A control method and apparatus of a self-moving device, a device, a storage medium, and a program product

Abstract

This invention discloses a control method, device, equipment, storage medium, and program product for a self-moving device. By acquiring real-time environmental information surrounding a target object and dynamically determining the appropriate transport operation based on this information, rather than applying a uniform grasping and transporting method to all objects, the self-moving device can perceive and adapt to the specific spatial state of the object. Therefore, the device can automatically switch to the most suitable operating strategy based on the surrounding environmental information corresponding to the target object to achieve grasping and transporting. This fundamentally reduces the risk of collisions or operational failures due to spatial limitations, significantly improving the safety and success rate of performing grasping and transporting tasks in complex home environments. It facilitates the storage of target objects or the cleaning of areas previously obscured by target objects, improving the automation level and cleaning coverage of the self-moving device.

Description

Technical Field

[0001] This invention relates to the field of equipment control technology, and in particular to a control method, apparatus, device, storage medium, and program product for self-moving equipment. Background Technology

[0002] In a home environment, self-moving devices (such as robotic vacuum cleaners and service robots) often encounter randomly placed objects when performing autonomous tasks such as cleaning and tidying. These objects may be scattered in specific environmental scenarios, such as passageways, corners, under sofas, beds, coffee tables, or along the device's path. With the development of self-moving devices, it is becoming possible for those equipped with robotic arms or hands to collect these objects. Therefore, how to enable self-moving devices to autonomously and effectively grasp objects based on their surroundings for subsequent collection or cleaning of areas previously obscured by objects has become a problem that needs to be solved. Summary of the Invention

[0003] This application provides a control method, apparatus, device, storage medium, and program product for a self-moving device, which solves the technical problem in the prior art of how to enable a self-moving device to autonomously and effectively combine with the surrounding environment of the target object to grasp the target object, and achieves the technical effect of enabling a self-moving device to autonomously and effectively combine with the surrounding environment of the target object to grasp the target object.

[0004] In a first aspect, this application provides a control method for a self-moving device, the self-moving device being equipped with a robotic arm, the method comprising: Obtain information about the surrounding environment of the target object to be captured; Based on the surrounding environment information, determine the corresponding transportation operation for the target object; Based on the transport operation, the robotic arm of the self-moving device is controlled to grasp and transport the target object.

[0005] In some embodiments of this application, based on the foregoing scheme, the robotic arm includes at least one connecting arm and a robotic hand, and the transport operation includes a first transport operation or a second transport operation; wherein, The first transport operation includes: controlling the robotic arm to grip the target object, and controlling the connecting arm to rotate in order to lift and transport the target object; The second transport operation includes: controlling the robotic arm to grip the target object, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low space, and controlling the connecting arm to rotate to lift and transport the target object.

[0006] In some embodiments of this application, based on the foregoing scheme, the first adjustment operation includes at least one of the following actions: the self-moving device body adjusts its position, the device body adjusts its posture, and the robotic arm adjusts its posture.

[0007] In some embodiments of this application, based on the foregoing scheme, determining the transport operation corresponding to the target object based on the surrounding environment information includes: Based on the surrounding environmental information, determine whether the target object is in a low-ceilinged space; If the surrounding environmental information indicates that the target object is not in a low-lying space, the transportation operation is determined to be the first transportation operation; If the surrounding environmental information indicates that the target object is in a low-lying space, the transportation operation is determined to be the second transportation operation.

[0008] In some embodiments of this application, based on the foregoing scheme, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along a first direction away from the low space; wherein the first direction is determined based on the position of the target object in the low space and the relative position between the self-moving device and the target object.

[0009] In some embodiments of this application, based on the foregoing scheme, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along the second direction; the second direction is the opposite direction of movement when the robotic arm approaches the target object before clamping it.

[0010] In some embodiments of this application, determining whether the target object is in a low-lying space based on the aforementioned scheme and the surrounding environment information includes: The actual height of the top space of the target object is determined based on the surrounding environment information; If the actual height is less than or equal to the first preset height, then the target object is determined to be in a low-ceilinged space. If the actual height is greater than the first preset height, then it is determined that the target object is not in a low-ceilinged space.

[0011] In some embodiments of this application, based on the foregoing scheme, when the surrounding environmental information indicates that the target object is in a low-lying space, before controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Based on the surrounding environmental information, determine whether the target object's state in the low-ceilinged space meets the preset conditions for being captured; If the target object meets the preset conditions for being grasped in a low-ceilinged space, the basic gripping pose of the self-moving device is determined based on the surrounding environment information; the basic gripping pose includes the minimum allowable distance between the device body of the self-moving device and the target object, and the maximum allowable angle between the connecting arm and the top plane of the device body. Based on the aforementioned transport operation, the robotic arm of the self-moving device is controlled to grasp and transport the target object, including: Based on the transport operation and the basic gripping pose, the robotic arm of the self-moving device is controlled to grasp and transport the target object.

[0012] In some embodiments of this application, based on the foregoing scheme, the surrounding environment information includes: the height difference between the top of the target object and the first projection of the target object onto the nearest vertical obstacle, and the distance difference between the second projection of the first end of the target object onto the horizontal plane and the third projection of the second end of the obstacle at the top of the target object onto the horizontal plane; the first end is the end of the target object closer to the self-moving device, and the second end is the end of the top obstacle closer to the self-moving device; Determining whether the target object's state in a low-ceilinged space meets the preset conditions for being grasped based on the surrounding environmental information includes: If the height difference is less than the second preset height or the distance difference is greater than the preset depth, then it is determined that the target object does not meet the preset conditions for being grasped in the low space. If the height difference is greater than or equal to the second preset height and the distance difference is less than or equal to the preset depth, then the target object is determined to meet the preset conditions for being grasped in the low-ceiling space.

[0013] In some embodiments of this application, based on the foregoing scheme, when the surrounding environmental information indicates that the target object is in a low-lying space, before controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the position information of the target object and the current pose information of the self-moving device; Based on the aforementioned transport operation, the robotic arm of the self-moving device is controlled to grasp and transport the target object, including: Based on the location information and the current pose information, the self-moving device is controlled to adjust to a target pose that matches the location information, and the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the transport operation.

[0014] In some embodiments of this application, based on the foregoing scheme, after controlling the self-moving device to adjust to a target pose matching the location information, the method further includes: Determine the target grasping position of the target object; Based on the aforementioned transport operation, the robotic arm of the self-moving device is controlled to grasp and transport the target object, including: Based on the transport operation, the robotic arm of the self-moving device is controlled to grasp the target grasping position and transport the target object.

[0015] In some embodiments of this application, determining the target grasping position of the target object based on the foregoing scheme includes: If a preset valid grasping position of the target object exists within the current field of view of the self-moving device, then any preset valid grasping position within the current field of view is determined as the target grasping position. If there is no preset valid grasping position for the target object within the current field of view of the self-moving device, then the self-moving device is controlled to perform at least one second adjustment operation until there is a preset valid grasping position for the target object within the current field of view of the self-moving device, and any preset valid grasping position within the current field of view is determined as the target grasping position.

[0016] In some embodiments of this application, based on the foregoing scheme, the second adjustment operation includes at least one of the following actions: The self-moving device adjusts its position, adjusts its posture, adjusts its posture, and the robotic arm touches the target object to adjust the target object's posture.

[0017] In some embodiments of this application, based on the foregoing scheme, controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation includes: After the robotic arm performs the action of grasping the target object, if the robotic arm fails to grasp the target object, the surrounding environment information is updated, the transport operation is updated based on the updated surrounding environment information, and the self-moving device is controlled to grasp the target object again according to the updated transport operation, until the robotic arm successfully grasps and transports the target object, or until the number of times the robotic arm attempts to grasp the target object is greater than or equal to a preset number.

[0018] In some embodiments of this application, based on the foregoing scheme, during the process of controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the minimum distance between the robotic arm and surrounding obstacles; When the minimum distance is less than or equal to the preset safety distance, the self-moving device is controlled to perform a third adjustment operation to increase the distance between the robotic arm and surrounding obstacles. The third adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0019] In some embodiments of this application, based on the foregoing scheme, the surrounding environment information of the target object is obtained through any of the following methods: The surrounding environment information is determined based on the sensor data collected by the self-moving device; The surrounding environment information is determined based on the location information of the target object and the map data stored in the self-moving device; The surrounding environment information is determined based on the data input by the user.

[0020] In some embodiments of this application, based on the foregoing scheme, controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation includes: The self-moving device is controlled to carry the target object and move it to a target position that matches a specified position. The self-moving device is then controlled to perform a fourth adjustment operation to place the target object at the specified position. The fourth adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0021] In some embodiments of this application, based on the foregoing scheme, after placing the target object at the designated location, the method further includes: Obtain the actual placement posture of the target object at the specified position; If the actual placement posture does not conform to the preset placement posture, the robotic arm is controlled to adjust its posture to change the placement posture of the target object so that the actual placement posture of the target object conforms to the preset placement posture.

[0022] In some embodiments of this application, based on the foregoing scheme, obtaining the surrounding environment information of the target object to be captured includes: In response to the detection signal generated by the self-moving device during the execution of an autonomous task, indicating that the target shoe has been detected, information about the surrounding environment of the target object to be grasped is acquired. The autonomous task includes a cleaning task and a tidying task; or... In response to the detection signal of the target shoe being detected by the user-triggered representation generated during the execution of the user intervention task by the self-moving device, the surrounding environment information of the target object to be grasped is obtained, and the user intervention task includes the task corresponding to the self-moving device in the remote control mode.

[0023] In some embodiments of this application, based on the foregoing scheme, during the process of controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the actual load of the robotic arm, wherein the actual load is either weight or current. When the actual load is greater than or equal to the preset load, the robotic arm is controlled to release the target object.

[0024] In some embodiments of this application, based on the foregoing scheme, the target object is a target shoe.

[0025] Secondly, this application provides a control device for a self-moving device, the self-moving device being equipped with a robotic arm, the device comprising: The acquisition module is used to acquire information about the surrounding environment of the target object to be captured. The transport operation determination module is used to determine the transport operation corresponding to the target object based on the surrounding environment information. The grasping and transporting module is used to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation.

[0026] In some embodiments of this application, based on the foregoing scheme, the robotic arm includes at least one connecting arm and a robotic hand, and the transport operation includes a first transport operation or a second transport operation; wherein, The first transport operation includes: controlling the robotic arm to grip the target object, and controlling the connecting arm to rotate in order to lift and transport the target object; The second transport operation includes: controlling the robotic arm to grip the target object, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low space, and controlling the connecting arm to rotate to lift and transport the target object.

[0027] In some embodiments of this application, based on the foregoing scheme, the first adjustment operation includes at least one of the following actions: the self-moving device body adjusts its position, the device body adjusts its posture, and the robotic arm adjusts its posture.

[0028] In some embodiments of this application, based on the foregoing scheme, the vehicle operation determination module includes: The determination submodule is used to determine whether the target object is in a low-ceilinged space based on the surrounding environment information. The transport operation determination submodule is used to determine the transport operation as the first transport operation when the surrounding environmental information indicates that the target object is not in a low-lying space; and to determine the transport operation as the second transport operation when the surrounding environmental information indicates that the target object is in a low-lying space.

[0029] In some embodiments of this application, based on the foregoing scheme, the second transport operation includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along a first direction away from the low space; wherein the first direction is determined based on the position of the target object in the low space and the relative position between the self-moving device and the target object.

[0030] In some embodiments of this application, based on the foregoing scheme, the second transport operation includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along the second direction; the second direction is the opposite direction of movement when the robotic arm approaches the target object before clamping it.

[0031] In some embodiments of this application, based on the foregoing scheme, a determination submodule is used for: The actual height of the top space of the target object is determined based on the surrounding environment information; If the actual height is less than or equal to the first preset height, then the target object is determined to be in a low-ceilinged space. If the actual height is greater than the first preset height, then it is determined that the target object is not in a low-ceilinged space.

[0032] In some embodiments of this application, based on the foregoing scheme, a judgment submodule is used to determine whether the target object's state in the low space meets the preset conditions for being grasped, based on the surrounding environment information indicating that the target object is in a low space. The pose determination module is used to determine the basic gripping pose of the self-moving device based on the surrounding environment information if the target object meets the preset conditions for being gripped in a low space. The basic gripping pose includes the minimum allowable distance between the device body of the self-moving device and the target object, and the maximum allowable angle between the connecting arm and the top plane of the device body. The grasping and transporting module is used to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation and the basic gripping pose.

[0033] In some embodiments of this application, based on the foregoing scheme, the surrounding environment information includes: the height difference between the top of the target object and the first projection of the target object onto the nearest vertical obstacle, and the distance difference between the second projection of the first end of the target object onto the horizontal plane and the third projection of the second end of the obstacle at the top of the target object onto the horizontal plane; the first end is the end of the target object closer to the self-moving device, and the second end is the end of the top obstacle closer to the self-moving device; The conditional submodule is used for: If the height difference is less than the second preset height or the distance difference is greater than the preset depth, then it is determined that the target object does not meet the preset conditions for being grasped in the low space. If the height difference is greater than or equal to the second preset height and the distance difference is less than or equal to the preset depth, then the target object is determined to meet the preset conditions for being grasped in the low-ceiling space.

[0034] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used to acquire the position information of the target object and the current pose information of the self-moving device when the surrounding environmental information indicates that the target object is in a low space. The grasping and transporting module is used to control the self-moving device to adjust to a target pose that matches the position information and the current pose information based on the position information, and to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation.

[0035] In some embodiments of this application, based on the foregoing solution, the apparatus further includes: The grasping position determination module is used to determine the target grasping position of the target object after controlling the self-moving device to adjust to the target pose that matches the position information; The grasping and transporting module is used to control the robotic arm of the self-moving device to grasp the target grasping position and transport the target object based on the transporting operation.

[0036] In some embodiments of this application, based on the foregoing scheme, the capture location determination module is used for: If a preset valid grasping position of the target object exists within the current field of view of the self-moving device, then any preset valid grasping position within the current field of view is determined as the target grasping position. If there is no preset valid grasping position for the target object within the current field of view of the self-moving device, then the self-moving device is controlled to perform at least one second adjustment operation until there is a preset valid grasping position for the target object within the current field of view of the self-moving device, and any preset valid grasping position within the current field of view is determined as the target grasping position.

[0037] In some embodiments of this application, based on the foregoing scheme, the second adjustment operation includes at least one of the following actions: The self-moving device adjusts its position, adjusts its posture, adjusts its posture, and the robotic arm touches the target object to adjust the target object's posture.

[0038] In some embodiments of this application, based on the foregoing scheme, the capture and transport module is used for: After the robotic arm performs the action of grasping the target object, if the robotic arm fails to grasp the target object, the surrounding environment information is updated, the transport operation is updated based on the updated surrounding environment information, and the self-moving device is controlled to grasp the target object again according to the updated transport operation, until the robotic arm successfully grasps and transports the target object, or until the number of times the robotic arm attempts to grasp the target object is greater than or equal to a preset number.

[0039] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used to acquire the minimum distance between the robotic arm and surrounding obstacles during the process of the robotic arm of the self-moving device grasping and transporting the target object based on the transport operation control. The device control module is used to control the self-moving device to perform a third adjustment operation to increase the distance between the robotic arm and surrounding obstacles when the minimum distance is less than or equal to a preset safety distance. The third adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0040] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used to acquire the surrounding environment information of the target object in any of the following ways: The surrounding environment information is determined based on the sensor data collected by the self-moving device; The surrounding environment information is determined based on the location information of the target object and the map data stored in the self-moving device; The surrounding environment information is determined based on the data input by the user.

[0041] In some embodiments of this application, based on the foregoing scheme, the capture and transport module is used for: The self-moving device is controlled to carry the target object and move it to a target position that matches a specified position. The self-moving device is then controlled to perform a fourth adjustment operation to place the target object at the specified position. The fourth adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0042] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used to acquire the actual placement posture of the target object at the designated position after the target object is placed at the designated position; The equipment control module is used to control the robotic arm to adjust its posture to change the placement posture of the target object when the actual placement posture does not conform to the preset placement posture, so that the actual placement posture of the target object conforms to the preset placement posture.

[0043] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used for: In response to the detection signal generated by the self-moving device during the execution of an autonomous task, indicating that the target shoe has been detected, information about the surrounding environment of the target object to be grasped is acquired. The autonomous task includes a cleaning task and a tidying task; or... In response to the detection signal of the target shoe being detected by the user-triggered representation generated during the execution of the user intervention task by the self-moving device, the surrounding environment information of the target object to be grasped is obtained, and the user intervention task includes the task corresponding to the self-moving device in the remote control mode.

[0044] In some embodiments of this application, based on the foregoing scheme, the acquisition module is used to acquire the actual load of the robotic arm during the process of the robotic arm of the self-moving device grasping and transporting the target object based on the transport operation control, wherein the actual load is either weight or current. The equipment control module is used to control the robotic arm to release the target object when the actual load is greater than or equal to the preset load.

[0045] In some embodiments of this application, based on the foregoing scheme, the target object is a target shoe.

[0046] Thirdly, this application provides a self-moving device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to execute a control method for a self-moving device as provided in the first aspect.

[0047] Fourthly, this application provides a non-transitory computer-readable storage medium that, when the instructions in the storage medium are executed by the processor of a self-moving device, enables the self-moving device to perform a control method for a self-moving device as provided in the first aspect.

[0048] Fifthly, this application provides a computer program product including computer instructions that are executed by a processor to implement a control method for a self-moving device as provided in the first aspect.

[0049] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: This application's embodiments acquire real-world environmental information surrounding the target object and dynamically determine the appropriate transport operation based on this information, rather than applying a uniform grasping and transport method to all objects. This allows the self-moving device to perceive and adapt to the specific spatial state of the object. Consequently, the device can automatically switch to the most suitable operating strategy based on the surrounding environmental information corresponding to the target object to achieve grasping and transport. This fundamentally reduces the risk of collisions or operational failures due to spatial limitations, significantly improving the safety and success rate of grasping and transporting tasks in complex home environments. This facilitates the storage of target objects or the cleaning of areas previously obscured by target objects, enhancing the automation level and cleaning coverage of the self-moving device. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating a control method for a self-moving device provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a self-moving device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a control device for a self-moving device provided in an embodiment of this application; Figure 4 This application provides an embodiment of a self-moving device architecture diagram.

[0052] Figure label: 1-Self-moving device, 11-Device body, 12-Robotic arm. Detailed Implementation

[0053] This application provides a control method, apparatus, device, storage medium, and program product for a self-moving device, which solves the technical problem in the prior art of how to enable a self-moving device to autonomously and effectively combine with the surrounding environment of the target object to grasp the target object, and achieves the technical effect of enabling a self-moving device to autonomously and effectively combine with the surrounding environment of the target object to grasp the target object.

[0054] The technical solution of this application embodiment is to solve the above-mentioned technical problems, and the general idea is as follows: This application's embodiments acquire real-world environmental information surrounding the target object and dynamically determine the appropriate transport operation based on this information, rather than applying a uniform grasping and transport method to all objects. This allows the self-moving device to perceive and adapt to the specific spatial state of the object. Consequently, the device can automatically switch to the most suitable operating strategy based on the surrounding environmental information corresponding to the target object to achieve grasping and transport. This fundamentally reduces the risk of collisions or operational failures due to spatial limitations, significantly improving the safety and success rate of grasping and transporting tasks in complex home environments. This facilitates the storage of target objects or the cleaning of areas previously obscured by target objects, enhancing the automation level and cleaning coverage of the self-moving device.

[0055] This application embodiment divides the transport operation into a first transport operation and a second transport operation, enabling the self-moving device to employ differentiated action sequences for open spaces and low-ceilinged spaces, namely direct lifting and dragging followed by lifting. This refined action division avoids collisions caused by forcibly lifting the robotic arm in low-ceilinged spaces, while ensuring simple and efficient actions in open spaces. It can grasp and transport objects in both low-ceilinged and non-low-ceilinged spaces, taking into account task diversity, safety, and execution efficiency.

[0056] This application embodiment concretizes the first adjustment operation into multi-dimensional posture coordination between the device body and the robotic arm, enabling the self-moving device to flexibly combine backward, turning, and pitch adjustment actions when dragging a target object out of a low-ceilinged space. This multi-degree-of-freedom collaborative adjustment method can effectively adapt to different depths and orientations of the target object within the low-ceilinged space, improving the ability to successfully remove objects from complex and confined spaces.

[0057] This application embodiment uses both height difference and distance difference as parameters to determine whether the target object's state in a low-ceilinged space meets the preset conditions for grasping. This allows the system to assess "graspability" by adding consideration of the object's depth of indentation, rather than solely evaluating spatial height. This multi-dimensional condition assessment can more accurately identify situations where there is sufficient height space but the object is too deeply recessed to be reachable, effectively filtering out targets that truly possess the conditions for autonomous operation and preventing invalid operations.

[0058] This application embodiment sets a basic gripping posture, using the minimum allowable distance and maximum allowable angle as rigid safety constraints before the robotic arm enters a low-lying space. This ensures that the device body and the robotic arm are confined within a collision-free spatial boundary from the very beginning of the operation. This set of posture constraints is universally applicable to the entire robotic arm chain, ensuring that all connecting arms enter in a low-lying posture, fundamentally establishing the premise for safe operation and avoiding situations where excessive upward movement of local joints compromises the overall safety.

[0059] This embodiment of the application precisely couples the robotic arm's motion commands to the selected gripping position on the target object after positioning, ensuring that the gripping action acts on a stable part confirmed by structural analysis, thus avoiding the impact of blind gripping on gripping stability. This precise locking of the target position ensures that the gripping point has a good force-bearing structure, providing a stable force base for subsequent dragging and lifting, and reducing repeated operations caused by slippage.

[0060] This application's embodiments introduce a second adjustment operation, coordinated by the device body and the robotic arm, when no effective grasping position is available within the field of view. This includes the ability to actively touch the object to change its posture, enabling the self-moving device to proactively alter the environmental state to create operable conditions. This approach overcomes the limitations of passively searching for fixed grasping points, significantly improving the system's proactive adaptability and task completion rate when facing scenarios with poor object posture or occlusion.

[0061] This application's embodiments update the surrounding environment information and modify the transport operation accordingly after a capture failure. This prevents the self-moving device from simply repeating the same action mechanically when faced with an operational failure, instead allowing for iterative strategy iteration based on feedback. This closed-loop retry mechanism fully utilizes the newly revealed environmental state from the failure, dynamically correcting the operation mode and greatly enhancing the system's robustness and eventual success rate in uncertain environments.

[0062] This application embodiment establishes a dynamic safety assurance mechanism that runs parallel to the main transportation task by continuously monitoring the minimum distance between the robotic arm and obstacles during transportation and triggering real-time collision avoidance adjustments. This approach integrates safety protection throughout the entire operation cycle, proactively correcting the trajectory before the critical point of motion interference occurs, and protecting the integrity of the equipment and its surrounding environment without interrupting the task.

[0063] This application's embodiments associate and match designated locations with target object types, and compare and correct the actual placement posture with a preset posture, extending the storage and placement process from simple unloading to a complete action including sorting, repositioning, and posture adjustment. This end-to-end processing effectively ensures the standardization and overall aesthetics of the final storage result, enabling self-moving devices to complete more refined home organization tasks.

[0064] This application's embodiments introduce load monitoring based on weight or current during transport, and perform active release in case of overload, enabling the robotic arm to sense external load anomalies and autonomously execute hardware protection. This mechanism provides a real-time safety boundary for the device at the physical interaction level, effectively preventing overcurrent in the transmission system or structural damage caused by forcibly transporting abnormal objects, thus ensuring the long-term service life of the device.

[0065] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0066] First, it should be clarified that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0067] This application provides a control method for a self-moving device, the self-moving device being equipped with a robotic arm. The method includes steps S11-S13, which can be found in detail elsewhere. Figure 1 As shown.

[0068] Step S11: Obtain information about the surrounding environment of the target object to be captured; Step S12: Determine the transport operation corresponding to the target object based on the surrounding environment information; Step S13: Based on the transport operation, control the robotic arm of the self-moving device to grasp and transport the target object.

[0069] The self-moving devices involved in this application's embodiments can be intelligent devices with autonomous mobility and equipped with robotic arms, such as robotic vacuum cleaners, robotic mops, robotic vacuum and mop combos, service robots, companion robots, warehouse handling robots, and unmanned vehicles. This application's embodiments will only use robotic vacuum cleaners or robotic vacuum and mop combos as examples for subsequent descriptions. Figure 2 As shown, the self-moving device 1 (sweeping robot or sweeping and mopping robot) is equipped with a robotic arm 12. The self-moving device 1 includes a device body 11, and the robotic arm 12 is mounted on the device body 11. The end of the robotic arm 12 is also equipped with a gripper.

[0070] Regarding step S11, obtain the surrounding environment information of the target object to be captured.

[0071] In this embodiment, the target object can be various items that the self-moving device needs to grasp and transport in a work scenario, such as shoes, toys, and miscellaneous items in a home environment. For ease of explanation, this embodiment mainly uses a shoe as an example for illustrative description, but the actual application is not limited to this. The core is that, regardless of the specific object, the corresponding transport operation is dynamically determined and executed based on the real environmental information around it, thereby safely and reliably completing the grasping and transport.

[0072] In step S11, the surrounding environment information of the target object to be captured is obtained, which can be triggered in the following two ways.

[0073] The first method: In response to the detection signal generated by the self-moving device during the execution of the device autonomous task, the detection signal of the target object is detected, and the surrounding environment information of the target object to be grasped is obtained. The device autonomous task includes cleaning task and tidying task.

[0074] The second method: In response to the detection signal of the target object being detected by the user-triggered representation generated during the execution of the user intervention task by the self-moving device, the surrounding environment information of the target object to be captured is obtained, and the user intervention task includes the task corresponding to the self-moving device in the remote control mode.

[0075] Regarding the first approach, it responds to a detection signal generated by the self-moving device during the execution of an autonomous task, representing the detection of a target object. The autonomous task refers to a task performed autonomously by the self-moving device according to a preset program, without real-time user intervention, such as cleaning tasks (including sweeping, vacuuming, and mopping) and tidying tasks (including putting items back in their place). In this approach, the self-moving device continuously senses its environment while performing such tasks. When it detects a target object (e.g., an object located on its path or scattered on the ground), it automatically generates a detection signal and triggers the acquisition of information about the surrounding environment of the target object. This information is then used to determine the appropriate transport operation to grasp and transport the target object.

[0076] Regarding the second approach, it responds to a detection signal generated by the user during the execution of a user-intervention task by the self-moving device, indicating that the target object has been detected. The user intervention task refers to a task performed by the self-moving device under the direct control of the user, typically in remote control mode. Remote control mode allows the user to control the movement and actions of the self-moving device in real time via a remote control, mobile app, or voice commands. In this mode, after observing the target object, the user actively triggers the detection signal (e.g., clicking the "grab this object" command on the app interface). The device then acquires information about the surrounding environment of the object to determine the appropriate transport operation for grasping and transporting the target object.

[0077] The difference between the first and second methods lies in the triggering source and the nature of the task. The former is triggered autonomously by the device, belonging to a fully automated, unattended scenario; the latter is triggered by the user's active intervention, belonging to a human-machine collaboration scenario. The connection between the two is that they together constitute a complete triggering mechanism for self-moving devices to grasp target objects, covering two typical application scenarios: independent device operation and direct user control, enabling the device to respond flexibly in different usage situations.

[0078] For example, a user has a robotic vacuum cleaner equipped with a mechanical arm in their home. During the day, when the robot is performing automatic cleaning tasks, it autonomously detects a slipper obstructing its cleaning path on the living room floor, or detects slippers that need to be collected. It then automatically triggers a grabbing process, acquiring information about the slipper's surrounding environment to determine the appropriate transport operation to grab and carry the slipper – this corresponds to the first method mentioned above. At night, the user returns home and casually places another slipper at the bedroom door. They then remotely control the robot via a mobile app to move it to the bedroom door and click the "Grab this object" button on the app. The robot then acquires information about the slipper's surrounding environment to determine the appropriate transport operation to grab and carry the slipper – this corresponds to the second method mentioned above.

[0079] Furthermore, embodiments of this application can obtain information about the surrounding environment of the target object in any of the following ways: The first method: Determine the surrounding environment information based on sensor data collected by the self-moving device; The second method: Determine the surrounding environment information based on the location information of the target object and the map data stored in the self-moving device; The third method: Determine the surrounding environment information based on user input data.

[0080] Regarding the first approach, the self-moving device uses its onboard sensors, such as vision, structured light, or lidar, to collect real-time 3D environmental data around the target object, thereby generating information about the surrounding environment. This real-time perception-based approach allows the device to flexibly respond to unfamiliar or dynamically changing work scenarios without relying on prior knowledge, directly obtaining the most realistic current spatial conditions.

[0081] Regarding the second method, the mobile device utilizes the known location information of the target object, combined with its own stored environmental map data built through historical operations, to indirectly deduce the spatial characteristics of the location area, thus forming surrounding environmental information. This approach fully leverages the historical data accumulated by the device, quickly identifying the spatial type of the target without repeated scanning, effectively reducing the computational burden of real-time processing and improving response speed.

[0082] Regarding the third method, the self-moving device receives data about the spatial conditions of the target object directly provided by the user through an interactive interface or voice, and uses this data as information about the surrounding environment. This method allows users to transfer experiential knowledge that is difficult for sensors to fully detect to the device, providing clear spatial reference for subsequent operations when the device is first introduced or the environment is too concealed.

[0083] Regarding step S12, the transportation operation corresponding to the target object is determined based on the surrounding environment information.

[0084] like Figure 2 As shown in the embodiments of this application, the robotic arm includes at least one connecting arm and a robotic hand. Correspondingly, the transport operation includes a first transport operation or a second transport operation; wherein, The first transport operation includes: controlling the robotic arm to grip the target object, and controlling the connecting arm to rotate in order to lift and transport the target object; The second transport operation includes: controlling the robotic arm to grip the target object, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space, and controlling the connecting arm to rotate to lift and transport the target object. The first adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0085] The first transport operation corresponds to a scenario where the target object is surrounded by open space and has no obstructions above. After the robotic arm grips the target object, it directly controls the rotation of the connecting arm, using the rotational motion of the connecting arm to vertically lift the target object off the ground for transport. The entire process can be completed solely through the joint movements of the robotic arm itself, resulting in simple actions and high execution efficiency.

[0086] The second transport operation is specifically designed for scenarios where the target object is trapped in a low-ceilinged space, such as under a sofa or bed, where there is insufficient overhead space to directly lift the robotic arm. After the robotic arm grips the target object, it does not immediately attempt to lift it. Instead, it first controls the self-moving device to perform a first adjustment operation. This adjustment operation uses a combination of actions such as the device body retracting, turning, or fine-tuning the robotic arm's posture to drag the target object from the low-ceilinged space to a non-low-ceilinged space with an unobstructed overhead view. Only after ensuring sufficient overhead space is achieved does the connecting arm rotate to lift and transport the target object.

[0087] Furthermore, regarding the second transport operation, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space specifically includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along a first direction away from the low space; wherein the first direction is determined based on the position of the target object in the low space and the relative position between the self-moving device and the target object.

[0088] The first direction is not a fixed, single orientation. Instead, it is determined by the self-moving device, considering the target object's current depth within the low-ceilinged space, as well as the self-moving device's posture and orientation relative to the target object. This comprehensive approach ensures an effective dragging of the target object out of the low-ceilinged space while avoiding interference with surrounding obstacles. For example, if a shoe is located under the bed in the left corner, and the self-moving device approaches and clamps the shoe from the right side of the bed, dragging it directly backward might cause the shoe to collide with the bed leg. In this case, by analyzing the shoe's position and the device's relative posture, the determined first direction might be towards the right rear, that is, along an arc-shaped path that avoids all obstacles, safely dragging the shoe out. The first direction is not fixed but dynamically planned to ensure the shortest path and lowest collision risk when transferring the target object outward from the confined space.

[0089] More specifically, the self-moving device can be controlled to perform the first adjustment operation to drag the target object to a non-low space along a second direction; the second direction is the opposite of the direction of movement when the robotic arm approaches the target object before gripping it.

[0090] The second direction is a typical and simplified implementation of the first direction. It directly takes the opposite direction of the robot arm's movement when it approaches the target object before gripping it as the dragging direction. Since the approaching process has verified the feasibility of the path, its opposite direction naturally constitutes a safe exit path. In other words, in this case, the determined second direction is a specific value of the first direction.

[0091] The advantage of the first direction lies in its high environmental adaptability, which can flexibly formulate the optimal escape route based on the actual spatial geometry. The advantage of the second direction lies in its use of existing motion experience, which eliminates the need to recalculate the path, making it quick and reliable. It is especially suitable for common scenarios where self-moving devices extend in a straight line from an open area into a low space to grab objects.

[0092] Comparing the first and second transport operations, the core difference lies in the different spatial conditions they address, leading to significant differences in the operation sequence. The first transport operation assumes that the robotic arm has sufficient overhead clearance after gripping the object, allowing for direct lifting and transport. The second transport operation, however, faces a situation where the space above the target object is limited. Direct lifting would cause the robotic arm to collide with overhead obstacles. Therefore, a dragging step, coordinated by the overall or partial posture of the equipment, must be introduced to first remove the target object from the confined space, thus resolving the spatial limitations before proceeding to the lifting and transport phase, similar to the first transport operation.

[0093] Further, determining the transport operation corresponding to the target object based on the surrounding environment information includes: Based on the surrounding environmental information, determine whether the target object is in a low-ceilinged space; If the surrounding environmental information indicates that the target object is not in a low-lying space, the transportation operation is determined to be the first transportation operation; If the surrounding environmental information indicates that the target object is in a low-lying space, the transportation operation is determined to be the second transportation operation.

[0094] Specifically, determining whether the target object is in a low-ceilinged space based on the surrounding environment information includes: determining the actual height of the top space of the target object based on the surrounding environment information; if the actual height is less than or equal to a first preset height, then determining that the target object is in a low-ceilinged space; if the actual height is greater than the first preset height, then determining that the target object is not in a low-ceilinged space.

[0095] The actual height of the top space of the target object refers to the vertical distance measured upwards from the top of the target object to the lower edge of the first obstacle. This height directly reflects the clearance available for the robotic arm to move above the target object. For example, if a shoe is located on the floor under a bed, with the highest point of the shoe's upper being 10 centimeters, and the lower edge of the bed board directly above it being 15 centimeters from the ground, then the actual height of the shoe's top space is 5 centimeters. If there is a drawer protruding from the bottom of the shoe's upper, only 3 centimeters away from the shoe's upper, even though the bed board is higher, the actual height is based on the nearest obstacle, and in this case, it is also 3 centimeters.

[0096] Before performing the transport operation, the system first uses information about the surrounding environment to determine the spatial type of the target object. Specifically, it extracts the actual height of the space above the target object and compares it with a pre-set first preset height. This first preset height is typically greater than or equal to the minimum safe clearance required for the robotic arm to directly lift the object after gripping it. If the actual height is less than or equal to the first preset height, it indicates that the space above is insufficient for the robotic arm to lift the object directly; the target object is determined to be in a low-ceilinged space, and the second transport operation is then employed: dragging followed by lifting. Conversely, if the actual height is greater than the first preset height, it indicates that the space above is ample; the target object is determined not to be in a low-ceilinged space, and the first transport operation is directly employed, allowing the robotic arm to grip and lift the object. For example, if the first preset height is set to 30 centimeters, a shoe placed under the bed has an actual top space height of 8 centimeters, which is less than 30 centimeters, so the device determines that it is in a low space. Another shoe on the living room floor has no obstacles detected above it within the effective detection range of the sensor, meaning that the actual top space height exceeds the first preset height. Based on this, the device determines that the shoe is not in a low space and will execute the corresponding operation path.

[0097] Regarding step S13, the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the transport operation.

[0098] When the surrounding environmental information indicates that the target object is not in a low-lying space, the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the first transport operation.

[0099] Once the system determines, based on the surrounding environment information, that the target object is not in a low-lying space, it initiates the first transport operation. The complete execution process of this operation is as follows: the self-moving device first adjusts its own posture to approach the target object; after the robotic arm reaches the predetermined gripping position, it grips the target object; then, it controls the connecting arm to rotate directly upwards, vertically lifting the target object off the ground to a safe transport height; finally, the device carries the target object to the designated location.

[0100] For example, if there's a shoe waiting to be stored in the center of the living room floor, the automated mobile device detects through sensors that there are no obstacles above the shoe within its detection range, and the overhead space is open, determining that it's not in a low-ceilinged area. As the device approaches the shoe, a robotic arm extends and grips the middle of the shoe, while the connecting arm performs an upward rotation, smoothly lifting the shoe off the ground. The automated mobile device then maintains this lifted posture and transports the shoe to a designated placement point next to the shoe rack. The entire process requires no additional dragging of the shoe.

[0101] When the surrounding environment information indicates that the target object is in a low-lying space, before the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the second transport operation, it is necessary to determine whether the current state of the target object meets the basic conditions for grasping and transporting by the self-moving device. Specifically, it is based on the surrounding environment information to determine whether the state of the target object in the low-lying space meets the preset conditions for being grasped.

[0102] The surrounding environment information includes: the height difference between the top of the target object and the first projection of the target object onto the nearest vertical obstacle; the distance difference between the second projection of the first end of the target object onto the horizontal plane and the third projection of the second end of the obstacle at the top of the target object onto the horizontal plane; the first end is the end of the target object closer to the self-moving device, and the second end is the end of the top obstacle closer to the self-moving device.

[0103] Height difference refers to the vertical distance from the top of the target object upwards to the bottom edge of the nearest obstacle directly above it. This parameter measures how narrow the space above the target object is for the robotic arm and connecting arm to move. For example, if a shoe is located under a bed, with the highest point of the shoe's instep 8 centimeters from the ground and the bottom edge of the bed directly above it 14 centimeters from the ground, then the height difference is 6 centimeters. The smaller this value, the more cramped the overhead space, and the less room the robotic arm can maneuver.

[0104] The distance difference refers to the distance offset between the projections of the end of the target object closest to the self-moving device and the end of an obstacle above it closest to the self-moving device on a horizontal plane. This parameter reflects the degree of indentation of the target object relative to the edge of its overhead obstruction. For example, if a shoe is located at the bottom of a sofa, with the toe of the shoe 50 cm horizontally from the self-moving device and the self-moving device 30 cm horizontally from the front edge of the sofa, then the toe of the shoe is indented 20 cm in the horizontal plane compared to the front edge of the sofa. This 20 cm difference is the distance difference. The larger this value, the deeper the target object is embedded within the obstruction.

[0105] Determining whether the target object's state in a low-ceilinged space meets the preset conditions for being grasped based on the surrounding environmental information includes: If the height difference is less than the second preset height or the distance difference is greater than the preset depth, then it is determined that the target object does not meet the preset conditions for being grasped in the low space. If the height difference is greater than or equal to the second preset height and the distance difference is less than or equal to the preset depth, then the target object is determined to meet the preset conditions for being grasped in the low-ceiling space.

[0106] When determining whether a target object is graspable, the system compares the height difference and distance difference with their respective preset thresholds. The second preset height represents the minimum safe clearance that the robotic arm can extend into and operate in a gripping state, while the preset depth represents the maximum permissible depth that the robotic arm can safely penetrate without interfering with overhead obstacles.

[0107] When the height difference is less than the second preset height, it indicates that the gap above the target object is too narrow, and even if the robotic arm manages to reach it, it cannot complete the gripping action without colliding with the top obstacle. When the distance difference is greater than the preset depth, it indicates that the target object is recessed too deeply into the obstruction, and the robotic arm, limited by its own length or the proximity of the device itself, cannot reach the target object. In either of these situations, the system determines that the current state of the target object does not meet the preset conditions for gripping. Only when the height difference is greater than or equal to the second preset height, and the distance difference is less than or equal to the preset depth, does it indicate that there is sufficient gap above the target object for the robotic arm to operate, and the depth of the target object is within the reach of the robotic arm. In this case, the system determines that the state meets the preset conditions for gripping.

[0108] For example, let's set the second preset height to 5 cm and the preset depth to 15 cm. Scenario 1: The height difference at the top of one shoe is 3 cm, and the distance difference is 10 cm. Although the depth is within the reachable range, the height difference of 3 cm is less than 5 cm, so the robotic arm cannot avoid colliding with the obstacle above after reaching in, thus the grasping conditions are not met. Scenario 2: The height difference of one shoe is 8 cm, and the distance difference is 25 cm. While there is ample space at the top, the shoe's recessed depth of 25 cm exceeds the preset depth of 15 cm, so even with full extension, the robotic arm cannot reach the shoe, again resulting in the grasping conditions not being met. Scenario 3: The height difference of one shoe is 7 cm, and the distance difference is 8 cm. The upper gap is sufficient, and the recessed depth is within the reachable range; both conditions are met, and the system determines that the shoe's current state is sufficient for successful grasping.

[0109] Furthermore, when the surrounding environmental information indicates that the target object is in a low-lying space, before controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Based on the surrounding environmental information, determine whether the target object's state in the low-ceilinged space meets the preset conditions for being captured; If the target object meets the preset conditions for being grasped in a low-ceilinged space, the basic gripping pose of the self-moving device is determined based on the surrounding environment information; the basic gripping pose includes the minimum allowable distance between the device body of the self-moving device and the target object, and the maximum allowable angle between the connecting arm and the top plane of the device body.

[0110] The basic gripping pose is a set of constraint parameters for the state of the self-moving device before it performs a gripping action at the edge of a low-ceilinged space. These parameters include the minimum allowable distance between the device body and the target object, and the maximum allowable angle between each connecting arm section and the plane containing the top of the device body.

[0111] The maximum allowable angle is a uniform upper limit. Regardless of the number of connecting arms in the robotic arm, the angle formed between any connecting arm and the top plane of the equipment body during operation must be strictly less than this set value. This is because when operating in low-ceilinged spaces, the presence of overhead obstacles constitutes an overall height restriction plane. If any connecting arm exceeds this angle and tilts upwards, it may cause that connecting arm or its joint to collide with the top, thus causing the entire grasping action to fail. Therefore, this restriction must be maintained throughout the entire arm chain.

[0112] For example, the device itself is 40 cm high, with a usable clearance of 15 cm at the top. The robotic arm consists of two connecting arms. The system calculates and determines the maximum allowable angle to be 20 degrees. During the grasping process, the upper arm joint closer to the main body rotates to 15 degrees, and the lower arm joint closer to the robotic arm rotates to 18 degrees, both within the 20-degree limit. The overall outline of the robotic arm does not touch the overhead obstacle, ensuring safe operation. If the lower arm joint rotates to 22 degrees, although it only exceeds the limit by 2 degrees, the height increase at its end has already caused interference between the arm and the overhead obstacle. Even if the upper arm angle is within the acceptable range, a collision cannot be avoided. This demonstrates why the angle limit must apply to each connecting arm segment.

[0113] After determining that the target object's state in a low-ceilinged space meets the preset conditions for grasping, the system does not immediately drive the robotic arm to grasp it. Instead, it first calculates a set of basic gripping poses based on the surrounding environment. The core significance of these pose parameters is to define a safe operating baseline for the self-moving device, transforming abstract spatial constraints into concrete, executable motion constraints. This ensures that subsequent grasping and dragging actions are within a physically feasible and collision-free range from the starting point. The minimum allowable distance ensures that the device will not collide with obstacles during approach, while the maximum allowable angle ensures that the entire robotic arm chain maintains a low posture at the beginning of the operation. For example, the system determines that the minimum allowable distance to a shoe is 30 centimeters, and the maximum allowable angle is 15 degrees. Based on this, the self-moving device first stops 30 centimeters horizontally from the shoe, and then adjusts the joint angles of all connecting arms to a low posture within 15 degrees, completing the deployment of the basic gripping pose. Under this safe baseline, the robotic arm then extends forward to perform the gripping action. The entire initial movement is performed within the safety boundaries, effectively avoiding obstruction or collisions caused by improper initial posture.

[0114] Based on this, the robotic arm of the self-moving device can be controlled to grasp and transport the target object based on the transport operation and the basic gripping pose. Specifically, the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the second transport operation and the basic gripping pose. When the target object is in a low-lying space and the gripping conditions are met, the system integrates the complete execution process of safety constraints and drag-and-lift strategies. The self-moving device first positions itself according to the basic gripping pose, stopping the device body at a position that maintains a distance greater than or equal to the minimum allowable distance from the target object, and controlling the joint angle of each connecting arm to be adjusted to within the maximum allowable angle, so that the entire robotic arm enters the edge area of ​​the low-lying space in a low-lying posture. At this safety baseline, the robotic arm extends forward to grasp the target object, and then performs the second transport operation: first, through the device body retracting, turning, or fine-tuning the attitude of the connecting arm, the target object is dragged along the planned safe path from the low-ceilinged space to an unobstructed area above; after confirming that the surrounding environment has changed to a non-low-ceilinged space, the angle restriction of the connecting arm is released, and the connecting arm is driven to rotate upward, lifting the target object off the ground and transporting it to the designated position. The entire process combines static posture constraints with dynamic transport strategies, with each step—from safe entry and safe dragging out to final lifting—being interconnected.

[0115] Furthermore, if the target object's state in a low-ceilinged space does not meet the preset conditions for being captured, a manual intervention reminder signal is generated to prompt the user to handle the situation manually.

[0116] When the system determines, based on height and distance differences, that the target object's position in a low-ceilinged space does not meet the preset conditions for grasping, it indicates that if the robotic arm were to forcibly intervene, there is a high probability of collision or inaccessibility due to the narrow gap at the top or the object being too deeply recessed. In this situation, the self-moving device will not attempt to grasp the object but will immediately halt the autonomous operation process and generate a manual intervention alert signal. This signal can be issued via the device's built-in voice module, indicator lights, or a push notification to the associated user terminal application, clearly informing the user that the space where the object is located is too narrow or too deep, exceeding the device's autonomous handling capabilities. For example, if the top of a shoe has a height difference of only 3 centimeters, making it impossible for the robotic arm to safely reach in, the device will issue a voice prompt "Please remove obstacles in the low-ceilinged space," or send a notification to the user's mobile phone, reminding the user to manually remove the shoe or adjust its position. Through this mechanism, the system achieves a clear connection between autonomous capabilities and human assistance while ensuring operational safety.

[0117] Furthermore, when the surrounding environmental information indicates that the target object is in a low-lying space, before controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the position information of the target object and the current pose information of the self-moving device; Based on the location information and the current pose information, the self-moving device is controlled to adjust to a target pose that matches the location information, and the robotic arm of the self-moving device is controlled to grasp and transport the target object based on the transport operation.

[0118] First, the system simultaneously acquires two sets of key data: the target object's position information, i.e., its spatial coordinates in the current environment map; and the self-moving device's current pose information, i.e., the device's current position and orientation. Then, the system compares and calculates these two sets of data to determine the necessary movement path from the current pose to the entrance of the low-ceilinged space where the object is located. Next, the self-moving device adjusts itself based on the calculation results, for example, by moving forward or turning, until the device finally stops at a target pose that matches the target object's position information. This target pose ensures that the device is facing the low-ceilinged space opening and is in the optimal relative position to the target object for effective subsequent dragging operations.

[0119] After completing the target pose adjustment and deployment, the system immediately connects to the subsequent process, starting the grasping operation based on the determined second transport operation. At this point, since the equipment is already in the optimal starting position, the robotic arm can smoothly reach into low-ceilinged spaces along the planned path. After gripping the target object, through the coordinated movements of the combined equipment body and the robotic arm, the object is dragged to a non-low-ceilinged space, and finally lifted and transported to the destination. The entire process from position perception and self-localization to target pose alignment provides a spatial reference for precise and reliable operation in low-ceilinged spaces.

[0120] More specifically, after controlling the self-moving device to adjust to a target pose matching the location information, the method further includes: Determine the target grasping position of the target object; Based on the transport operation, the robotic arm of the self-moving device is controlled to grasp the target grasping position and transport the target object.

[0121] After the self-moving device completes the target pose adjustment and positions itself at the entrance of the low-ceilinged space, the system does not immediately perform gripping. Instead, it first performs a local analysis of the target object to select a specific and feasible target gripping position. This target gripping position is determined based on a comprehensive consideration of factors such as the object's contour, orientation, and the distribution of surrounding obstacles obtained by sensors. Priority is given to parts of the object with obvious features, suitable curvature, and where the robotic arm can stably close and apply force, such as the heel of a shoe.

[0122] After determining the target gripping position, the system couples the robotic arm movement commands from the transport operation to that position, guiding the robotic arm to move precisely toward the selected area and complete the gripping. This ensures a high success rate and stability of the gripping action, avoiding slippage or ineffective dragging due to improper gripping position. After gripping the target position, the self-moving device then follows the predetermined procedure of the second transport operation, first dragging the target object from a low-ceilinged space to an open area through a first adjustment action, and then raising the connecting arm to transport it to its destination.

[0123] Determining the target grasping position of the target object includes: If a preset valid grasping position of the target object exists within the current field of view of the self-moving device, then any preset valid grasping position within the current field of view is determined as the target grasping position. If there is no preset valid grasping position for the target object within the current field of view of the self-moving device, the self-moving device is controlled to perform at least one second adjustment operation until there is a preset valid grasping position for the target object within the current field of view of the self-moving device, and any preset valid grasping position within the current field of view is determined as the target grasping position; the second adjustment operation includes at least one of the following actions: the self-moving device body adjusts its position, the device body adjusts its posture, the robotic arm adjusts its posture, and the robotic arm touches the target object to adjust the posture of the target object.

[0124] Preset effective gripping positions refer to a series of parts that the system pre-defines based on the type of the target object, suitable for gripping by the robotic arm, such as the heel, sides of the shoe upper, or the toe area. If any of these preset positions is directly visible within the sensor's field of view after the self-moving device is in place, it means that the current orientation of the target object exposes a feature area that can be gripped. In this case, the system can directly select one as the target gripping position without performing additional environmental interaction. For example, after the device stops at the entrance of a low-ceilinged space, the camera image clearly shows the heel of a sneaker facing the device, and the heel is one of the preset effective gripping positions for this shoe type. The system will then directly determine this heel area as the target gripping position and drive the robotic arm to grip it.

[0125] If no preset valid gripping position is visible within the current field of view of the self-moving device, it indicates that the current posture of the target object is not conducive to direct gripping. At this time, the system will trigger a series of active adjustment actions. These adjustment actions include: fine-tuning the position of the device itself to change the viewing angle, adjusting its own posture to obtain a better field of view tilt angle, fine-tuning the probe posture of the robotic arm to find a gripping point, and even using the robotic arm to lightly touch or flick the target object to cause it to flip or shift, thereby exposing the originally hidden gripping position. The system will continuously perform these second adjustment operations and re-check whether a preset valid gripping position appears in the field of view after each adjustment. Once it appears, it will be identified as the target gripping position and the adjustment will stop. For example, a slipper is located deep under the bed with the upper facing up. From the device's perspective, no heel or edge structure that can be used for gripping is visible. The device first tries to slightly move its body to the left to change the viewing angle, but still does not find a valid position; then it extends a connecting arm to gently touch the side of the slipper, causing it to flip and expose the edge of the sole. At this time, the edge of the sole appears in the field of view as a preset valid gripping position, and the system immediately locks the position and performs gripping.

[0126] When determining the target gripping position, the system can also make more refined decisions based on the specific attributes of the target object. Firstly, it can select more suitable structural features as effective gripping positions based on the type of target object. For example, for footwear, the system prioritizes the thick heel counter of athletic shoes, the rear edge of the shoe opening for leather shoes, and the joint edge between the upper and sole of slippers. This differentiated setting ensures that the gripping position matches the structural strength and geometric characteristics of the object, improving the stability of the grip. Secondly, when multiple preset effective gripping positions exist simultaneously within the field of view, the system can select the best one according to preset priority rules. Priority can be comprehensively set based on factors such as gripping stability, dragging force direction, and the sufficiency of the robotic arm's closed space. For example, the system sets the heel area as the highest priority, followed by the sides of the shoe upper, and the toe area as the lowest. If the heel and toe of a shoe are visible simultaneously, the system will prioritize the heel as the target gripping position because the dragging force is more easily transmitted along the long axis of the shoe when gripping from the heel, making it less likely for the shoe to slip during dragging.

[0127] Furthermore, controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation includes: After the robotic arm performs the action of grasping the target object, if the robotic arm fails to grasp the target object, the surrounding environment information is updated, the transport operation is updated based on the updated surrounding environment information, and the self-moving device is controlled to grasp the target object again according to the updated transport operation, until the robotic arm successfully grasps and transports the target object, or until the number of times the robotic arm attempts to grasp the target object is greater than or equal to a preset number.

[0128] After the robotic arm performs a grasping action, the system uses sensor feedback to determine whether the target object has been securely gripped. If a grasping failure is detected, such as the robotic arm slipping, failing to reach the object, or the object not being successfully pulled out, the system will not simply repeat the same mechanical action. It will first re-collect the latest data on the target object and its surrounding environment to update the environmental information, as the failure itself may have changed the object's position or spatial state. Based on the updated environmental information, the system will reassess the current spatial conditions, potentially switching the transport operation from the first to the second operation, adjusting the dragging direction, or changing the target grasping position, thus forming an updated transport operation plan. Subsequently, the self-moving device will execute the grasping and transport process again according to the updated plan. This process is repeated until one of two termination conditions occurs: either the robotic arm successfully grasps and transports the target object, completing the task; or the cumulative number of grasping attempts reaches the preset limit, the system determines that it has exceeded its autonomous processing capacity, stops retrying, and generates a manual intervention reminder signal to avoid unnecessary consumption or equipment damage.

[0129] For example, when the self-mounted device first attempts to retrieve a shoe from under the bed, the initial transport operation is the second transport operation, which plans to clamp the heel and drag it backward. However, during execution, the side of the shoe is pressed against the bed leg, and dragging backward causes the shoe to get stuck, causing the robotic arm to slip and the retrieval to fail. After detecting the failure, the system immediately updates the surrounding environment information and finds that the shoe has slightly shifted and its contact with the bed leg has changed. Based on this, the system updates the transport operation to drag along the right rear direction at the angle to the bed leg, while adjusting the target gripping position from the heel to the side of the shoe to better adapt to the new force angle. The self-mounted device executes the updated plan again, successfully pulling the shoe out and lifting the transport. If it still fails after three consecutive attempts, and the preset number of attempts is three, the device stops iterating and sends a prompt to the user requesting manual assistance.

[0130] Furthermore, during the process of controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the minimum distance between the robotic arm and surrounding obstacles; When the minimum distance is less than or equal to the preset safety distance, the self-moving device is controlled to perform a third adjustment operation to increase the distance between the robotic arm and surrounding obstacles. The third adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0131] At any moment during a transport operation, the system continuously monitors the real-time minimum distance between the robotic arm's joints and the manipulator and various obstacles in the surrounding environment via sensors. This parameter reflects the safety margin of the current operation. Once this minimum distance is detected to shrink to or below a preset safe distance, it means that the robotic arm is about to make contact with or collide with an obstacle, and the system immediately triggers a third adjustment operation for proactive avoidance. The third adjustment operation is a set of flexibly combinable collision avoidance actions, including: controlling the device body to move slightly to increase the overall spacing, adjusting the device body's posture to change the robotic arm's working reference plane, or fine-tuning the joint angles of the robotic arm itself to allow the arm to bypass the obstacle. By executing these actions, the system increases the distance between the robotic arm and the obstacle in real time, bringing the operation back to a safe range, and then continues to execute the predetermined grasping or transport process. This mechanism provides real-time safety monitoring of the robotic arm's movement without interrupting the main task.

[0132] For example, the self-moving device is performing the second transport operation, dragging a shoe outward from the bottom of a sofa along a curved path. During the dragging process, the elbow joint of the robotic arm gradually approaches the edge of the sofa's bottom frame along the movement trajectory. The system detects that the minimum distance between the elbow joint and the sofa's bottom frame has decreased from 8 centimeters to 3 centimeters, reaching the preset safe distance threshold. The system then determines that intervention is needed and performs a third adjustment operation, controlling the device body to slightly shift to the right while simultaneously pressing the elbow joint downward by 2 degrees. After the adjustment, the minimum distance between the elbow and the sofa's bottom frame is restored to the safe range of 7 centimeters, and the device then continues to complete the remaining dragging and lifting actions without making contact with the sofa throughout the entire process.

[0133] Specifically, controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation includes: The self-moving device is controlled to carry the target object and move it to a target position that matches a specified position. The self-moving device is then controlled to perform a fourth adjustment operation to place the target object at the specified position. The fourth adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0134] With the robotic arm firmly holding the target object, the self-moving device first moves the object to a target location that matches the designated position. This target location is typically a spatial coordinate close to the designated placement point, such as in front of a shoe rack or on one side of an entryway storage area. Upon reaching the target location, the system does not simply release the robotic arm and drop the object randomly. Instead, based on the specific spatial conditions of the designated location, it controls the self-moving device to perform a fourth adjustment operation. Through fine-tuning of the device itself, posture adjustment, and coordinated changes in the robotic arm's posture, the target object is precisely aligned with the designated position and finally placed securely.

[0135] For example, a self-moving device carries a shoe from the living room to the shoe rack area. The system first moves the shoe to the target position directly in front of the open shelf at the bottom of the shoe rack, while the shoe is still suspended outside the rack. Then, the device performs a fourth adjustment: the connecting arm rotates forward and downward to align the shoe with the space inside the shelf, the device body moves slightly forward to deliver the shoe into the shelf, and the robotic arm releases after confirming that the sole has contacted the shelf, completing the placement. Throughout the process, the movement and adjustment work together to ensure the shoe is smoothly delivered to the designated position rather than being thrown or tipped over.

[0136] It's important to note that the final placement of the target object is not fixed. Instead, it's dynamically determined by the system based on factors such as the object's type, attributes, and pre-defined user habits. The system can pre-build a storage location mapping, associating different categories of objects with corresponding spatial areas—for example, shoes with shoe racks, toys with storage boxes, and books with bookshelves. During actual transport and placement, the self-moving device first identifies the target object's category, then automatically selects the matching location based on the mapping, and finally transports and places the object there. This mechanism makes storage behavior more aligned with the organization logic of a real home environment, achieving intelligent operation of categorized placement rather than simple stacking.

[0137] After placing the target object at the designated location, the method further includes: Obtain the actual placement posture of the target object at the specified position; If the actual placement posture does not conform to the preset placement posture, the robotic arm is controlled to adjust its posture to change the placement posture of the target object so that the actual placement posture of the target object conforms to the preset placement posture.

[0138] After the target object has been placed in the designated position, the self-moving device uses its own sensors to obtain the object's actual placement posture, such as the object's orientation, whether it is upright or tilted, and whether it is aligned with other stored items. The system compares the obtained actual placement posture with the pre-set placement posture. If they match, the placement effect meets the requirements, and the task ends; if they do not match, the robotic arm is controlled to contact the target object again, and its placement state is changed through fine-tuning actions such as pushing, pushing, and straightening until the actual posture matches the preset posture.

[0139] For example, the system defaults to placing shoes on the shoe rack with the toes facing inwards and the heels facing outwards, upright. When the mobile device places a sneaker on a shelf, the camera detects that the shoe is actually lying on its side, horizontally on the shelf, which does not match the default upright posture. The device then controls a robotic arm to approach the side of the shoe and gently flip it to straighten it, ensuring the sole is on the shelf and the toe is facing inwards. Once the posture is confirmed to be correct, the robotic arm retracts, and the placement task is completed.

[0140] Furthermore, during the process of controlling the robotic arm of the self-moving device to grasp and transport the target object based on the transport operation, the method further includes: Obtain the actual load of the robotic arm, wherein the actual load is either weight or current. When the actual load is greater than or equal to the preset load, the robotic arm is controlled to release the target object.

[0141] During the movement (including dragging) or lifting of the target object by the robotic arm, the system monitors the actual load borne by the robotic arm in real time. This load can be directly obtained from the weight value via force sensors, or indirectly reflected by monitoring the current value of the joint drive motor. The system continuously compares this real-time value with a preset load. The preset load is a safety threshold set based on the structural strength of the robotic arm, the capability of the drive system, and safety margins, representing the upper limit that the robotic arm can safely bear. Once the actual load is detected to reach or exceed the preset load, it indicates that the target object may be abnormally heavy, or that the object is stuck by a foreign object during transport, causing additional resistance. Continuing to apply force will risk damaging the robotic arm's transmission components or burning out the motor. In this situation, the system will immediately execute a protective action, controlling the robotic arm to release the target object, removing the abnormal load, and preventing damage to the equipment itself. Subsequently, the system can record this event and issue an anomaly warning to the user, such as reminding the user to check if the object is too heavy or stuck. For example, when the self-moving device picks up a shoe and lifts it, the motor current driving the connecting arm rotates continuously increases and touches the preset current threshold, indicating that the shoe may be pressed down by other heavy objects or that the shoe material is abnormally heavy. The device then controls the robotic arm to release the shoe, stops the transport, and prompts the user to handle the situation, thereby avoiding damage to the robotic arm caused by forced transport.

[0142] In summary, this application's embodiments acquire real-world environmental information surrounding the target object and dynamically determine the appropriate transport operation based on this information, rather than applying a uniform grasping and transport method to all objects. This allows the self-moving device to perceive and adapt to the specific spatial state of the object. Consequently, the device can automatically switch to the most suitable operating strategy based on the surrounding environmental information corresponding to the target object to achieve grasping and transport. This fundamentally reduces the risk of collisions or operational failures due to spatial limitations, significantly improving the safety and success rate of grasping and transporting tasks in complex home environments. This facilitates the storage of target objects or the cleaning of areas previously obscured by target objects, enhancing the automation level and cleaning coverage of the self-moving device.

[0143] This application embodiment divides the transport operation into a first transport operation and a second transport operation, enabling the self-moving device to employ differentiated action sequences for open spaces and low-ceilinged spaces, namely direct lifting and dragging followed by lifting. This refined action division avoids collisions caused by forcibly lifting the robotic arm in low-ceilinged spaces, while ensuring simple and efficient actions in open spaces. It can grasp and transport objects in both low-ceilinged and non-low-ceilinged spaces, taking into account task diversity, safety, and execution efficiency.

[0144] This application embodiment concretizes the first adjustment operation into multi-dimensional posture coordination between the device body and the robotic arm, enabling the self-moving device to flexibly combine backward, turning, and pitch adjustment actions when dragging a target object out of a low-ceilinged space. This multi-degree-of-freedom collaborative adjustment method can effectively adapt to different depths and orientations of the target object within the low-ceilinged space, improving the ability to successfully remove objects from complex and confined spaces.

[0145] This application embodiment uses both height difference and distance difference as parameters to determine whether the target object's state in a low-ceilinged space meets the preset conditions for grasping. This allows the system to assess "graspability" by adding consideration of the object's depth of indentation, rather than solely evaluating spatial height. This multi-dimensional condition assessment can more accurately identify situations where there is sufficient height space but the object is too deeply recessed to be reachable, effectively filtering out targets that truly possess the conditions for autonomous operation and preventing invalid operations.

[0146] This application embodiment sets a basic gripping posture, using the minimum allowable distance and maximum allowable angle as rigid safety constraints before the robotic arm enters a low-lying space. This ensures that the device body and the robotic arm are confined within a collision-free spatial boundary from the very beginning of the operation. This set of posture constraints is universally applicable to the entire robotic arm chain, ensuring that all connecting arms enter in a low-lying posture, fundamentally establishing the premise for safe operation and avoiding situations where excessive upward movement of local joints compromises the overall safety.

[0147] This embodiment of the application precisely couples the robotic arm's motion commands to the selected gripping position on the target object after positioning, ensuring that the gripping action acts on a stable part confirmed by structural analysis, thus avoiding the impact of blind gripping on gripping stability. This precise locking of the target position ensures that the gripping point has a good force-bearing structure, providing a stable force base for subsequent dragging and lifting, and reducing repeated operations caused by slippage.

[0148] This application's embodiments introduce a second adjustment operation, coordinated by the device body and the robotic arm, when no effective grasping position is available within the field of view. This includes the ability to actively touch the object to change its posture, enabling the self-moving device to proactively alter the environmental state to create operable conditions. This approach overcomes the limitations of passively searching for fixed grasping points, significantly improving the system's proactive adaptability and task completion rate when facing scenarios with poor object posture or occlusion.

[0149] This application's embodiments update the surrounding environment information and modify the transport operation accordingly after a capture failure. This prevents the self-moving device from simply repeating the same action mechanically when faced with an operational failure, instead allowing for iterative strategy iteration based on feedback. This closed-loop retry mechanism fully utilizes the newly revealed environmental state from the failure, dynamically correcting the operation mode and greatly enhancing the system's robustness and eventual success rate in uncertain environments.

[0150] This application embodiment establishes a dynamic safety assurance mechanism that runs parallel to the main transportation task by continuously monitoring the minimum distance between the robotic arm and obstacles during transportation and triggering real-time collision avoidance adjustments. This approach integrates safety protection throughout the entire operation cycle, proactively correcting the trajectory before the critical point of motion interference occurs, and protecting the integrity of the equipment and its surrounding environment without interrupting the task.

[0151] This application's embodiments associate and match designated locations with target object types, and compare and correct the actual placement posture with a preset posture, extending the storage and placement process from simple unloading to a complete action including sorting, repositioning, and posture adjustment. This end-to-end processing effectively ensures the standardization and overall aesthetics of the final storage result, enabling self-moving devices to complete more refined home organization tasks.

[0152] This application's embodiments introduce load monitoring based on weight or current during transport, and perform active release in case of overload, enabling the robotic arm to sense external load anomalies and autonomously execute hardware protection. This mechanism provides a real-time safety boundary for the device at the physical interaction level, effectively preventing overcurrent in the transmission system or structural damage caused by forcibly transporting abnormal objects, thus ensuring the long-term service life of the device.

[0153] Based on the same inventive concept, the embodiments of this application provide, as follows: Figure 3 The control device for a self-moving device shown includes: Acquisition module 31 is used to acquire information about the surrounding environment of the target object to be captured; The transport operation determination module 32 is used to determine the transport operation corresponding to the target object based on the surrounding environment information. The grasping and transporting module 33 is used to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation.

[0154] In some embodiments of this application, based on the foregoing scheme, the robotic arm includes at least one connecting arm and a robotic hand, and the transport operation includes a first transport operation or a second transport operation; wherein, The first transport operation includes: controlling the robotic arm to grip the target object, and controlling the connecting arm to rotate in order to lift and transport the target object; The second transport operation includes: controlling the robotic arm to grip the target object, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low space, and controlling the connecting arm to rotate to lift and transport the target object.

[0155] In some embodiments of this application, based on the foregoing scheme, the first adjustment operation includes at least one of the following actions: the self-moving device body adjusts its position, the device body adjusts its posture, and the robotic arm adjusts its posture.

[0156] In some embodiments of this application, based on the foregoing scheme, the vehicle operation determination module 32 includes: The determination submodule is used to determine whether the target object is in a low-ceilinged space based on the surrounding environment information. The transport operation determination submodule is used to determine the transport operation as the first transport operation when the surrounding environmental information indicates that the target object is not in a low-lying space; and to determine the transport operation as the second transport operation when the surrounding environmental information indicates that the target object is in a low-lying space.

[0157] In some embodiments of this application, based on the foregoing scheme, the second transport operation includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along a first direction away from the low space; wherein the first direction is determined based on the position of the target object in the low space and the relative position between the self-moving device and the target object.

[0158] In some embodiments of this application, based on the foregoing scheme, the second transport operation includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along the second direction; the second direction is the opposite direction of movement when the robotic arm approaches the target object before clamping it.

[0159] In some embodiments of this application, based on the foregoing scheme, a determination submodule is used for: The actual height of the top space of the target object is determined based on the surrounding environment information; If the actual height is less than or equal to the first preset height, then the target object is determined to be in a low-ceilinged space. If the actual height is greater than the first preset height, then it is determined that the target object is not in a low-ceilinged space.

[0160] In some embodiments of this application, based on the foregoing scheme, a judgment submodule is used to determine whether the target object's state in the low space meets the preset conditions for being grasped, based on the surrounding environment information indicating that the target object is in a low space. The pose determination module is used to determine the basic gripping pose of the self-moving device based on the surrounding environment information if the target object meets the preset conditions for being gripped in a low space. The basic gripping pose includes the minimum allowable distance between the device body of the self-moving device and the target object, and the maximum allowable angle between the connecting arm and the top plane of the device body. The grasping and transporting module 33 is used to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation and the basic gripping pose.

[0161] In some embodiments of this application, based on the foregoing scheme, the surrounding environment information includes: the height difference between the top of the target object and the first projection of the target object onto the nearest vertical obstacle, and the distance difference between the second projection of the first end of the target object onto the horizontal plane and the third projection of the second end of the obstacle at the top of the target object onto the horizontal plane; the first end is the end of the target object closer to the self-moving device, and the second end is the end of the top obstacle closer to the self-moving device; The conditional submodule is used for: If the height difference is less than the second preset height or the distance difference is greater than the preset depth, then it is determined that the target object does not meet the preset conditions for being grasped in the low space. If the height difference is greater than or equal to the second preset height and the distance difference is less than or equal to the preset depth, then the target object is determined to meet the preset conditions for being grasped in the low-ceiling space.

[0162] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used to acquire the position information of the target object and the current pose information of the self-moving device when the surrounding environment information indicates that the target object is in a low space. The grasping and transporting module 33 is used to control the self-moving device to adjust to a target pose that matches the position information and the current pose information based on the position information, and to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation.

[0163] In some embodiments of this application, based on the foregoing solution, the apparatus further includes: The grasping position determination module is used to determine the target grasping position of the target object after controlling the self-moving device to adjust to the target pose that matches the position information; The grasping and transporting module 33 is used to control the robotic arm of the self-moving device to grasp the target grasping position and transport the target object based on the transporting operation.

[0164] In some embodiments of this application, based on the foregoing scheme, the capture location determination module is used for: If a preset valid grasping position of the target object exists within the current field of view of the self-moving device, then any preset valid grasping position within the current field of view is determined as the target grasping position. If there is no preset valid grasping position for the target object within the current field of view of the self-moving device, then the self-moving device is controlled to perform at least one second adjustment operation until there is a preset valid grasping position for the target object within the current field of view of the self-moving device, and any preset valid grasping position within the current field of view is determined as the target grasping position.

[0165] In some embodiments of this application, based on the foregoing scheme, the second adjustment operation includes at least one of the following actions: The self-moving device adjusts its position, adjusts its posture, adjusts its posture, and the robotic arm touches the target object to adjust the target object's posture.

[0166] In some embodiments of this application, based on the foregoing scheme, the grabbing and transporting module 33 is used for: After the robotic arm performs the action of grasping the target object, if the robotic arm fails to grasp the target object, the surrounding environment information is updated, the transport operation is updated based on the updated surrounding environment information, and the self-moving device is controlled to grasp the target object again according to the updated transport operation, until the robotic arm successfully grasps and transports the target object, or until the number of times the robotic arm attempts to grasp the target object is greater than or equal to a preset number.

[0167] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used to acquire the minimum distance between the robotic arm and surrounding obstacles during the process of the robotic arm of the self-moving device grasping and transporting the target object based on the transport operation control. The device control module is used to control the self-moving device to perform a third adjustment operation to increase the distance between the robotic arm and surrounding obstacles when the minimum distance is less than or equal to a preset safety distance. The third adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0168] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used to acquire the surrounding environment information of the target object in any of the following ways: The surrounding environment information is determined based on the sensor data collected by the self-moving device; The surrounding environment information is determined based on the location information of the target object and the map data stored in the self-moving device; The surrounding environment information is determined based on the data input by the user.

[0169] In some embodiments of this application, based on the foregoing scheme, the grabbing and transporting module 33 is used for: The self-moving device is controlled to carry the target object and move it to a target position that matches a specified position. The self-moving device is then controlled to perform a fourth adjustment operation to place the target object at the specified position. The fourth adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

[0170] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used to acquire the actual placement posture of the target object at the designated position after the target object is placed at the designated position; The equipment control module is used to control the robotic arm to adjust its posture to change the placement posture of the target object when the actual placement posture does not conform to the preset placement posture, so that the actual placement posture of the target object conforms to the preset placement posture.

[0171] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used for: In response to the detection signal generated by the self-moving device during the execution of an autonomous task, indicating that the target shoe has been detected, information about the surrounding environment of the target object to be grasped is acquired. The autonomous task includes a cleaning task and a tidying task; or... In response to the detection signal of the target shoe being detected by the user-triggered representation generated during the execution of the user intervention task by the self-moving device, the surrounding environment information of the target object to be grasped is obtained, and the user intervention task includes the task corresponding to the self-moving device in the remote control mode.

[0172] In some embodiments of this application, based on the foregoing scheme, the acquisition module 31 is used to acquire the actual load of the robotic arm during the process of the robotic arm of the self-moving device grasping and transporting the target object based on the transport operation control. The actual load is either weight or current. The equipment control module is used to control the robotic arm to release the target object when the actual load is greater than or equal to the preset load.

[0173] In some embodiments of this application, based on the foregoing scheme, the target object is a target shoe.

[0174] Based on the same inventive concept, the embodiments of this application provide, as follows: Figure 4 The self-moving device shown includes: Processor 41; Memory 42 is used to store executable instructions of the processor 41; The processor 41 is configured to execute a control method for a self-moving device as described above.

[0175] Based on the same inventive concept, embodiments of this application provide a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of a self-moving device, enables the self-moving device to execute a control method for a self-moving device as described above.

[0176] Based on the same inventive concept, embodiments of this application provide a computer program product, including computer instructions, which are executed by a processor to implement a control method for a self-moving device as described above.

[0177] Since the self-moving device described in this embodiment is the self-moving device used to implement the information processing method in the embodiments of this application, those skilled in the art can understand the specific implementation methods and various variations of the self-moving device in this embodiment based on the information processing method described in the embodiments of this application. Therefore, how the self-moving device implements the method in the embodiments of this application will not be described in detail here. Any self-moving device used by those skilled in the art to implement the information processing method in the embodiments of this application falls within the scope of protection of this application.

[0178] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0179] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0180] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0181] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0182] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0183] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A control method for a self-moving device, characterized in that, The self-moving device is equipped with a robotic arm, and the method includes: Obtain information about the surrounding environment of the target object to be captured; Based on the surrounding environment information, determine the corresponding transportation operation for the target object; Based on the transport operation, the robotic arm of the self-moving device is controlled to grasp and transport the target object.

2. The control method for a self-moving device as described in claim 1, characterized in that, The robotic arm includes at least one connecting arm and a robotic hand, and the transport operation includes a first transport operation or a second transport operation; wherein... The first transport operation includes: controlling the robotic arm to grip the target object, and controlling the connecting arm to rotate in order to lift and transport the target object; The second transport operation includes: controlling the robotic arm to grip the target object, controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low space, and controlling the connecting arm to rotate to lift and transport the target object.

3. The control method for a self-moving device as described in claim 2, characterized in that, The first adjustment operation includes at least one of the following actions: adjusting the position of the self-moving device body, adjusting the posture of the device body, and adjusting the posture of the robotic arm.

4. The control method for a self-moving device as described in claim 2, characterized in that, Determining the transportation operation corresponding to the target object based on the surrounding environment information includes: Based on the surrounding environmental information, determine whether the target object is in a low-ceilinged space; If the surrounding environmental information indicates that the target object is not in a low-lying space, the transportation operation is determined to be the first transportation operation; If the surrounding environmental information indicates that the target object is in a low-lying space, the transportation operation is determined to be the second transportation operation.

5. The control method for a self-moving device as described in claim 4, characterized in that, Controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along a first direction away from the low space; wherein the first direction is determined based on the position of the target object in the low space and the relative position between the self-moving device and the target object.

6. The control method for a self-moving device as described in claim 4, characterized in that, Controlling the self-moving device to perform a first adjustment operation to drag the target object to a non-low-profile space includes: The self-moving device is controlled to perform the first adjustment operation to drag the target object to a non-low space along the second direction; the second direction is the opposite direction of movement when the robotic arm approaches the target object before clamping it.

7. A control device for a self-moving device, characterized in that, The self-moving device is equipped with a robotic arm, and the device includes: The acquisition module is used to acquire information about the surrounding environment of the target object to be captured. The transport operation determination module is used to determine the transport operation corresponding to the target object based on the surrounding environment information. The grasping and transporting module is used to control the robotic arm of the self-moving device to grasp and transport the target object based on the transporting operation.

8. A self-moving device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute a control method for a self-moving device as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the self-moving device, the self-moving device is enabled to perform a control method for a self-moving device as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions, which are executed by a processor to implement a control method for a self-moving device as described in any one of claims 1 to 6.

Images