target object image; wherein the target object image corresponds to the target object.

[0160] Further, the processing unit 704 is specifically used for: performing image segmentation on at least one target image to determine the target object image in the target image; extracting feature point information of the target object image; determining the feature point position information and pose information of the target object based on the feature point information; and determining behavior information based on the feature point position information and pose information.

[0161] Furthermore, the processing unit 704 is specifically used to: determine the behavior information as target behavior information when the pose information indicates that there are at least two target objects in the target area, and the feature point position information indicates that at least two target objects have overlapping areas in each target image.

[0162] Furthermore, the control unit 706 is specifically used for: controlling the robot to move to the target position when the behavior information is the target behavior information; controlling the robot to perform the target task; and controlling the robot to clean the target area.

[0163] Furthermore, the control unit 706 is also used to: when the target area is a set area, or when the system time is within a set time period and the target area is a set area, control the robot to move to the target area and then control the robot to perform the target task; wherein the number of set areas and set time periods is one or more, and one set area corresponds to one or more set time periods.

[0164] Furthermore, the processing unit 704 is also used to: determine at least one first area in the target scene based on the robot's historical cleaning data and the target object's historical behavior information; the control unit 706 is also used to: control the robot to perform cleaning work or target detection work on at least one first area according to the target frequency; wherein, the first area is the robot's key cleaning area or the high-frequency gathering area of ​​the target object.

[0165] In one embodiment of this application, another robot control device is also proposed. For example... Figure 8 As shown, Figure 8 A structural block diagram of a robot control device 800 provided in an embodiment of this application is shown.

[0166] The robot control device 800 includes:

[0167] Memory 802, on which programs or instructions are stored;

[0168] The processor 804 executes the above-described program or instructions to implement the steps of the robot control method as described in any of the above embodiments.

[0169] The robot control device 800 provided in this embodiment includes a memory 802 and a processor 804. When the program or instructions in the memory 802 are executed by the processor 804, they implement the steps of the robot control method as described in any of the above embodiments. Therefore, the robot control device 800 has all the beneficial effects of the robot control method in any of the above embodiments, which will not be repeated here.

[0170] Specifically, the memory 802 and the processor 804 can be connected via a bus or other means. The processor 804 may include one or more processing units, and the processor 804 may be a chip such as a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA).

[0171] In one embodiment of this application, a robot is also proposed. For example... Figure 9 As shown, Figure 9 A structural block diagram of a robot 900 provided in an embodiment of this application is shown. The robot 900 includes the robot control device 800 in the above embodiments. Therefore, the robot 900 possesses all the technical effects of the robot control device 800 in the above embodiments, which will not be repeated here.

[0172] In practical applications, the aforementioned robot 900 can specifically refer to intelligent robots with autonomous mobility, such as cleaning robots, photography robots, child companion robots, and question-and-answer robots, without any specific limitations.

[0173] An embodiment of the fifth aspect of this application provides a readable storage medium. A program or instructions are stored thereon, which, when executed by a processor, implement the steps of the robot control method as described in any of the foregoing embodiments.

[0174] The readable storage medium provided in this application provides a program or instruction that, when executed by a processor, can implement the steps of the robot control method as described in any of the above embodiments. Therefore, this readable storage medium possesses all the beneficial effects of the robot control method in any of the above embodiments, which will not be elaborated further here.

[0175] Specifically, the aforementioned readable storage medium can include any medium capable of storing or transmitting information. Examples of readable storage media include electronic circuits, semiconductor memory devices, read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), flash memory, erasable ROM (EROM), magnetic tape, floppy disk, optical disk, hard disk, fiber optic media, radio frequency (RF) links, optical data storage devices, etc. Code segments can be downloaded via computer networks such as the Internet and intranets.

[0176] In the description of this specification, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance, unless otherwise expressly specified and limited. The terms "connection," "installation," and "fixing," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0177] In the description of this specification, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0178] Furthermore, the technical solutions of the various embodiments of this application can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by this application.

[0179] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A robot control method, characterized in that, The robot control method includes: Obtain scene information for the target scene; The target area where the target object is located is determined based on the scene information; Acquire at least one target image of the target region, wherein the target image contains the target object; Determine the behavioral information of the target object based on the at least one target image; The robot is controlled to work based on the behavioral information; Determining the behavioral information of the target object based on the at least one target image includes: Perform image segmentation on the at least one target image to determine the target object image in the target image; Extract feature point information from the target object image; The pose information and feature point position information of the target object are determined based on the feature point information; Determining the behavior information based on the pose information and the feature point location information includes: determining the behavior information as target behavior information when the pose information indicates that the number of target objects is at least two, and the feature point location information indicates that at least two target objects have overlapping areas in at least one target image.

2. The robot control method according to claim 1, characterized in that, The scene information includes sound information, and determining the target area where the target object is located based on the scene information includes: Spectral recognition is performed on the sound information to determine the target sound in the sound information, and the target sound corresponds to the target object; The target area is determined based on the target sound.

3. The robot control method according to claim 1, characterized in that, The scene information includes image information, and determining the target area where the target object is located based on the scene information includes: Target detection is performed on the image information to determine the target object image in the image information, and the target object image corresponds to the target object; The target region is determined based on the target object image.

4. The robot control method according to claim 1, characterized in that, The step of controlling the robot to work based on the behavioral information includes: When the behavior information is the target behavior information, control the robot to move to the target location where the target object is located; Control the robot to perform the target task, thereby driving the target object out of the target area; Control the robot to clean the target area.

5. The robot control method according to any one of claims 1 to 4, characterized in that, After determining the target area where the target object is located based on the scene information, the robot control method further includes: If the target area is a set area, or if the target area is a set area and the system time is within a set time period, the robot is controlled to move to the target area and perform the target task to drive away the target object; The number of the set areas and the set time periods is one or more, and one set area corresponds to one or more set time periods.

6. The robot control method according to any one of claims 1 to 4, characterized in that, After determining the behavioral information of the target object based on the at least one target image, the robot control method further includes: Based on the historical behavior information of the target object and the historical cleaning data of the robot, at least one first area in the target scene is determined, wherein the first area is a high-frequency gathering area of ​​the target object or a key cleaning area of ​​the robot; The robot is controlled to perform target detection or cleaning work on at least one first area at a target frequency.

7. A robot control device, characterized in that, The robot control device includes: The acquisition unit is used to acquire scene information of the target scene; The processing unit is used to determine the target area where the target object is located based on the scene information; The acquisition unit is further configured to acquire at least one target image of the target region, the target image containing the target object; The processing unit is further configured to determine the behavioral information of the target object based on the at least one target image; A control unit is used to control the robot to work based on the behavioral information; The processing unit is specifically configured to: perform image segmentation on the at least one target image to determine a target object image in the target image; extract feature point information of the target object image; determine feature point position information and pose information of the target object based on the feature point information; and determine the behavior information based on the feature point position information and the pose information. The processing unit is further configured to determine the behavior information as target behavior information when the pose information indicates that there are at least two target objects in the target area and the feature point position information indicates that at least two target objects have overlapping areas in each target image.

8. A robot control device, characterized in that, include: Memory, which stores programs or instructions; A processor that, when executing the program or instructions, implements the steps of the robot control method as described in any one of claims 1 to 6.

9. A robot, characterized in that, include: The robot control device as described in claim 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the robot control method as described in any one of claims 1 to 6.

Images