Motion control method and device based on pet position information, equipment and medium

Abstract

The embodiment of the invention discloses a motion control method and device based on pet position information, equipment and a medium. In the embodiment of the invention, in each working process of the automatic cleaning equipment, an environment image is acquired through an image acquisition module, whether a pet exists in the environment image or not is identified, if the pet exists, the pet position information is updated, and before each working, the detection sequence of the space area is determined according to the pet position information; therefore, on the basis that the pet is actively detected and the staying position of the pet is quickly confirmed according to the individual characteristics of the pet, the most appropriate motion strategy for executing the current work is integrally grasped in the dimension of the whole cleaning target environment, and the adaptive capacity of the automatic cleaning equipment in the pet keeping environment is effectively improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of motion control technology, and in particular to a motion control method, apparatus, device, and storage medium based on pet location information. Background Art

[0002] With the continuous development of electronic technology, various forms of smart homes have begun to appear in people's lives, providing users with convenience in many aspects and improving their quality of life. For example, automatic cleaning devices can free people up from a large part of their time by freeing them from housework, allowing them to enjoy other rich aspects of life.

[0003] Traditional automated cleaning devices are limited to detecting environmental maps, automatically planning routes based on these detections, and adaptively avoiding obstacles (i.e., avoiding collisions with furniture, walls, pets, etc.). To accommodate the increasing number of pet owners, existing automated cleaning devices are taking a pet-friendly approach by further detecting obstacles to determine if they are pets, thereby implementing more targeted obstacle avoidance mechanisms. For example, they may perform more thorough cleaning near furniture and walls, while circumventing pets at a greater distance to avoid disturbing them.

[0004] When the inventor used the existing automatic cleaning equipment, he found that the existing automatic cleaning equipment can only set an overall motion path for cleaning and real-time detection of pets based on cleaning. It cannot actively detect and discover pets based on their individual characteristics, and has weak adaptability to the pet-raising environment. Summary of the Invention

[0005] The present invention provides a motion control method, device, equipment and medium based on pet location information to solve the technical problem that existing automatic cleaning equipment cannot actively detect and discover pets based on their individual characteristics and has weak adaptability to pet-raising environments.

[0006] In a first aspect, an embodiment of the present invention provides a motion control method based on pet location information, which is used in an automatic cleaning device equipped with an image acquisition module. The motion control method includes:

[0007] Receive motion trigger instructions;

[0008] In response to the motion trigger instruction, determining an area detection sequence according to pre-stored pet location information, where the areas in the area detection sequence are spatial areas in a pre-stored environment map;

[0009] Control the automatic cleaning equipment to move in each spatial area according to the regional detection sequence, and collect environmental images in real time through the image acquisition module during the movement;

[0010] The environment image is detected, and when a pet is detected, the pet location information is updated.

[0011] In response to the motion trigger instruction, the area detection order is determined according to the pre-stored pet location information, including:

[0012] In response to the motion trigger instruction, the spatial areas are sorted from high to low according to the number of times the pet is detected in each spatial area in the pre-stored pet location information, and the sorting result is used as the area detection order.

[0013] Among them, the motion trigger instruction includes a cleaning instruction;

[0014] Accordingly, the motion control method further includes:

[0015] When a pet is detected, a reset motion path for the current spatial area is generated, the reset motion path avoids the positions that have been passed and the position of the pet, and moves along the reset motion path.

[0016] The motion control method further includes:

[0017] The probability of pet appearance is detected in the environmental image, and the motion path is reset according to the corresponding path reset strategy based on the probability interval corresponding to the detected current appearance probability, so as to improve the detection result of the pet appearance probability or restore the motion path.

[0018] Wherein, when a pet is detected, a reset motion path of the current spatial area is generated, the reset motion path avoids the positions that have been passed and the position of the pet, and after moving along the reset motion path, the method further includes:

[0019] When it is confirmed that the pet has left the location, the location where the pet is located in the reset movement path is cleaned.

[0020] Among them, the motion triggering instruction includes a seek instruction;

[0021] Accordingly, the motion control method further includes:

[0022] When a pet is detected, the corresponding environment image is sent to a preset terminal device.

[0023] The motion control method further includes:

[0024] When a pet is detected, the detected pet is individually identified, and the movement is ended when it is confirmed that the pet specified in the search instruction has been detected or all spatial areas have been passed.

[0025] The motion control method further includes:

[0026] When a pet is detected, the detected pet is individually identified, and the movement is terminated when it is confirmed that all pets specified by the search command are detected;

[0027] The detected pets are individually identified. If it is confirmed that all pets specified by the search command have not been detected and all spatial areas have been passed, the pets move in each spatial area in the order of regional detection.

[0028] The motion control method further includes:

[0029] Perform location status statistics on pet location information to confirm the activity status of each pet;

[0030] When it is confirmed that the same pet has stayed in the same location for a preset time, the automatic cleaning device is controlled to perform pet confirmation detection at the same location;

[0031] When the result of the pet confirmation detection is that the same pet is still staying in the same position, the corresponding environment image is sent to a preset terminal device and / or the automatic cleaning device is controlled to move closer to the pet.

[0032] In a second aspect, an embodiment of the present invention further provides a motion control device based on pet location information, which is used in an automatic cleaning device, wherein the automatic cleaning device is equipped with an image acquisition module, and the motion control device includes:

[0033] An instruction receiving unit, configured to receive a motion trigger instruction;

[0034] a sequence confirmation unit for confirming, in response to a motion trigger instruction, a region detection sequence based on pre-stored pet location information, wherein the regions in the region detection sequence are spatial regions in a pre-stored environment map;

[0035] A motion control unit is used to control the automatic cleaning device to move in each spatial area according to the area detection sequence, and to collect environmental images through the image acquisition module during the movement;

[0036] The detection and recording unit is used to detect the environmental image and update the pet's location information when a pet is detected.

[0037] Among them, the sequence confirmation unit is specifically used to respond to the motion trigger instruction, sort the spatial areas from high to low according to the number of times the pet is detected in each spatial area in the pre-stored pet location information, and use the sorting result as the area detection order.

[0038] Among them, the motion trigger instruction includes a cleaning instruction;

[0039] Accordingly, the motion control device further includes:

[0040] The path reset unit is used to generate a reset motion path for the current spatial area when a pet is detected, the reset motion path avoids the positions that have been passed and the position of the pet, and moves along the reset motion path.

[0041] The motion control device further includes:

[0042] The probability response unit is used to detect the probability of pet appearance in the environmental image, and reset the motion path according to the corresponding path reset strategy based on the probability interval corresponding to the detected current occurrence probability, so as to improve the detection result of the pet appearance probability or restore the motion path.

[0043] The motion control device further includes:

[0044] The supplementary cleaning unit is used to generate a reset motion path for the current spatial area when a pet is detected. The reset motion path avoids the positions that have been passed and the position where the pet is located. After moving along the reset motion path, the position where the pet is located in the reset motion path is cleaned when it is confirmed that the pet has left the position.

[0045] Among them, the motion triggering instruction includes a seek instruction;

[0046] Accordingly, the motion control device further includes:

[0047] The first image sending unit is used to send the corresponding environment image to a preset terminal device when a pet is detected.

[0048] The motion control device further includes:

[0049] The first movement ending unit is used to individually identify the detected pets when a pet is detected, and to end the movement when it is confirmed that all pets specified by the search instruction have been detected or all spatial areas have been passed.

[0050] The motion control device further includes:

[0051] The second movement ending unit is used to individually identify the detected pets when a pet is detected, and end the movement when it is confirmed that all pets specified by the search instruction are detected;

[0052] The supplementary detection unit is used to individually identify the detected pets and move in each spatial area according to the regional detection order when confirming that all pets specified by the search instruction have not been detected and have passed through all spatial areas.

[0053] The motion control device further includes:

[0054] A status statistics unit is used to perform location status statistics on pet location information to confirm the activity status of each pet;

[0055] A status confirmation unit is used to control the automatic cleaning device to perform pet confirmation detection at the same location when confirming that the same pet has stayed at the same location for a preset time period;

[0056] The abnormality handling unit is used to send the corresponding environment image to a preset terminal device and / or control the automatic cleaning device to approach the pet when the result of the pet confirmation detection is that the same pet is still staying in the same position.

[0057] In a third aspect, an embodiment of the present invention provides an electronic device, comprising:

[0058] one or more processors;

[0059] a memory for storing one or more computer programs;

[0060] When one or more computer programs are executed by one or more processors, the electronic device implements the motion control method based on pet position information as in the first aspect.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the motion control method based on pet position information as in the first aspect.

[0062] In the aforementioned motion control method, apparatus, device, and medium based on pet location information, the motion control method is used for an automatic cleaning device equipped with an image acquisition module. The motion control method comprises: receiving a motion trigger instruction; in response to the motion trigger instruction, determining a region detection sequence based on pre-stored pet location information, wherein the regions in the region detection sequence are spatial regions in a pre-stored environmental map; controlling the automatic cleaning device to move within each spatial region according to the region detection sequence, and capturing environmental images during the movement through the image acquisition module; detecting the environmental images, and updating the pet location information if a pet is detected. During each operation, the automatic cleaning device captures environmental images through the image acquisition module and identifies whether a pet is present in the environmental image. If a pet is present, the pet location information is updated. Before each operation, the detection sequence for the spatial regions is determined based on the pet location information. This allows the automatic cleaning device to proactively detect pets based on their individual characteristics and quickly determine their location, while comprehensively grasping and executing the most appropriate motion strategy for the current operation within the entire cleaning target environment, effectively improving the adaptability of the automatic cleaning device in pet-raising environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0064] Figure 1 A method flow chart of a motion control method based on pet location information provided in an embodiment of the present application;

[0065] Figure 2 is a schematic diagram of the spatial area distribution in an exemplary environmental map;

[0066] Figure 3 for Figure 2 Schematic diagram of the first motion path in the middle space area C;

[0067] Figure 4 A schematic diagram of the structure of a motion control device based on pet position information provided in an embodiment of the present application;

[0068] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] To make the objectives, technical solutions, and advantages of this application more apparent, embodiments of the present application will be further described in detail below with reference to the accompanying drawings. It will be understood that the specific embodiments described herein are intended to illustrate the present invention, not to limit it. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all of the components.

[0070] It should be noted that due to space limitations, this application specification does not enumerate all optional implementation methods. After reading this application specification, those skilled in the art should be able to understand that as long as the technical features do not contradict each other, any combination of technical features can constitute an optional implementation method.

[0071] Each embodiment is described in detail below.

[0072] Figure 1This is a method flow chart of a motion control method based on pet location information provided in an embodiment of the present application. The motion control method in the embodiment of the present application is used for an automatic cleaning device, which is equipped with an image acquisition module. In addition, the automatic cleaning device is also equipped with a positioning module such as a laser radar, a cleaning module such as a water tank and a rag, and a motion module such as a walking wheel. The components involved in electronic control and the image acquisition module in these modules can be controlled by the microprocessor of the automatic cleaning device. Accordingly, the data collected by the image acquisition module and the positioning module can be sent to the microprocessor for processing. The microprocessor can generate control instructions based on the received data and send the control instructions to the cleaning module and the motion module to realize the work control under the corresponding specific environmental conditions. In addition, there are charging modules, communication modules, etc., and the positioning module, cleaning module and motion module can all be implemented with reference to the relevant automatic cleaning equipment technical field. The specific installation method and basic working principle will not be explained in detail here, and the corresponding work content will not be repeated. For example, the process of returning to the charging station to charge through the charging module after cleaning is completed is not repeated. Automatic cleaning equipment includes specific examples such as sweepers and mops.

[0073] like Figure 1 As shown, the motion control method includes but is not limited to steps S110 to S140.

[0074] Step S110: receiving a motion trigger instruction.

[0075] Motion-triggered commands refer to commands that instruct the automatic cleaning device to perform a task that requires motion, such as cleaning commands and search commands. The core work content of the cleaning command is to clean the environment (usually a house); the core work content of the search command is to find the specific location of the pet in the environment.

[0076] In a specific implementation, the motion trigger command can be received externally, for example, by a user operating a control application installed on a terminal device to instruct the automatic cleaning device to clean the house, or to instruct the automatic cleaning device to locate a pet within the house. The motion trigger command can also be generated by the automatic cleaning device based on the operating status settings, such as when a scheduled cleaning function is used, the motion trigger command is automatically generated at the set time, and is generated and received internally by the automatic cleaning device.

[0077] For different motion trigger instructions, the specific work content of the automatic cleaning device is different, but as a whole, the processing procedures in steps S120-S140 need to be executed. It should be understood that the embodiments of the present application are all aimed at the work content completed by the automatic cleaning device during the motion process, and highlight how to control the motion process. For the specific work content during the motion process, such as cleaning, you can refer to the cleaning process in the relevant technology without being disturbed by the motion process in the embodiments of the present application. You can just clean while moving. The embodiments do not provide detailed descriptions of the specific work content that can be directly implemented by referring to the relevant technology.

[0078] Step S120: In response to the motion trigger instruction, the region detection sequence is confirmed according to the pre-stored pet position information, and the regions in the region detection sequence are spatial regions in the pre-stored environment map.

[0079] Different pets have different individual characteristics. For example, some pet cats are quiet, some are playful, and some are energetic. As a result, the locations where pets like to stay, the ways of activities, and their preferences are also different. Based on this, the embodiment of the present application not only detects external obstacles through laser radar, but also further uses an image acquisition module to detect and record the presence of pets in the environment, thereby obtaining the preferences of pets in various spatial areas, and based on the preferences, confirming the order of regional detection, which is equivalent to starting the detection from the location where the pet is most likely to appear, so as to prioritize the location of the pet, thereby giving priority to the area where the pet is located during the entire movement process, and then avoiding interference with the pet as much as possible in the future, and flexibly responding to the rich environmental changes caused by the huge individual differences of pets. The overall regional detection sequence design can be to first interrupt the cleaning of the spatial area where the pet is located, or to not clean a certain range centered on the pet's location when planning the movement path (that is, first clean the periphery of a certain range centered on the pet's location). In addition, in the specific implementation process, in the absence of historical data, the pre-stored pet location information can also be the preference and habit information of each pet entered by the user, which can be updated later according to the detection results. The corresponding pre-stored pet location information is generated based on the actual detection results of the pet. When the user enters the preference and habit information of each pet, the user can enter the pet name, images from various angles, etc., to achieve more accurate detection later.

[0080] In the specific implementation process, the house is usually divided into multiple spatial areas by walls and doors, such as the living room area, balcony area, master bedroom area, kitchen area, etc. In the specific processing process, referring to the size of the general spatial area, considering that the shooting range of the image acquisition module on the automatic cleaning equipment can usually easily cover the entire spatial area, the spatial area can be used as an example as the basic unit for regional detection and sorting, without having to make more detailed divisions based on the map grid of the environment map. For example Figure 2 The environmental map shown corresponds to six spatial regions from AF. Of course, in specific implementation, the spatial region can be further divided into multiple sub-regions, and each sub-region corresponds to separate statistics and sorting. In the specific sorting process, in response to the motion trigger instruction, the spatial regions are sorted from high to low according to the number of times the pet is detected in each spatial region in the pre-stored pet location information, and the sorting results are used as the region detection order. For example, the pet is Figure 2 The number of times each spatial area is detected is A-12, B-18, C-30, D-21, E-25, and F-27, so the corresponding area detection order should be C→F→E→D→B→A.

[0081] The division of spatial areas can be that the automatic cleaning equipment first detects obstacles in the house and obtains a rasterized environmental map. The grids in the environmental map can be grouped by clustering. This grouping process can group connected grids that are close together. If there is occlusion in the middle, it is equivalent to being far away and they will not be grouped together. This is equivalent to the clustering process being able to identify multiple grids that are continuous inside and isolated by blank areas outside as the same spatial area. Of course, detailed obstacles in the same spatial area can also be identified and processed in the spatial area, for example Figure 2 In the house shown, the spatial area D is assumed to be the living room. There is a blank area in the center of the spatial area D. In fact, a coffee table may be placed in the center of the spatial area D.

[0082] Step S130: Control the automatic cleaning device to move in each spatial area according to the area detection sequence, and collect environmental images through the image collection module during the movement.

[0083] After confirming the area detection order, a motion path can be generated for each spatial area respectively, and the movement in each spatial area is subsequently completed according to the corresponding motion path. The motion path initially generated each time the motion trigger instruction is responded to is defined as the first motion path. Each spatial area and the layout within the spatial area are different. The first motion path corresponding to each spatial area may be different or not completely the same, but the first motion path is generated in the same way. For example, the first motion path can be an inward spiral path (i.e., sweeping from the periphery to the center in circles) or an outward spiral path (i.e., sweeping from the center to the periphery in circles). Of course, it can also be a bow-shaped path.

[0084] exist Figure 3 In the exemplary movement mode shown, the spatial area C should be the first spatial area to be detected in the order of area detection, wherein the solid line shows an inward spiral path, that is, the movement of the automatic cleaning device is from the outer ring near the wall in the spatial area to the center of the spatial area in a spiral approach; wherein the dotted line shows an outward spiral path, which requires the automatic cleaning device to first reach the center of the spatial area, and then move in the opposite direction from the spiral path shown by the solid line.

[0085] It should be noted that the environmental image acquisition module captures environmental images during movement in the embodiments of this application, not just during movement based on the first motion path. Rather, the environmental image acquisition module can be continuously captured during movement, thereby capturing as much information as possible about the pet's location and enabling the most comprehensive analysis of the pet's movement status. Accordingly, content detection can be performed on all or a certain percentage of the captured environmental images, and content detection can be performed in step S140.

[0086] Step S140: Detect the environment image, and if a pet is detected, update the pet's location information.

[0087] A pre-trained pet recognition model can be used to detect the content of environmental images. When the pet recognition model identifies a pet in the environmental image, it returns a probability score and the pet's location in the image. If the pet's probability score is below a preset threshold (indicating that the pet may be far away, partially obscured, or misidentified, resulting in significant uncertainty), it indicates a high probability of no interference with the pet and the robot can continue to move along the first motion path until the output probability score reaches the preset threshold. When the probability score reaches the preset threshold, the pet is considered detected. The pet's location information is then updated based on the pet's current spatial region. Specifically, this can include recording only the spatial region and the time of detection, or the specific location within the spatial region and the time of detection. It can also include accurate recognition of different types of pets, or even of different individuals of the same species based on individual images. In specific implementations, to ensure accurate recording of the pet's spatial region, it is necessary to accurately obtain the pet's spatial region detection results through image recognition or the position of the automatic cleaning device. For example, image recognition can accurately identify the pet in the living room or balcony. Another example is to confirm that the pet is in the spatial region adjacent to the automatic cleaning device based on the position of the automatic cleaning device, the orientation of the image acquisition module, or even the detection results of a LiDAR. The pet recognition model can use object detection methods such as the YOLO series and NanoDet. The pet recognition model is specially trained to accurately identify a variety of pets in different environments and lighting conditions, such as cats, dogs, and different cat types.

[0088] Continuously updating pet location information can address changes in activity habits caused by seasonal and individual pets. For example, pets prefer cooler areas in the summer and warmer areas in the winter. There's a transition period from summer to winter and vice versa, and pets' location preferences also change between seasons. This allows for a clear record of the pet's current and most recent location preferences. Accordingly, during the update process, pet location information can be limited to the most recent six months or even shorter periods to reduce potential interference from historical records. Of course, pet location information can also be recorded continuously. During the processing process, the region detection sequence is determined based solely on pet location information from the same time period each year. For example, activity on August 14th would be determined based on the pet's location information from August of each year. In addition to the more macroscopic changes in activity habits caused by monthly and seasonal changes, it is also possible to identify changes in daily habits at a more microscopic level, such as morning, noon, evening, and night, with corresponding location preferences generated and recorded accordingly.

[0089] In general, during each working process of the automatic cleaning equipment, the image acquisition module collects environmental images and identifies whether there are pets in the environmental images. If there are pets, the pet's location information is updated. Before each work, the detection order of the spatial area is determined according to the pet's location information. In this way, the pet can be actively detected according to the individual characteristics of the pet and the pet's location can be quickly confirmed. On the basis of this, the most appropriate motion strategy for the current work can be grasped and executed in the dimension of the entire cleaning target environment, effectively improving the adaptability of the automatic cleaning equipment in the pet-raising environment.

[0090] If the motion trigger instruction is the cleaning instruction described above; the cleaning instruction in the embodiment of the present application may not only instruct the automatic cleaning device to clean the house, but also detect the pet's position during the cleaning process and adjust the cleaning path to adapt to the pet's position, which is equivalent to the cleaning instruction being a comprehensive instruction for cleaning and pet detection. Therefore, the motion control method in the embodiment of the present application can also generate a reset motion path for the current spatial area when a pet is detected. The reset motion path can avoid the positions that have been passed and the position of the pet, and move along the reset motion path. The reset motion path is used to be used in the current spatial area after the pet is detected. The principle of generating the reset motion path can be to avoid the position that the automatic cleaning device has passed, thereby avoiding repeated cleaning; and avoiding the position of the pet, thereby avoiding disturbing the pet. In this way, the cleaning efficiency is improved while ensuring the comfort of the pet in the pet-raising state.

[0091] In one specific implementation, the pet's location can be an area within a preset distance range from the pet, which is equivalent to controlling the automatic cleaning device to maintain a relatively large distance from the pet. The preset distance range can be pre-set or obtained through statistics or learning based on the pet's response during the detection process. That is, the pet recognition model can also recognize the pet's behavior. When the pet's movement in the automatic cleaning device is detected, causing the pet to change from static to dynamic, the distance between the automatic cleaning device and the pet at that time is recorded as a reference for subsequent distance maintenance from the pet. The preset range for different species or even different individuals of the same species can also be finely set to account for individual differences or finely updated based on historical records, so that targeted path adjustments can be made during movement based on the specific individual differences of the pets detected. When generating the reset motion path, priority can be given to avoiding the pet's location. For example, if the pet is near a door in a certain spatial area, if the automatic cleaning device moves into the interior of the spatial area to clean, it will enter the pet's location, and the interior of the spatial area will be temporarily avoided. That is, the reset motion path can temporarily not cover the interior of the spatial area. It should be understood that after the reset motion path is generated, the first motion path corresponding to the spatial area is equivalent to being invalid in the current cleaning process. If the pre-stored pet location information has not changed, the first motion path is valid by default in the next cleaning process until a detection result that triggers the reset motion path appears. After the automatic cleaning device moves to avoid the location of the pet using the reset motion path, it can also clean the location of the pet in the reset motion path after confirming that the pet has left the location. Specifically, it can be performed after a period of time to the location where the pet was recently detected. If the pet is not detected, that is, the pet has left, the previously uncleaned area can be supplemented with cleaning to ensure that each cleaning instruction corresponds to the cleaning of the entire house.

[0092] In another optional implementation, the environmental image can also be tested for the probability of a pet appearing. Based on the probability interval corresponding to the detected current probability of pet appearance, the motion path can be reset according to the corresponding path reset strategy to improve the detection result of the pet appearance probability or restore the motion path. For example, if the detection result of the environmental image confirms that the probability of a pet appearing is low, it is equivalent to the suspected presence of a pet in the environmental image. At this time, the general location of the suspected pet in the spatial area can be confirmed from the environmental image. Then, the general location can be approached to obtain a clearer or more comprehensive environmental image and perform pet detection with a more specific goal. During this process, if the judgment of the suspected presence of a pet is correct, the detection result of the pet appearance probability will increase until the presence of a pet is confirmed. At this time, the pet appearance treatment strategy such as avoidance and delayed cleaning can be implemented according to the above-mentioned treatment method. If the detection result of the pet appearance probability does not improve during the approach process, or even decreases, it can be confirmed that the previously suspected presence of a pet is not actually present. The initial motion path can be restored and the movement can be carried out according to the original plan. In this way, the pet search can be carried out in the clearest possible direction and the search direction may be incorrect. Stop the loss in time, thereby improving the cleaning or search efficiency.

[0093] If the motion trigger command is the find command described above, the motion control method in the embodiments of the present application can also send the corresponding environmental image to a preset terminal device when a pet is detected. For the find command, this can be considered to have only one command objective: to find the pet's location. The primary data processing during the movement of the automatic cleaning device lies in motion control and environmental image acquisition. The specific method for identifying a pet from environmental images has been described above and will not be repeated here. After a pet is detected, the corresponding result can be fed back to the user. In specific implementations, the core of the find command is to determine the pet's location. A relatively small preset threshold can be used to compare the pet's probability score. This means that even if the pet is far away, the environmental image can be fed back to the user, or video recording and transmission can be initiated. Of course, environmental images can also be sent when a pet is detected during the movement in response to a cleaning command. For family members, the automatic cleaning device can monitor and track the pet's location while performing its cleaning task, allowing family members to quickly understand their pet's activities when they are away. While the automatic cleaning device flexibly adapts to pet-rearing environments, family members also have a new and convenient way to check their pet's status.

[0094] Considering that some households may have multiple pets, to ensure comprehensive detection, this motion control method can also perform individual identification on detected pets. The motion ends when all pets specified in the search command have been detected or all spatial areas have been traversed. In other words, the motion ends when all pets have been found or all spatial areas have been exhausted. Of course, if the user's search command in the control application is to find one or more specified pets, the motion can end when the specified pets have been found.

[0095] In another alternative implementation, considering that pets can move, their movements may just evade the automatic cleaning device's detection motion and enter an already detected spatial area. In this case, further comprehensive processing can be performed. Specifically, if a pet is detected, the detected pet is individually identified. If all pets specified in the search instruction are confirmed to be detected, the motion is terminated. If the detected pet is individually identified and it is confirmed that all pets specified in the search instruction have not been detected and all spatial areas have been passed through, the motion is then moved through each spatial area according to the regional detection order. If it is confirmed that all pets specified in the search instruction have not been detected and all spatial areas have been passed through, a supplementary search can be performed based on the first motion path. During the supplementary search, the first motion path is fine-tuned to adapt to the pets already found to avoid disturbing the pets already found. Another processing method is to perform a supplementary rapid search. This processing method differs from the previous search process in that if the first motion path initially generated according to the motion trigger instruction does not detect or does not detect all pets, a second motion path with a lower distribution density (shorter total path length) is used for a rapid detection. For image detection based on the image acquisition module, as long as the pet remains on the ground, the two detections can basically guarantee detection. This is equivalent to if the search instruction specifies multiple pets, the movement will only end directly after all the specified pets are found. Otherwise, the movement and detection need to continue until all the specified pets are detected or the predetermined number of detections have been completed and the result of no or partial detection of the specified pet is fed back, thereby fully meeting the user's various pet search needs. Of course, the second movement path can be a movement path with a higher distribution density than the first movement path, which is equivalent to performing a more detailed detection after completing a detection according to the first movement path. If no pet is detected or not detected, a more detailed detection is performed until all the specified pets are detected or the predetermined number of detections have been completed and the result of no or partial detection of the specified pet is fed back. It should be understood that the end of the movement corresponding to the search instruction usually refers to returning to the charging station, rather than staying in place.

[0096] In the embodiment of the present application, the pet location information records the pet's activity data, and the pet's status can be further judged based on this activity data. For example, the pet location information is statistically analyzed to confirm the activity status of each pet. When it is confirmed that the same pet has stayed in the same location for a preset time, the automatic cleaning device is controlled to perform a pet confirmation detection at the same location. When the result of the pet confirmation detection shows that the same pet is still staying in the same location, the corresponding environment image is sent to a preset terminal device and / or the automatic cleaning device is controlled to approach the pet. This is equivalent to the automatic cleaning device actively detecting the pet, or even actively approaching or touching the pet, if it is confirmed that the pet has remained motionless for a long time based on the statistics of the pet's location information, to confirm whether the pet is in a normal state. It should be understood that the automatic cleaning device in the embodiment of the present application detects pets at intervals. In the event of an interruption in pet monitoring, the determination of the pet's status is relatively rough. Further comprehensive detection of the pet's status can be performed through image comparison, posture detection, etc. For example, although the pet is staying in one location, the pet's area image in the environmental image taken at the same location and angle by the automatic cleaning device is different, or the pet's posture is clearly standing. In this case, the pet can be determined to be normal, and the automatic cleaning device can handle it according to the processing strategy described above for the presence of a pet. Specifically, location status statistics can be performed at a set detection time, actively initiated by the user, or automatically each time a pet is detected.

[0097] It should be understood that the processing procedures for various situations described in the embodiments of the present application are not descriptions of the specific processing procedures for a single detection, but rather an overall description of possible implementation methods during the operation of the entire automatic cleaning device. As long as the technical solutions described in the embodiments do not conflict with each other, they can be executed in an automatic cleaning device. For example, an automatic cleaning device can perform individual identification of pets, as well as position status statistics and corresponding further confirmation on the basis of being able to execute steps S110-S140, as long as the automatic cleaning device has image acquisition capabilities, communication capabilities or data processing capabilities based on environmental images. In addition, during the detection process, the operating status of the image acquisition module can be further controlled, such as the frequency of image acquisition, rotation detection at a certain frequency, etc. Specifically, for example, 0, 1 or 2 of the frequency of rotation when moving along the first motion path and the frequency of image acquisition are higher than the frequency of rotation when moving along the second motion path and the frequency of image acquisition.

[0098] The above-mentioned motion control method based on pet location information is used in an automatic cleaning device equipped with an image acquisition module. The motion control method includes: receiving a motion trigger instruction; in response to the motion trigger instruction, determining a region detection sequence based on pre-stored pet location information, where the regions in the region detection sequence are spatial regions in a pre-stored environmental map; controlling the automatic cleaning device to move within each spatial region according to the region detection sequence, and capturing environmental images during the movement through the image acquisition module; detecting the environmental images, and updating the pet location information if a pet is detected. During each operation, the automatic cleaning device captures environmental images through the image acquisition module and identifies whether a pet is present in the environmental image. If a pet is present, the pet location information is updated. Before each operation, the detection sequence for the spatial regions is determined based on the pet location information. This allows the automatic cleaning device to proactively detect pets based on their individual characteristics and quickly confirm their location. The method then comprehensively grasps and executes the most appropriate motion strategy for the current operation within the entire cleaning target environment, effectively improving the adaptability of the automatic cleaning device in pet-raising environments.

[0099] Figure 4 This is a structural diagram of a motion control device based on pet location information provided in an embodiment of the present application. The motion control device is used in an automatic cleaning device, which is equipped with an image acquisition module, such as Figure 4 As shown, the motion control device includes an instruction receiving unit 210 , a sequence confirmation unit 220 , a motion control unit 230 and a detection recording unit 240 .

[0100] Among them, the instruction receiving unit 210 is used to receive the motion trigger instruction; the sequence confirmation unit 220 is used to respond to the motion trigger instruction and confirm the area detection sequence according to the pre-stored pet location information, and the areas in the area detection sequence are the spatial areas in the pre-stored environmental map; the motion control unit 230 is used to control the automatic cleaning device to move in each spatial area according to the area detection sequence, and collect environmental images through the image acquisition module during the movement; the detection recording unit 240 is used to detect the environmental image and update the pet location information when a pet is detected.

[0101] Based on the above embodiment, the sequence confirmation unit 220 is specifically used to respond to the motion trigger instruction, sort the spatial areas from high to low according to the number of times the pet is detected in each spatial area in the pre-stored pet location information, and use the sorting results as the area detection order.

[0102] Based on the above embodiment, the motion trigger instruction includes a cleaning instruction;

[0103] Accordingly, the motion control device further includes:

[0104] The path reset unit is used to generate a reset motion path for the current spatial area when a pet is detected, the reset motion path avoids the positions that have been passed and the position of the pet, and moves along the reset motion path.

[0105] Based on the above embodiment, the motion control device further includes:

[0106] The probability response unit is used to detect the probability of pet appearance in the environmental image, and reset the motion path according to the corresponding path reset strategy based on the probability interval corresponding to the detected current occurrence probability, so as to improve the detection result of the pet appearance probability or restore the motion path.

[0107] Based on the above embodiment, the motion control device further includes:

[0108] The supplementary cleaning unit is used to generate a reset motion path for the current spatial area when a pet is detected. The reset motion path avoids the positions that have been passed and the position where the pet is located. After moving along the reset motion path, the position where the pet is located in the reset motion path is cleaned when it is confirmed that the pet has left the position.

[0109] Based on the above embodiment, the motion trigger instruction includes a search instruction;

[0110] Accordingly, the motion control device further includes:

[0111] The first image sending unit is used to send the corresponding environment image to a preset terminal device when a pet is detected.

[0112] Based on the above embodiment, the motion control device further includes:

[0113] The first movement ending unit is used to individually identify the detected pets when a pet is detected, and to end the movement when it is confirmed that all pets specified by the search instruction have been detected or all spatial areas have been passed.

[0114] Based on the above embodiment, the motion control device further includes:

[0115] The second movement ending unit is used to individually identify the detected pets when a pet is detected, and end the movement when it is confirmed that all pets specified by the search instruction are detected;

[0116] The supplementary detection unit is used to individually identify the detected pets and move in each spatial area according to the regional detection order when confirming that all pets specified by the search instruction have not been detected and have passed through all spatial areas.

[0117] Based on the above embodiment, the motion control device further includes:

[0118] A status statistics unit is used to perform location status statistics on pet location information to confirm the activity status of each pet;

[0119] A status confirmation unit is used to control the automatic cleaning device to perform pet confirmation detection at the same location when confirming that the same pet has stayed at the same location for a preset time period;

[0120] The abnormality handling unit is used to send the corresponding environment image to a preset terminal device and / or control the automatic cleaning device to approach the pet when the result of the pet confirmation detection is that the same pet is still staying in the same position.

[0121] The motion control device provided in the embodiments of the present application is included in an electronic device and can be used to execute the corresponding motion control method provided in the above embodiments, and has corresponding functions and beneficial effects.

[0122] It is worth noting that in the embodiment of the above-mentioned motion control device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0123] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device includes a processor 310 and a memory 320. The electronic device may also include an input device 330, an output device 340, and a communication device 350. The number of processors 310 in the electronic device may be one or more. Figure 5 In the figure, a processor 310 is used as an example; the processor 310, memory 320, input device 330, output device 340 and communication device 350 in the electronic device can be connected via a bus or other means. Figure 5 The bus connection is taken as an example.

[0124] Memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the motion control method in the embodiments of the present application. Processor 310 executes the software programs, instructions, and modules stored in memory 320 to execute various functional applications and data processing of the electronic device, thereby implementing the aforementioned motion control method.

[0125] The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the electronic device, etc. In addition, the memory 320 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include a memory remotely located relative to the processor 310, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0126] The input device 330 may be used to receive network configuration information. The output device 340 may include a display device such as a display screen.

[0127] The above electronic device can be used to execute any motion control method and has corresponding functions and beneficial effects.

[0128] An embodiment of the present invention also provides a storage medium containing computer-executable instructions. When the computer-executable instructions are executed by a computer processor, they are used to perform relevant operations in the motion control method provided in any embodiment of the present application and have corresponding functions and beneficial effects.

[0129] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products.

[0130] Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0132] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0134] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A motion control method based on pet position information for automatic cleaning equipment, characterized in that: The automatic cleaning device is equipped with an image acquisition module, and the motion control method includes: Receive motion trigger instructions; In response to the motion trigger instruction, determining an area detection sequence according to pre-stored pet location information, wherein the areas in the area detection sequence are spatial areas in a pre-stored environment map; Controlling the automatic cleaning device to move in each of the spatial areas according to the area detection sequence, and collecting environmental images through the image acquisition module during the movement; The environmental image is detected, and when a pet is detected, the pet location information is updated.

2. The motion control method according to claim 1, wherein: The step of determining the area detection order according to pre-stored pet location information in response to the motion trigger instruction includes: In response to the motion trigger instruction, the spatial areas are sorted from high to low according to the number of times the pet is detected in each of the spatial areas in the pre-stored pet location information, and the sorting result is used as the area detection order.

3. The motion control method according to claim 1, wherein: The motion triggering instruction includes a cleaning instruction; Accordingly, the motion control method further includes: When a pet is detected, a reset motion path for the current spatial area is generated, the reset motion path avoids positions that have been passed and the position of the pet, and movement is performed along the reset motion path.

4. The motion control method according to claim 1, wherein: Also includes: The pet appearance probability is detected on the environmental image, and the motion path is reset according to the corresponding path reset strategy based on the probability interval corresponding to the detected current appearance probability, so as to improve the detection result of the pet appearance probability or restore the motion path.

5. The motion control method according to claim 3 or 4, characterized in that: When a pet is detected, generating a reset motion path for the current spatial area, wherein the reset motion path avoids positions that have already been passed and the position of the pet, and moving along the reset motion path, further comprising: When it is confirmed that the pet has left the location, the location of the pet in the reset movement path is cleaned.

6. The motion control method according to claim 1, wherein: The motion triggering instruction includes a search instruction; Accordingly, the motion control method further includes: When a pet is detected, the corresponding environment image is sent to a preset terminal device.

7. The motion control method according to claim 6, characterized in that: The motion control method further includes: When a pet is detected, the detected pet is individually identified, and the movement is terminated when it is confirmed that the pet specified by the search instruction has been detected or all spatial areas have been passed.

8. The motion control method according to claim 6, wherein: The motion control method further includes: When a pet is detected, the detected pet is individually identified, and when it is confirmed that all pets specified by the search instruction are detected, the movement is ended; Individual identification is performed on the detected pets. When it is confirmed that all pets specified by the search instruction have not been detected and all spatial areas have been passed, the pets move in each of the spatial areas according to the area detection order.

9. The motion control method according to claim 1, wherein: Also includes: Performing location status statistics on the pet location information to confirm the activity status of each pet; When it is confirmed that the same pet has stayed at the same location for a predetermined time, the automatic cleaning device is controlled to perform pet confirmation detection at the same location; When the result of the pet confirmation detection is that the same pet is still staying in the same position, the corresponding environment image is sent to a preset terminal device and / or the automatic cleaning device is controlled to approach the pet.

10. A motion control device based on pet location information, used in an automatic cleaning device, characterized in that: The automatic cleaning device is equipped with an image acquisition module, and the motion control device includes: An instruction receiving unit, configured to receive a motion trigger instruction; a sequence confirmation unit, configured to confirm, in response to the motion trigger instruction, a region detection sequence based on pre-stored pet location information, wherein the regions in the region detection sequence are spatial regions in a pre-stored environment map; A motion control unit, configured to control the automatic cleaning device to move in each of the spatial regions according to the region detection sequence, and to capture environmental images through the image acquisition module during the movement; The detection and recording unit is used to detect the environmental image and update the pet location information when a pet is detected.

11. An electronic device, characterized in that include: one or more processors; a memory for storing one or more computer programs; When the one or more computer programs are executed by the one or more processors, the electronic device implements the motion control method based on pet position information as described in any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the motion control method based on pet position information as described in any one of claims 1 to 9 is implemented.

Images