Robot control method and device, robot, medium and product

Abstract

The invention provides a robot control method and device, a robot, a medium and a product, and relates to the technical field of intelligent robots, the robot is provided with a mechanical arm, and the mechanical arm is used for clamping a target object on an advancing path; in the process that the mechanical arm clamps the target object to execute the target task, in response to the hijacking operation of the user, under the condition that it is determined that the robot is in the suspended state, the robot is controlled to continue to keep the clamping state and suspend execution of the target task, so that the target object is prevented from falling off in the process that the robot is moved, potential safety hazards are avoided, and the user experience is improved. Operation is prevented from being executed in an unstable state, potential damage to the surrounding environment is reduced, and power consumption can be saved; and after it is detected that the robot is in the contact surface state, the robot is controlled to execute the release action to relieve clamping of the mechanical arm on the target object, so that the robot rapidly returns to the normal working process, the influence of task interruption is reduced, and the operation continuity and the correctness of follow-up execution control logic are ensured.

Description

Technical Field

[0001] The present application relates to the field of intelligent robot technology, and in particular to a robot control method, device, robot, medium and product. Background Art

[0002] With the continuous development of intelligent robot technology, cleaning robots are not only limited to performing cleaning tasks on cleaning surfaces, but have also gradually integrated robotic arms, enabling them to perform more complex tasks, such as picking up, moving and arranging debris on cleaning surfaces. This expansion of functions has enabled cleaning robots to play a greater role in improving the cleanliness and automation level of the home environment.

[0003] In related technologies, the robotic arm of a cleaning robot can identify the target object through a sensor system when performing a task. Then, through precise positioning and identification, the robotic arm can clamp the target object and move the target object to a designated position to assist in performing the cleaning task.

[0004] However, during actual use, the cleaning robot may be picked up or moved due to environmental changes or human intervention. Such unforeseen movements may cause the clamped target object to fall or cause damage to the surrounding environment, posing a safety hazard. Moreover, if the robot is picked up or moved while performing a robotic arm clamping task, after the robot is placed back on the cleaning surface, due to the interruption of the task, the robotic arm may enter an abnormal state or the operating logic may be confused, thereby affecting the execution of subsequent tasks and causing the cleaning robot to be unable to resume its work flow normally. Summary of the Invention

[0005] The present application provides a robot control method, device, robot, medium and product, which can release the clamped target object in a timely, automatic and safe manner after the robot is abnormally moved and contacts the surface again, avoiding safety risks caused by continuous clamping or sudden movement of the robot arm, and at the same time avoiding execution logic disorder or target task execution abnormality caused by abnormal conditions, thereby improving the reliability of the robot and user experience.

[0006] In a first aspect, the present application provides a control method for a robot, wherein the robot is provided with a robotic arm, and the robotic arm is used to clamp a target object on a travel path; the method comprises:

[0007] In the process of the robot arm gripping the target object to perform the target task, in response to the user's hijacking operation, if it is determined that the robot is in a suspended state, the robot is controlled to continue to maintain the gripping state and suspend the execution of the target task;

[0008] After detecting that the robot is in a contact surface state, the robot is controlled to perform a release action to release the grip of the robot arm on the target object.

[0009] Therefore, when the robot is being moved by the user and is suspended in mid-air, maintaining the grip prevents the target object from falling during the move, thereby avoiding damage or loss. Furthermore, by pausing the task, the robot can be prevented from performing actions in an unstable state, avoiding potential damage to itself or the surrounding environment. It can also prevent operational logic confusion caused by sensor misreading or position changes, allowing the robot to resume the task after regaining stability, ensuring the integrity and continuity of the task. Furthermore, pausing the task in the suspended state can save power and other resources, extending the robot's operating time.

[0010] Furthermore, by confirming that the robot is in contact with the surface and then executing the release action, the robot arm automatically releases the grip of the target object, which can improve the accuracy and safety of object placement and avoid misplacement or accidental dropping. For example, releasing in a stable contact state can prevent the object from being damaged due to accidental dropping and protect the surrounding environment and equipment.

[0011] In this way, this application can solve the safety hazards and operational abnormalities caused by the existing cleaning robots failing to promptly and reasonably handle the clamping state when being lifted by external forces during the execution of the robotic arm clamping task, thereby greatly improving the operational safety and intelligence level of the robot.

[0012] Optionally, the robot further includes a sensor system, which is used to detect posture information and / or pressure information of the robot. Determining whether the robot is in a suspended state includes:

[0013] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a suspended state.

[0014] The posture information can provide detailed information about the robot's position and posture, and the pressure information can reflect whether the robot is in contact with the ground or other surfaces. Therefore, by detecting the robot's posture information and / or pressure information in real time, it can be determined whether the robot is in a suspended state, enabling the robot to make more accurate judgments and improve the accuracy of detection.

[0015] Optionally, the sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a suspension detection unit, a distance detection unit, a lidar sensor, and a vision sensor; and determining that the robot is in a suspended state based on posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0016] The attitude and acceleration information detected by the inertial measurement unit (IMU) are within the abnormal threshold range;

[0017] The pressure sensor does not detect any pressure information between it and the contact surface;

[0018] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is greater than a preset distance threshold;

[0019] The visual sensor detects that the degree of difference in the change of the environmental characteristics of the contact surface does not meet the preset conditions.

[0020] Therefore, the robot can be determined to be in an airborne state based on the position and / or pressure information detected by at least one of the aforementioned sensors, improving detection flexibility. Furthermore, by combining data from at least one sensor, the robot can more accurately determine its own state, reducing the possibility of misjudgment. Even if a sensor fails or generates abnormal data, other sensors can still provide position or pressure information, enhancing the robot's reliability.

[0021] Optionally, the robot further includes a sensor system, and the method further includes:

[0022] When the robot is in a contact surface state, if the sensor system identifies the presence of a target object and determines that the target object needs to be clamped and moved to perform the target task, the robot arm is controlled to clamp the target object.

[0023] In this way, after the robotic arm releases its grip on the target object, if it is determined that the target object still needs to be clamped and moved to perform the target task, the robotic arm can be controlled to clamp the target object again to continue performing the target task, ensuring the continuity of the target task execution process. After the robotic arm releases its grip on the target object, by re-evaluating the object and environment before performing the next operation, the robot can ensure that it continues to perform the task under appropriate conditions, reduce the possibility of errors and failures, and ensure the logic of task execution.

[0024] Optionally, the sensor system is further configured to detect posture information and / or pressure information of the robot; detecting that the robot is in a state of contacting a surface includes:

[0025] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a state of contacting the surface again.

[0026] Through the posture information detected by the sensor system, the robot can accurately determine its position and direction in space, and based on the pressure information detected by the sensor system, it can accurately determine whether it is in contact with the surface. Therefore, based on the posture information and / or pressure information, it can be accurately determined whether the robot is in a state of contacting the surface. Executing the task when it is again determined that the robot is in a state of contacting the surface can prevent misoperation or damage caused by unexpected movement, avoid the robot running in an unstable state, improve the safety of operation, and reduce errors and deviations in the execution of subsequent tasks, thereby enhancing the reliability of the task.

[0027] Optionally, the sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a hover detection unit, a distance detection unit, a lidar sensor, and a vision sensor; and determining that the robot is in a state of contacting the surface again based on posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0028] The attitude and acceleration information detected by the inertial measurement unit (IMU) are not within the abnormal threshold range;

[0029] The pressure sensor detects the pressure information between the contact surface and the contact surface;

[0030] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is less than or equal to a preset distance threshold;

[0031] The visual sensor detects that the degree of difference in the environmental characteristics of the contact surface changes meets the preset conditions.

[0032] Therefore, the robot can determine whether it has again contacted a surface based on the position and / or pressure information detected by at least one of the aforementioned sensors, improving detection flexibility. Furthermore, by combining data from at least one sensor, the robot can more accurately determine whether it has contacted a surface, reducing the potential error introduced by a single sensor. Even if a sensor fails or generates abnormal data, other sensors can still provide position or pressure information, enhancing the robot's reliability.

[0033] Optionally, the robotic arm is a two-finger gripper structure, and / or the sensor system includes a pressure feedback sensor, and the pressure feedback sensor is disposed on the robotic arm; the method further includes:

[0034] Based on the operating state of the two-finger gripper structure and / or the pressure information detected by the pressure feedback sensor, it is determined whether the target object is in a gripped state.

[0035] In this way, the operating status of the two-finger gripper structure can be used to directly determine whether the gripper has successfully grasped the target object. This direct mechanical feedback can quickly provide information on the gripping status, reducing the reliance on complex sensors and signal processing, making the detection process simpler and more efficient, and reducing the cost of use. The pressure feedback sensor can provide real-time pressure information. The pressure information from the pressure sensor can quickly determine whether the target object is in a gripped state. Accordingly, by combining the operating status of the two-finger gripper structure and the pressure information fed back by the pressure feedback sensor, it is possible to accurately and promptly determine whether the gripping target object is gripped, thereby providing a more comprehensive understanding of the gripping status.

[0036] Optionally, when it is determined that the robot is in a suspended state, controlling the robot to continue to maintain the gripping state and suspend execution of the target task includes:

[0037] When it is determined that the robot is in a suspended state and the duration of the suspended state is greater than a first threshold, controlling the robot to continue to maintain the clamping state and suspend execution of the target task;

[0038] Among them, when the robot suspends the execution of the target task, the robot is controlled to be in a standby state; in the standby state, the motor power of the robot is less than a preset cleaning power threshold.

[0039] In this way, after determining that the robot is in a suspended state, it is also necessary to detect the duration of the suspended state to accurately determine whether the robot is in a hijacked state. After determining that the robot is in a hijacked state, the robot is controlled to continue to maintain the clamping state to prevent the clamped target object from accidentally falling. At the same time, the robot is controlled to pause the execution of the current target task to prevent the robot from continuing to operate in an unstable or abnormal state, avoiding possible erroneous logic execution or potential harm to the user. Accordingly, the robot is also controlled to enter a standby state to reduce the motor power, which helps to save energy consumption. It can not only save energy and extend the working time of the robot, but also reduce the wear of the motor and other mechanical components, thereby extending the service life of the robot. In addition, by entering the standby state, the robot can also quickly resume normal operation after the standby state is released, reducing downtime.

[0040] Optionally, the method further includes:

[0041] When it is determined that the robot is in a suspended state and the duration of the suspended state is less than or equal to a first threshold, the robot is controlled to continue to perform the target task.

[0042] This way, if the robot's suspended state lasts for a short period of time and is within the first safety threshold, the robot can continue executing its target task, avoiding unnecessary interruptions. This improves task completion efficiency and ensures smooth and continuous operation. It also avoids frequent pauses and resumptions of the target task due to brief suspended states, saving time and reducing instability caused by frequent state switching. Furthermore, because the robot can flexibly adjust its operating strategy based on the duration of its suspended state, it can adapt to different working environments and task requirements, improving its adaptability.

[0043] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0044] After detecting that the robot is in a contact surface state, if it is determined that the impact force between the robot and the contact surface is greater than a second threshold, the robot is controlled to perform a release action.

[0045] In this way, performing the release action when the impact force is detected to be greater than the second threshold can prevent the target object from being damaged due to excessive impact force, and avoid damage to the robot or robotic arm caused by excessive impact force, thereby improving the safety of the overall operation. Furthermore, by responding to abnormal impact force in a timely manner and taking appropriate measures, the downtime caused by unexpected situations can be reduced and the overall operational efficiency can be improved.

[0046] Optionally, the method further includes:

[0047] After detecting that the robot is in a contact surface state, and determining that the impact force between the robot and the contact surface is less than or equal to a second threshold, the robot arm is controlled to continue gripping the target object and performing the target task.

[0048] Therefore, by detecting the impact force, the robot arm can ensure safe operation, avoiding damage to equipment or objects caused by excessive impact force. If the impact force is less than or equal to a preset second threshold, the robot can continue to perform the task, avoiding unnecessary interruptions, thereby improving the efficiency of completing the target task and increasing the success rate of target task execution. In this way, users do not need to worry about the impact force between the robot and the contact surface affecting task execution, because the robot can automatically handle these state changes, improving the robot's intelligence.

[0049] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0050] After detecting that the robot is in contact with the surface, the distance between the positions of the robot before and after being hijacked is obtained;

[0051] When it is determined that the distance is smaller than the third threshold, the robot is controlled to perform a release action, and the robot is controlled to continue to perform the target task.

[0052] Therefore, after detecting the contact surface state and evaluating the position change of the robot, determining whether to perform the release action is done through precise distance judgment, which can reduce errors caused by misoperation and ensure the accuracy and reliability of the target task execution. If the position change is less than the preset third threshold, it means that the state of the robot before and after being hijacked has not changed much, and the target task can be safely continued to be performed. At this time, performing the release action can not only ensure that the target object is released at the correct position and reduce operational errors, but also ensure the continuity and efficiency of the target task execution, avoid unnecessary interruptions, and thus improve the efficiency of the target task completion.

[0053] Optionally, the method further includes:

[0054] When it is determined that the distance is greater than the third threshold, the robotic arm is controlled to continue to maintain the clamping state and suspend execution of the target task.

[0055] Therefore, when the distance is confirmed to be greater than the third threshold, the target object can be protected by controlling the continued clamping state to prevent it from being released at an inappropriate time or position. Since the target object is not released, it can further avoid the target object being placed in the wrong position due to position changes, thereby preventing the target task from failing or the target object from being damaged. At the same time, suspending the execution of the target task can also avoid continuing to operate in an unstable or abnormal state, reducing potential safety hazards. In this way, the present application enables the robot to make better decisions, improve autonomy, and enhance the robot's adaptability in different scenarios through intelligent judgment of position changes.

[0056] Optionally, after releasing the grip of the target object by the robotic arm, the method further includes at least one of the following situations:

[0057] Control the robot to perform other tasks;

[0058] Control the robot to be in standby mode;

[0059] Control the robot to grip the target object again to continue performing the target task;

[0060] Generates a prompt message to inform the user that the target task execution is abnormal.

[0061] In this way, after releasing the grip of the robot arm on the target object, automatically switching to other tasks or retrying to grip the target object can reduce downtime and improve overall task efficiency. Entering the standby state helps save energy, especially when the robot does not need to perform other tasks immediately. By generating prompt information and providing status feedback, users can better understand the current status and task progress, so that they can take timely measures, improving operational convenience and thus improving user experience and satisfaction. Therefore, after the robot arm releases the grip of the target object, it can flexibly adjust its operating strategy according to the actual situation, improving its adaptability to different working environments and tasks.

[0062] Optionally, determining whether the robot is in an airborne state includes:

[0063] Obtain behavioral information about the hijacking operation and input the behavioral information into a pre-trained machine learning model to determine whether the robot is in a suspended state;

[0064] Among them, the trained machine learning model is obtained through training with multiple training samples, and the training samples include the user's hijacking operation behavior information and the state information corresponding to each behavior information, and the state information includes the suspended state and the contact surface state.

[0065] In this application, the robot can be determined to be in a suspended state by obtaining behavioral information of the hijacking operation and inputting it into a trained machine learning model. Since the machine learning model can recognize complex behavioral patterns, it is more accurate to determine whether the robot is in a suspended state than the traditional posture information and / or pressure information detection and threshold judgment method. The machine learning model can quickly process the input behavioral information and make judgments, thereby improving the robot's real-time response capability and thus improving processing efficiency. In addition, accurate state recognition through machine learning models can reduce false positives and missed positives, improve the stability of the overall operation, and help the robot take timely measures to prevent potential damage and safety hazards.

[0066] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0067] After detecting that the robot is in a state of contacting the surface, identifying a first position of the robot;

[0068] When it is determined that the first position is different from the second position where the robot was located before being hijacked, the robot is controlled to move to the second position, and after the robot is at the second position, the robot is controlled to perform a releasing action.

[0069] Therefore, by moving the robot back to the position before being hijacked, it can be ensured that the target object can be released at the predetermined location according to the original execution logic, avoiding operational errors or task failures caused by position offset, and ensuring the successful execution of the target task. In this way, through the above-mentioned position correction process, errors caused by misoperation can be reduced, the accuracy and reliability of the target task execution can be improved, and the waste of resources caused by erroneous release can be reduced. In addition, the above-mentioned position correction process is automatically executed by the robot, which improves the convenience of operation.

[0070] In a second aspect, the present application provides a control method for a robot, wherein the robot is provided with a robotic arm, and the robotic arm is used to clamp a target object on a travel path; the method comprises:

[0071] In the process of the robot arm gripping the target object and performing the target task, responding to the user's hijacking operation, obtaining behavior information of the hijacking operation;

[0072] The behavior information is input into a pre-trained machine learning model to determine whether the robot is in a suspended state; the trained machine learning model is trained using multiple training samples, the training samples including the user's hijacking operation behavior information and the state information corresponding to each behavior information, the state information including the suspended state and the contact surface state;

[0073] When it is determined that the robot is in a suspended state, the robot is controlled to continue to maintain the clamping state and suspend the execution of the target task;

[0074] After detecting that the robot is in a contact surface state, the robot is controlled to perform a release action to release the grip of the robot arm on the target object.

[0075] Therefore, compared to traditional posture information and / or pressure information detection and threshold judgment methods to determine whether the robot is in a suspended state, this application uses a trained machine learning model to make the determination, and the corresponding determination result is more accurate. The machine learning model can quickly process the input behavior information and make judgments, improving the robot's real-time response capability and thus improving processing efficiency. In addition, accurate state recognition through machine learning models can reduce false positives and missed positives, improve the stability of overall operation, and help the robot take timely measures to prevent potential damage and safety hazards.

[0076] Furthermore, when the robot is determined to be in a suspended state due to being moved by the user, maintaining the grip can prevent the target object from falling during the move, thereby avoiding damage or loss. Pausing the task can also prevent the robot from performing actions in an unstable state, potentially damaging itself or the surrounding environment. It can also prevent operational logic confusion caused by sensor misreading or position changes, allowing the robot to resume the task after regaining stability, ensuring the integrity and continuity of the task. Furthermore, pausing the task in the suspended state can save power and other resources, extending the robot's operating time.

[0077] Furthermore, by confirming that the robot is in contact with the surface and then executing the release action, the robot arm automatically releases the grip of the target object, which can improve the accuracy and safety of object placement and avoid misplacement or accidental dropping. For example, releasing in a stable contact state can prevent the object from being damaged due to accidental dropping and protect the surrounding environment and equipment.

[0078] In a third aspect, the present application provides a control device for a robot, wherein the robot is provided with a robotic arm, and the robotic arm is used to clamp a target object on a travel path; the device comprises:

[0079] The first determining module is configured to, in response to a user's hijacking operation, control the robot to maintain the gripping state and suspend the execution of the target task when the robot is determined to be in an airborne state during the process of the robot arm gripping the target object and performing the target task;

[0080] The first control module is used to control the robot to perform a release action after detecting that the robot is in a state of contacting a surface, so as to release the grip of the robot arm on the target object.

[0081] In a fourth aspect, the present application provides a control device for a robot, wherein the robot is provided with a robotic arm, and the robotic arm is used to clamp a target object on a travel path; the device comprises:

[0082] an acquisition module, configured to acquire behavior information of a hijacking operation in response to a user's hijacking operation during the process of the robotic arm gripping a target object and performing a target task;

[0083] The second determination module is configured to input the behavior information into a pre-trained machine learning model to determine whether the robot is in a suspended state; the trained machine learning model is obtained by training multiple training samples, the training samples including the user's hijacking operation behavior information and the state information corresponding to each behavior information, the state information including the suspended state and the contact surface state;

[0084] The second control module is used to control the robot to continue to maintain the clamping state and suspend the execution of the target task when it is determined that the robot is in a suspended state;

[0085] The third control module is used to control the robot to perform a release action after detecting that the robot is in a contact surface state, so as to release the grip of the robot arm on the target object.

[0086] In a fifth aspect, the present application provides a robot, which is provided with a robotic arm and a controller, the robotic arm is used to clamp a target object on a travel path, and the controller is used to execute the method as described in any one of the first and second aspects.

[0087] In a sixth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first and second aspects.

[0088] In a seventh aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method as described in any one of the first and second aspects.

[0089] It should be noted that the third to seventh aspects of this application correspond to the technical solutions of the first and second aspects of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar, which will not be repeated here.

[0090] In summary, the present application provides a robot control method, device, robot, medium and product. After detecting that the robot is picked up or moved, that is, in a suspended state, the robot arm is controlled to continue to maintain the clamping state of the target object to prevent the target object from falling during the movement of the robot, avoiding safety hazards. At the same time, the robot suspends the execution of the current target task to avoid performing operations in an unstable state, reduce potential damage to the surrounding environment, and save power consumption. During the movement process, the robot can also continue to detect the state of the robot. When it is detected that the robot contacts the ground again, that is, restores the contact surface state, the robot arm is controlled to perform a release action to release the clamping of the target object. By safely releasing the object after putting it back on the ground, the robot can quickly resume the normal working process, reduce the impact of task interruption, ensure the continuity of operation and the correctness of subsequent execution control logic, for example, it can decide whether to continue an unfinished task or re-plan a new task, effectively avoiding abnormal states and confusion in operation logic. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0092] Figure 1 A schematic diagram of a partial structure of a robot provided in an embodiment of the present application;

[0093] Figure 2 A schematic diagram of a partial structure of another robot provided in an embodiment of the present application;

[0094] Figure 3 A schematic diagram of an application scenario provided in an embodiment of the present application;

[0095] Figure 4 A schematic flow chart of a robot control method provided in an embodiment of the present application;

[0096] Figure 5 A schematic diagram of a scenario in which a robot processes a target object, provided in an embodiment of the present application;

[0097] Figure 6 A schematic flow chart of an optional robot control method provided in an embodiment of the present application;

[0098] Figure 7 A schematic flow chart of another robot control method provided in an embodiment of the present application;

[0099] Figure 8 A schematic structural diagram of a robot control device provided in an embodiment of the present application;

[0100] Figure 9 A schematic structural diagram of another robot control device provided in an embodiment of the present application;

[0101] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0102] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0103] To facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. For example, the first device and the second device are merely used to distinguish between different devices and do not limit their order. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean that they are different.

[0104] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0105] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or plural.

[0106] When performing tasks, the cleaning robot's robotic arm can identify the target object through the sensor system. Then, through precise positioning and identification, the robotic arm can clamp the target object and move the target object to the designated position to assist in performing cleaning tasks, thereby improving the cleanliness and automation level of the home environment.

[0107] However, during actual use, the cleaning robot may be picked up or moved due to environmental changes or human intervention. For example, a child may pick up the cleaning robot out of curiosity, or the user may temporarily move the cleaning robot. At this time, the cleaning robot body may be performing a robotic arm clamping task. This unforeseen action may cause the clamped target object to fall or cause damage to the surrounding environment, posing a safety hazard.

[0108] For example, since users or children cannot predict the movements of the robotic arm, there is a safety risk of the clamped object being suddenly released or maintained. Moreover, if the robot is picked up or moved while performing the robotic arm clamping task, after the robot is placed back on the cleaning surface, due to the interruption of the task, the robotic arm may enter an abnormal state or the operating logic may be confused, which in turn affects the execution of subsequent tasks and causes the cleaning robot to be unable to resume its work flow normally.

[0109] It is understandable that in related technologies, cleaning robots focus more on walking on the cleaning surface, obstacle avoidance and picking up functions, and lack a processing mechanism that can intelligently and safely release the clamped objects after the cleaning robot is in a clamping state and lifted by external force after landing again, so as to reduce the risk of misoperation during use and improve the stability of the robot and user experience.

[0110] In response to the above problems, the present application provides a robot control method. After detecting that the robot is picked up or moved, that is, in a suspended state, the robot arm is controlled to continue to maintain a clamping state on the target object to prevent the target object from falling during the movement of the robot, thereby avoiding safety hazards. At the same time, the robot suspends the execution of the current target task to avoid performing operations in an unstable state, reduce potential damage to the surrounding environment, and save power consumption. During the movement process, the robot can also continue to detect the state of the robot. When it is detected that the robot has re-contacted the ground, that is, restored to the contact surface state, the robot arm is controlled to perform a release action to release the clamping of the target object. By safely releasing the object after putting it back on the ground, the robot can quickly resume normal working procedures, reduce the impact of task interruption, ensure the continuity of operation and the correctness of subsequent execution control logic, for example, it can decide whether to continue an unfinished task or re-plan a new task, effectively avoiding abnormal states and confusion in operating logic.

[0111] It should be noted that the floor can also be replaced by other object surfaces, such as carpet surface, platform surface, etc. When the robot cleans the cleaning area, the floor can be understood as the cleaning surface. The description of the floor in the following embodiments can also be replaced by other contact surfaces, which will not be repeated here.

[0112] Optionally, the robot control method provided in this application is applied to a robot, exemplarily, Figure 1 A schematic diagram of a partial structure of a robot provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the robot 100 is provided with a robotic arm 101 and a controller 102. The robotic arm 101 is used to clamp the target object on the travel path; the controller 102 is used to execute any embodiment corresponding to the robot control method provided in the embodiments of the present application.

[0113] Optional, Figure 2 A schematic diagram of a partial structure of another robot provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the robot 100 has Figure 1 In addition to the structure shown, the robot 100 further includes a sensor system 103 , which is used to detect posture information and / or pressure information of the robot 100 .

[0114] Among them, the posture information may include the position information and posture information of the robot. The embodiment of the present application does not limit the specific content of the posture information. It can estimate the posture of the robot and then determine whether the robot is in a suspended state or in contact with the surface.

[0115] It should be noted that the posture information is at least used to detect whether the robot is in an off-ground state (suspended state).

[0116] It is understandable that the sensor system 103 includes at least one type of sensor. Therefore, the sensor system 103 can fuse data from different sensors to improve the accuracy and reliability of pose estimation.

[0117] Optionally, the sensor system 103 includes at least one of an inertial measurement unit (IMU), a pressure sensor, a suspension detection unit, a distance detection unit, a lidar sensor, and a visual sensor.

[0118] Among them, the IMU consists of an accelerometer and a gyroscope, which is used to measure the robot's linear acceleration and angular velocity. The linear acceleration and angular velocity can be used to calculate the robot's posture such as tilt angle and motion trajectory.

[0119] The pressure sensor can be used to detect pressure changes of the robot on different surfaces or environments, that is, to determine whether the robot is in contact with the ground or other objects. Optionally, the pressure sensor can be a ground pressure switch.

[0120] The suspension detection unit is used to identify whether the robot is in a suspended state. Optionally, the suspension detection unit can be a suspension detection switch.

[0121] The distance detection unit is used to measure the distance between the robot and surrounding objects. Optionally, the distance detection unit may include an optical ranging sensor, an infrared ranging sensor, a Time of Flight (TOF) sensor, etc. The TOF sensor can calculate the distance by measuring the time it takes for a light pulse to travel from the sensor to the object and then back.

[0122] LiDAR sensors generate a three-dimensional map of the environment by emitting lasers and measuring the reflection time, which is used to determine the robot's location and surrounding environment.

[0123] Vision sensors capture images or videos through cameras and are used to identify environmental features of contact surfaces, such as color, texture, lighting changes, distance or depth information.

[0124] Therefore, in the present application, it is possible to determine whether the robot is in a suspended state based on the sensor information detected by at least one of the above sensors. Different sensor combinations can be configured according to specific application requirements to adapt to specific operating environments and task requirements, thereby improving the accuracy and flexibility of detection.

[0125] Optionally, the robotic arm 101 is a two-finger gripper structure, and / or the sensor system 103 includes a pressure feedback sensor, and the pressure feedback sensor is disposed on the robotic arm 101 .

[0126] The two-finger gripper is an end effector used to grasp and manipulate objects. It consists of two movable "fingers" that can be opened and closed by a controller to pick up, place, and carry objects.

[0127] It is understandable that the design of the two-finger gripper is simple and efficient, suitable for handling objects of various shapes and sizes, and the two-finger gripper structure generally has high flexibility and adaptability, and can handle objects of different shapes and materials. It adapts to different grasping tasks by adjusting the distance between the "fingers".

[0128] The pressure feedback sensor is installed on the two-finger gripper structure to detect and measure the pressure applied by the two-finger gripper structure when grasping the target object, and then detect whether the target object falls off through the pressure information detected in real time by the pressure feedback sensor.

[0129] For example, Figure 3 A schematic diagram of an application scenario provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, this application scenario can be applied to a home scenario. Taking the robot 100 as a sweeping robot as an example, the sweeping robot performs a cleaning task in the bedroom area. At this time, the robotic arm of the sweeping robot is in an extended state, and clamps the target object and moves it to move the target object to the target position. In the process of moving the target object, the user moves the sweeping robot to the bedroom area.

[0130] In response to the user's operation of moving from the living room area to the bedroom area, the sweeping robot can control its robotic arm to continue to be in a clamping state to prevent the target object from falling abnormally and causing safety hazards. At the same time, the control logic of the sweeping robot is controlled to suspend the execution of the cleaning task in the living room area to prevent mechanical damage or sensor misreading caused by accidental startup of the sweeping robot during the moving process. Suspending the cleaning task can also prevent navigation and positioning errors caused by sudden changes in position and direction, resulting in abnormal states or confusion in operation logic.

[0131] Furthermore, after detecting that the robot vacuum is located on the cleaning surface of the bedroom area, the robot vacuum's robotic arm can be controlled to perform a release action to place the target object down. The robot vacuum can then replan its cleaning path based on its current location to clean the bedroom area, or it can automatically resume its previous cleaning task, continue moving the target object, and return to the bedroom area to perform the cleaning task. The embodiments of the present application do not specifically limit the operations performed by the robot after performing the release action.

[0132] It should be noted that the embodiments of the present application do not specifically limit the application scenarios of the robot control method. In different application scenarios, the robot performs different target tasks and clamps different target objects.

[0133] It should also be noted that the embodiment of the present application does not specifically limit the type of robot 100. Optionally, the robot 100 can be an intelligent robot with autonomous movement capabilities, such as a cleaning robot, a service robot, or a handling robot.

[0134] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0135] Figure 4 A schematic diagram of a flow chart of a robot control method provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the robot control method is applied to Figure 1and Figure 2 The robot shown; the control method of the robot comprises the following steps:

[0136] S401. In the process of the robot arm gripping the target object to perform the target task, in response to the user's hijacking operation, if it is determined that the robot is in a suspended state, the robot is controlled to continue to maintain the gripping state and suspend the execution of the target task.

[0137] It should be noted that the target object on the path of the robot arm can be marked during the previous mapping process, or it can be identified by the visual sensor during the execution of the target task. The present embodiment does not specifically limit the method for determining the target object to be clamped. Optionally, after identifying the target object, the robot can be controlled to adjust its body posture to facilitate gripping the target object.

[0138] It can be understood that the robotic arm clamps the target object on the travel path, and can clamp the target object during the cleaning process, and after cleaning the position corresponding to the target object, return the target object to its original position, or it can clamp the target object and move it to the target position for storage. The embodiment of the present application does not specifically limit the target task performed by clamping the target object on the travel path. The above is only an example. Different application scenarios or different types of robots have different target tasks for clamping the target object.

[0139] Optionally, the target task may be a cleaning task, a transporting task, an arranging task, etc., and the execution of the target task requires the robotic arm to perform a task of clamping the target object.

[0140] Optionally, in response to the user's hijacking operation, the hijacking operation may include the user directly lifting the robot, pausing the robot to perform the target task based on the application (Application, APP) corresponding to the terminal device, and then lifting the robot, or pausing the robot to perform the target task based on a key operation and then lifting the robot. The embodiment of the present application does not specifically limit the type of hijacking operation.

[0141] For example, the robot uses a robotic arm to clamp the target object. During the execution of the target task, the robot detects that it is in a suspended state through built-in sensor systems such as IMU and pressure sensors. This indicates that the robot is lifted off the ground and may be in the process of being moved by the user. At this time, the robot controls the robotic arm to continue to maintain the clamping state and not release the target object to prevent the target object from falling or being damaged during the moving process. The robot also controls the robot to pause the current target task execution to stop all task-related actions of the robot, prevent the robot from continuing to operate in an unstable state, and reduce the risk of accidents.

[0142] S402: After detecting that the robot is in a state of contacting the surface, control the robot to perform a release action to release the grip of the robot arm on the target object.

[0143] For example, when the robot is being moved, it can use its sensor system such as pressure sensors, contact sensors or visual sensors to detect whether it is in contact with the surface. After confirming that the robot is in contact with the surface, it controls the robotic arm to perform a release action to release the grip of the target object and ensure the safety of the target object, such as opening the gripper or other grasping mechanism to put down the target object.

[0144] Optionally, taking a cleaning robot as an example, the cleaning robot being in a surface contact state refers to a state in which the cleaning robot is in contact with a cleaning surface.

[0145] Therefore, when the robot is being moved by the user and is suspended in mid-air, maintaining the grip prevents the target object from falling during the move, thereby avoiding damage or loss. Furthermore, by pausing the task, the robot can be prevented from performing actions in an unstable state, avoiding potential damage to itself or the surrounding environment. It can also prevent operational logic confusion caused by sensor misreading or position changes, allowing the robot to resume the task after regaining stability, ensuring the integrity and continuity of the task. Furthermore, pausing the task in the suspended state can save power and other resources, extending the robot's operating time.

[0146] Furthermore, by confirming that the robot is in contact with the surface and then executing the release action, the robot arm automatically releases the grip of the target object, which can improve the accuracy and safety of object placement and avoid misplacement or accidental dropping. For example, releasing in a stable contact state can prevent the object from being damaged due to accidental dropping and protect the surrounding environment and equipment.

[0147] In this way, this application can solve the safety hazards and operational abnormalities caused by the existing cleaning robots failing to promptly and reasonably handle the clamping state when being lifted by external forces during the execution of the robotic arm clamping task, thereby greatly improving the operational safety and intelligence level of the robot.

[0148] Optionally, determining whether the robot is in an airborne state includes:

[0149] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a suspended state.

[0150] For example, the robot continuously collects the robot's posture information based on the sensor system, including position information, tilt angle, acceleration and other data. It can also continuously collect pressure information, and then identify whether the robot is in a contact surface state or a suspended state by analyzing this data.

[0151] Among them, certain thresholds or conditions can be set, such as acceleration changes, tilt angles, etc. that are greater than the thresholds. When it is detected that these conditions or thresholds are met, it is determined that the robot is in a suspended state. The embodiments of the present application do not limit the specific method of determining whether the robot is in a suspended state based on posture information and / or pressure information. The above is only an example.

[0152] The posture information can provide detailed information about the robot's position and posture, and the pressure information can reflect whether the robot is in contact with the ground or other surfaces. Therefore, by detecting the robot's posture information and / or pressure information in real time, it can be determined whether the robot is in a suspended state, enabling the robot to make more accurate judgments and improve the accuracy of detection.

[0153] Optionally, determining that the robot is in a suspended state based on the posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0154] The attitude and acceleration information detected by the inertial measurement unit (IMU) are within the abnormal threshold range;

[0155] The pressure sensor does not detect any pressure information between it and the contact surface;

[0156] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is greater than a preset distance threshold;

[0157] The visual sensor detects that the degree of difference in the change of the environmental characteristics of the contact surface does not meet the preset conditions.

[0158] In an embodiment of the present application, the abnormal threshold interval is a pre-set posture and acceleration threshold corresponding to determining that the robot is in a suspended state. For example, it may include an acceleration threshold, a tilt angle threshold, etc. When the posture and acceleration information exceeds the threshold range of normal operation, that is, it is in the abnormal threshold interval, it indicates that the robot is lifted or tilted and is in a suspended state.

[0159] The pressure sensor is used to detect the pressure between the robot and the ground or other contact surface. If the sensor does not detect pressure, it indicates that the robot may have left the contact surface.

[0160] The hover detection unit, distance detection unit, and lidar sensor can all measure the distance between the robot and the contact surface. If the detected distance is greater than a preset threshold, it indicates that the robot may be lifted.

[0161] The visual sensor can capture environmental images and detect changes in environmental characteristics through image processing technology. If the changes in environmental characteristics do not meet the preset conditions, it indicates that the robot has been moved to a different environment or is in a suspended state.

[0162] Therefore, the robot can be determined to be in an airborne state based on the position and / or pressure information detected by at least one of the aforementioned sensors, improving detection flexibility. Furthermore, by combining data from at least one sensor, the robot can more accurately determine its own state, reducing the possibility of misjudgment. Even if a sensor fails or generates abnormal data, other sensors can still provide position or pressure information, enhancing the robot's reliability.

[0163] Optionally, the method further includes:

[0164] When the robot is in a contact surface state, if the sensor system identifies the presence of a target object and determines that the target object needs to be clamped and moved to perform the target task, the robot arm is controlled to clamp the target object.

[0165] For example, Figure 5 A schematic diagram of a scenario in which a robot processes a target object is provided in an embodiment of the present application, such as Figure 5 As shown, take the target task as the sorting task as an example, that is, moving the target object from the first position to the second position, as shown in Figure 5 As shown in Figure A, when the robot arm is moving from the first position to the second position while holding the target object, in response to the user's hijacking operation, if it is determined that the robot is in a suspended state, the robot arm is controlled to continue holding the target object and suspend the execution of the sorting task. Further, after detecting that the robot is in contact with the ground, the robot is controlled to perform a release action, as shown in Figure 1. Figure 5 As shown in B, the grip of the target object by the robotic arm is released. After the target object is placed on the ground, if it is determined that the target object needs to be gripped to move to the second position, the robotic arm is controlled to grip the target object, as shown in FIG. Figure 5 As shown in C, the robot arm clamps the target object and moves to the second position. After reaching the second position, the robot is controlled to perform a release action, as shown in FIG. Figure 5 As shown in D, the target object is placed at a second position.

[0166] It can be understood that the sensor system can provide precise position information of the target object, so that the robot can accurately grasp and move the target object.

[0167] In this way, after the robotic arm releases its grip on the target object, if it is determined that the target object still needs to be clamped and moved to perform the target task, the robotic arm can be controlled to clamp the target object again to continue performing the target task, ensuring the continuity of the target task execution process. After the robotic arm releases its grip on the target object, by re-evaluating the object and environment before performing the next operation, the robot can ensure that it continues to perform the task under appropriate conditions, reduce the possibility of errors and failures, and ensure the logic of task execution.

[0168] Optionally, the sensor system is further configured to detect posture information and / or pressure information of the robot; detecting that the robot is in a state of contacting a surface includes:

[0169] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a state of contacting the surface again.

[0170] For example, Figure 5 As shown in Figure A, when the robot is in a contact surface state, that is, in contact with the ground, its robotic arm clamps the target object and moves from a first position to a second position. Furthermore, in response to the user's hijacking operation, the robot is in a suspended state. At this time, the robotic arm is controlled to continue clamping the target object and suspend the execution of the sorting task. Furthermore, after detecting that the robot is in a contact surface state again, that is, after contacting the ground again based on the posture information and / or pressure information detected by the sensor system, the robot can be controlled to perform a release action.

[0171] Through the posture information detected by the sensor system, the robot can accurately determine its position and direction in space, and based on the pressure information detected by the sensor system, it can accurately determine whether it is in contact with the surface. Therefore, based on the posture information and / or pressure information, it can be accurately determined whether the robot is in a state of contacting the surface. Executing the task when it is again determined that the robot is in a state of contacting the surface can prevent misoperation or damage caused by unexpected movement, avoid the robot running in an unstable state, improve the safety of operation, and reduce errors and deviations in the execution of subsequent tasks, thereby enhancing the reliability of the task.

[0172] Optionally, determining that the robot is in contact with the surface again based on the posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0173] The attitude and acceleration information detected by the inertial measurement unit (IMU) are not within the abnormal threshold range;

[0174] The pressure sensor detects the pressure information between the contact surface and the contact surface;

[0175] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is less than or equal to a preset distance threshold;

[0176] The visual sensor detects that the degree of difference in the environmental characteristics of the contact surface changes meets the preset conditions.

[0177] It should be noted that the setting of the abnormal threshold interval, the preset distance threshold and the preset conditions can refer to the description of the above embodiment and will not be repeated here.

[0178] It is understood that the IMU provides the robot's posture and acceleration information. If the posture and acceleration information are not within the abnormal threshold range, it indicates that the robot is in contact with the surface. The pressure sensor can detect the pressure between the robot and the contact surface. If pressure is detected, it indicates that the robot is in contact with the surface. The suspension detection unit, distance detection unit, and lidar sensor are used to measure the distance between the robot and the contact surface. If the distance is less than or equal to the preset distance threshold, it indicates that the robot is in contact with the surface. The visual sensor can detect changes in the environmental characteristics of the contact surface through image processing. If the degree of change meets the preset conditions, it can be inferred that the robot is in contact with the surface.

[0179] Therefore, the robot can determine whether it has again contacted a surface based on the position and / or pressure information detected by at least one of the aforementioned sensors, improving detection flexibility. Furthermore, by combining data from at least one sensor, the robot can more accurately determine whether it has contacted a surface, reducing the potential error introduced by a single sensor. Even if a sensor fails or generates abnormal data, other sensors can still provide position or pressure information, enhancing the robot's reliability.

[0180] Optionally, the method further includes:

[0181] Based on the operating state of the two-finger gripper structure and / or the pressure information detected by the pressure feedback sensor, it is determined whether the target object is in a gripped state.

[0182] Among them, the operating state can be used to characterize the degree of opening and closing and the force applied, which can cover all states of the gripper when performing the target task, including grasping, holding, moving and releasing objects, etc. The embodiment of the present application does not specifically limit the operating state of the two-finger gripper structure, which can be determined based on the actual application scenario.

[0183] In the present application, the state of the two-finger gripper structure can be determined by judging the degree of opening and closing of the two-finger gripper structure and the force applied, thereby determining whether the target object is clamped. It is also possible to determine whether the target object is clamped by analyzing the pressure information fed back by the pressure feedback sensor. Furthermore, the operating state of the two-finger gripper structure and the pressure information from the pressure sensor can be combined to more accurately determine whether the target object is in a clamped state.

[0184] In this way, the operating status of the two-finger gripper structure can be used to directly determine whether the gripper has successfully grasped the target object. This direct mechanical feedback can quickly provide information on the gripping status, reducing the reliance on complex sensors and signal processing, making the detection process simpler and more efficient, and reducing the cost of use. The pressure feedback sensor can provide real-time pressure information. The pressure information from the pressure sensor can quickly determine whether the target object is in a gripped state. Accordingly, by combining the operating status of the two-finger gripper structure and the pressure information fed back by the pressure feedback sensor, it is possible to accurately and promptly determine whether the gripping target object is gripped, thereby providing a more comprehensive understanding of the gripping status.

[0185] Optionally, when it is determined that the robot is in a suspended state, controlling the robot to continue to maintain the gripping state and suspend execution of the target task includes:

[0186] When it is determined that the robot is in a suspended state and the duration of the suspended state is greater than a first threshold, controlling the robot to continue to maintain the clamping state and suspend execution of the target task;

[0187] Among them, when the robot suspends the execution of the target task, the robot is controlled to be in a standby state; in the standby state, the motor power of the robot is less than a preset cleaning power threshold.

[0188] In the embodiment of the present application, in standby mode, the robot can retain its current working status and data, but is in a low-power state, that is, the robot's motor power is less than a preset cleaning power threshold. At the same time, in standby mode, the robot can also maintain the ability to quickly restore to a full-function state.

[0189] It should be noted that the sensor system not only detects whether the robot is in a suspended state, but also detects the duration of the suspended state. If the duration of the suspended state exceeds a preset first threshold, it can be accurately determined that the robot is in a hijacked state or has been manually lifted.

[0190] The embodiment of the present application does not specifically limit the setting of the first threshold, which can be set based on the requirements of actual application scenarios.

[0191] After confirming that the robot has been in the suspended state for a period exceeding a first threshold, it can be accurately determined that the robot has been hijacked. Therefore, the robot can be controlled to maintain the current gripping state to ensure that the gripped target object does not fall or be damaged due to accidental release. At the same time, the currently executing target task must be paused to avoid erroneous logic or accidental injury to the user caused by continued operation in an unstable state. In addition, after pausing the currently executing target task, the robot can enter a standby state and control the robot's motor power to be reduced to less than a preset cleaning power threshold to save energy and reduce unnecessary wear.

[0192] Optionally, taking the robot as a cleaning robot as an example, when the robot is in standby mode, the roller brush assembly, water pump assembly, motor, fan and other components can be controlled to stop rotating to reduce energy consumption.

[0193] In this way, after determining that the robot is in a suspended state, it is also necessary to detect the duration of the suspended state to accurately determine whether the robot is in a hijacked state. After determining that the robot is in a hijacked state, the robot is controlled to continue to maintain the clamping state to prevent the clamped target object from accidentally falling. At the same time, the robot is controlled to pause the execution of the current target task to prevent the robot from continuing to operate in an unstable or abnormal state, avoiding possible erroneous logic execution or potential harm to the user. Accordingly, the robot is also controlled to enter a standby state to reduce the motor power, which helps to save energy consumption. It can not only save energy and extend the working time of the robot, but also reduce the wear of the motor and other mechanical components, thereby extending the service life of the robot. In addition, by entering the standby state, the robot can also quickly resume normal operation after the standby state is released, reducing downtime.

[0194] Optionally, the method further includes:

[0195] When it is determined that the robot is in a suspended state and the duration of the suspended state is less than or equal to a first threshold, the robot is controlled to continue to perform the target task.

[0196] It should be noted that if the duration of the robot's suspension state is less than or equal to the preset first threshold, it indicates a short state change, which can be regarded as instantaneous jitter. At this time, the robot can be controlled to continue to perform the target task.

[0197] Optionally, taking the robot as a cleaning robot as an example, when the cleaning robot is in a short state, the internal components of the cleaning robot do not stop rotating.

[0198] This way, if the robot's suspended state lasts for a short period of time and is within the first safety threshold, the robot can continue executing its target task, avoiding unnecessary interruptions. This improves task completion efficiency and ensures smooth and continuous operation. It also avoids frequent pauses and resumptions of the target task due to brief suspended states, saving time and reducing instability caused by frequent state switching. Furthermore, because the robot can flexibly adjust its operating strategy based on the duration of its suspended state, it can adapt to different working environments and task requirements, improving its adaptability.

[0199] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0200] After detecting that the robot is in a contact surface state, if it is determined that the impact force between the robot and the contact surface is greater than a second threshold, the robot is controlled to perform a release action.

[0201] In this embodiment of the present application, a second threshold can be set in advance to determine whether the impact force is within a safe range. If the detected impact force is less than or equal to the second threshold, it indicates that the robot is in safe contact with the surface, which can be interpreted as the user placing the robot steadily on the contact surface. If the detected impact force is greater than the second threshold, it indicates that the impact force is too great, which can be interpreted as an abnormal landing. The impact force refers to the instantaneous force generated by the robot when it contacts the surface due to speed or other factors.

[0202] For example, after detecting that the robot is in a contact surface state and confirming that the impact force is greater than a second threshold at this time, the robotic arm is controlled to perform a release action and automatically release the grip on the target object to avoid potential damage to the target object, the robot and the robotic arm due to excessive impact force.

[0203] In this way, performing the release action when the impact force is detected to be greater than the second threshold can prevent the target object from being damaged due to excessive impact force, and avoid damage to the robot or robotic arm caused by excessive impact force, thereby improving the safety of the overall operation. Furthermore, by responding to abnormal impact force in a timely manner and taking appropriate measures, the downtime caused by unexpected situations can be reduced and the overall operational efficiency can be improved.

[0204] Optionally, the method further includes:

[0205] After detecting that the robot is in a contact surface state, and determining that the impact force between the robot and the contact surface is less than or equal to a second threshold, the robot arm is controlled to continue gripping the target object and performing the target task.

[0206] For example, after detecting that the robot is in contact with the surface and confirming that the impact force is less than or equal to the second threshold at this time, the robotic arm is controlled to continue clamping the target object and performing the target task, thereby ensuring the continuity and stability of the execution of the target task.

[0207] Therefore, by detecting the impact force, the robot arm can ensure safe operation, avoiding damage to equipment or objects caused by excessive impact force. If the impact force is less than or equal to a preset second threshold, the robot can continue to perform the task, avoiding unnecessary interruptions, thereby improving the efficiency of completing the target task and increasing the success rate of target task execution. In this way, users do not need to worry about the impact force between the robot and the contact surface affecting task execution, because the robot can automatically handle these state changes, improving the robot's intelligence.

[0208] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0209] After detecting that the robot is in contact with the surface, the distance between the positions of the robot before and after being hijacked is obtained;

[0210] When it is determined that the distance is smaller than the third threshold, the robot is controlled to perform a release action, and the robot is controlled to continue to perform the target task.

[0211] In an embodiment of the present application, the third threshold is a preset distance value, which is used to determine the distance the robot's position changes before and after being hijacked. If the distance between the robot's positions before and after being hijacked is less than the third threshold, it means that the robot has been moved a short distance, which may be unintentional or slight interference. At this time, the release action can be executed and the task can continue.

[0212] Among them, the third threshold can be set based on the actual application scenario requirements, and the embodiment of the present application does not specifically limit the size of the third threshold.

[0213] Therefore, after detecting the contact surface state and evaluating the position change of the robot, determining whether to perform the release action is done through precise distance judgment, which can reduce errors caused by misoperation and ensure the accuracy and reliability of the target task execution. If the position change is less than the preset third threshold, it means that the state of the robot before and after being hijacked has not changed much, and the target task can be safely continued to be performed. At this time, performing the release action can not only ensure that the target object is released at the correct position and reduce operational errors, but also ensure the continuity and efficiency of the target task execution, avoid unnecessary interruptions, and thus improve the efficiency of the target task completion.

[0214] Optionally, the method further includes:

[0215] When it is determined that the distance is greater than the third threshold, the robotic arm is controlled to continue to maintain the clamping state and suspend execution of the target task.

[0216] It should be noted that if the distance between the robot's positions before and after being hijacked is greater than the third threshold, it means that the robot has been moved a long distance. At this time, the clamped target object will not be released to avoid placing the target object in the wrong position. Accordingly, the control also suspends the currently executing target task to prevent the erroneous execution logic that may be caused by continuing the operation in an uncertain state.

[0217] Therefore, when the distance is confirmed to be greater than the third threshold, the target object can be protected by controlling the continued clamping state to prevent it from being released at an inappropriate time or position. Since the target object is not released, it can further avoid the target object being placed in the wrong position due to position changes, thereby preventing the target task from failing or the target object from being damaged. At the same time, suspending the execution of the target task can also avoid continuing to operate in an unstable or abnormal state, reducing potential safety hazards. In this way, the present application enables the robot to make better decisions, improve autonomy, and enhance the robot's adaptability in different scenarios through intelligent judgment of position changes.

[0218] Optionally, after releasing the grip of the target object by the robotic arm, the method further includes at least one of the following situations:

[0219] Control the robot to perform other tasks;

[0220] Control the robot to be in standby mode;

[0221] Control the robot to grip the target object again to continue performing the target task;

[0222] Generates a prompt message to inform the user that the target task execution is abnormal.

[0223] It is understandable that after releasing the grip of the robotic arm on the target object, the robot needs to decide the next operation, which can be determined based on the preset task execution logic or real-time application scenario requirements. The embodiments of the present application do not make specific limitations on this.

[0224] In some embodiments, after the robotic arm releases its grip on the target object, if the current target task has been completed or requires waiting, the robot can be scheduled to perform other predetermined work tasks to improve the robot's utilization and work efficiency. The scenarios that require waiting can include multiple scenarios, and the embodiments of the present application do not limit the specific scenarios, such as the scenario where the priority of the cleaning task corresponding to the area after the hijacking is greater than the priority of the target task.

[0225] In other embodiments, after releasing the grip of the robotic arm on the target object, if it is determined that there are no other tasks that need to be executed immediately or an abnormality occurs in the execution logic, the robot can enter a standby state to reduce energy consumption and wait for further instructions or task arrangements from the user.

[0226] In some other embodiments, after the robotic arm releases its grip on the target object, the robot can be controlled to grip the target object again to continue executing the unfinished target task, wherein the robot can identify the target object again and replan the walking path.

[0227] Optionally, after releasing the grip of the robotic arm on the target object, the original cleaning path can be directly restored to continue performing the target task.

[0228] Optionally, after releasing the grip of the target object, if an exception is detected during task execution, a prompt message can be generated to alert the user of the possible problem or exception, helping the user understand the current status and take timely measures to ensure the smooth progress of the target task. Optionally, the robot can also store the record of the failed processing process corresponding to the grip of the target object in the exception handling process file for subsequent review.

[0229] In this way, after releasing the grip of the robot arm on the target object, automatically switching to other tasks or retrying to grip the target object can reduce downtime and improve overall task efficiency. Entering the standby state helps save energy, especially when the robot does not need to perform other tasks immediately. By generating prompt information and providing status feedback, users can better understand the current status and task progress, so that they can take timely measures, improving operational convenience and thus improving user experience and satisfaction. Therefore, after the robot arm releases the grip of the target object, it can flexibly adjust its operating strategy according to the actual situation, improving its adaptability to different working environments and tasks.

[0230] Optionally, determining whether the robot is in an airborne state includes:

[0231] Obtain behavioral information about the hijacking operation and input the behavioral information into a pre-trained machine learning model to determine whether the robot is in a suspended state;

[0232] Among them, the trained machine learning model is obtained through training with multiple training samples, and the training samples include the user's hijacking operation behavior information and the state information corresponding to each behavior information, and the state information includes the suspended state and the contact surface state.

[0233] Optionally, after determining based on a machine learning model that the robot is in a suspended state after a hijacking operation, the robot can also dynamically optimize the execution logic of the target task in the clamped state based on the output of the machine learning model, such as controlling the suspension of the target task or whether to release the target object, to reduce the occurrence of high-risk scenarios. Such high-risk scenarios include accidental injury to the user, accidental damage to the target object, and robot damage.

[0234] In the embodiments of the present application, the machine learning model is a machine learning model based on deep learning, which may include models such as convolutional neural networks, recurrent neural networks, long short-term memory networks, and autoencoders. The embodiments of the present application do not specifically limit the type of machine learning model. The machine learning model is a behavior recognition model for identifying user hijacking operations.

[0235] Optionally, the training process of the machine learning model includes: obtaining multiple training samples, inputting the multiple training samples into the initial machine learning model for training, and obtaining a trained machine learning model, the training samples include the user's hijacking operation behavior information and the state information corresponding to each behavior information, the state information includes the suspended state and the contact surface state.

[0236] Among them, the machine learning model can adapt to new behavior patterns and environmental changes through continuous updating and training to improve the model's adaptability. In addition, by learning a large amount of sample data, the machine learning model can more accurately distinguish between the suspended state and the contact surface state, thereby improving the accuracy of the model's prediction and reducing misjudgments.

[0237] For example, while the robotic arm is gripping a target object and performing a cleaning task, in response to a user's gripping operation, the sensor system collects behavioral information related to the gripping operation. This information is then fed into a pre-trained machine learning model to generate an output indicating that the robot is in a suspended state. Furthermore, if the robot is determined to be in a suspended state, the robot is controlled to maintain the grip and suspend the cleaning task. Upon detecting that the robot is in contact with a surface, the robot is controlled to perform a release action to release the grip of the robotic arm on the target object.

[0238] Optionally, since the sensor system collects behavioral information related to the hijacking operation in real time, detecting that the robot is in a contact surface state includes: inputting the behavioral information related to the hijacking operation collected by the sensor system into a pre-trained machine learning model to obtain an output result that the robot is in a contact surface state.

[0239] It is understandable that other methods can also be used to determine whether the robot is in the contact surface state, such as directly determining whether the robot is in the contact surface state based on the robot's posture information and / or pressure information detected by the sensor system. The embodiments of the present application do not specifically limit this.

[0240] In this application, the robot can be determined to be in a suspended state by obtaining behavioral information of the hijacking operation and inputting it into a trained machine learning model. Since the machine learning model can recognize complex behavioral patterns, it is more accurate to determine whether the robot is in a suspended state than the traditional posture information and / or pressure information detection and threshold judgment method. The machine learning model can quickly process the input behavioral information and make judgments, thereby improving the robot's real-time response capability and thus improving processing efficiency. In addition, accurate state recognition through machine learning models can reduce false positives and missed positives, improve the stability of the overall operation, and help the robot take timely measures to prevent potential damage and safety hazards.

[0241] Optionally, after detecting that the robot is in contact with the surface, controlling the robot to perform a release action includes:

[0242] After detecting that the robot is in a state of contacting the surface, identifying a first position of the robot;

[0243] When it is determined that the first position is different from the second position where the robot was located before being hijacked, the robot is controlled to move to the second position, and after the robot is at the second position, the robot is controlled to perform a releasing action.

[0244] For example, after detecting that the robot is in a state of contacting a surface, it indicates that the robot can perform a release action. At this time, the current first position of the robot is identified and recorded, and the current first position is compared with the second position before the robot was hijacked. If the two positions are different, it indicates that the robot has undergone position displacement during the hijacking process. Furthermore, the robot can be controlled to move back to the second position, that is, the position before the robot was hijacked, and then the robot can be controlled to perform a release action to place the target object in the predetermined correct position.

[0245] Among them, if the second position is the target position where the target object needs to be placed during the robot's execution of the target task, then after the robot moves to the second position, the robot is immediately controlled to perform a release action to place the target object at the second position; if the second position is any position passed by the robot during the execution of the target task, and is not the target position where the target object needs to be placed, in this case, after the robot moves to the second position, the robot can restore the original walking path and task execution logic, and then control the robot to move from the second position to the target position to perform the release action, ensuring that the release action is performed at the correct location.

[0246] Therefore, by moving the robot back to the position before being hijacked, it can be ensured that the target object can be released at the predetermined location according to the original execution logic, avoiding operational errors or task failures caused by position offset, and ensuring the successful execution of the target task. In this way, through the above-mentioned position correction process, errors caused by misoperation can be reduced, the accuracy and reliability of the target task execution can be improved, and the waste of resources caused by erroneous release can be reduced. In addition, the above-mentioned position correction process is automatically executed by the robot, which improves the convenience of operation.

[0247] In combination with the above embodiments, Figure 6 A flow chart of an optional robot control method provided in an embodiment of the present application is shown as follows: Figure 6 As shown, the control method of the robot includes the following steps:

[0248] Step A: The robot starts to perform the sorting task, which includes the robotic arm performing a clamping task. Furthermore, based on the sensor system, the robot identifies the presence of a target object on the travel path and controls the robotic arm to clamp the target object. In the process of the robotic arm clamping the target object, the robot's posture state is judged based on the posture information and / or pressure information detected by the sensor system, that is, whether it is off the ground; if it is detected that the robot is off the ground (suspended state), step B is executed; otherwise, the robot continues to perform the sorting task.

[0249] Step B: Determine whether the robot is moved abnormally, that is, whether it is in a suspended state after being hijacked by the user. If it is determined that the robot is in a suspended state after being hijacked by the user, control the robot to suspend the execution of the sorting task and control the robot to be in a standby state. Furthermore, based on the sensor system, detect in real time whether the robot has landed, that is, is in a state of contacting the surface. If not, the sensor system continuously detects whether the robot has landed; if so, execute step C.

[0250] Step C: Determine whether the robot is released from an abnormal state. Abnormal state release can be understood as the robot being placed back on the ground, that is, in a surface contact state. If it is determined that the robot is in a surface contact state, the robot can be controlled to perform a release action to release the clamped target object. Furthermore, the robot can be restored to a normal standby state or controlled to continue to perform the sorting task.

[0251] Optionally, to avoid false triggering of the release action, the present application can also set specific threshold conditions, such as the duration of lift-off, landing impact detection, position change range detection, etc., to further confirm abnormal movement and whether the landing has been resumed, and ensure that the release operation is carried out under reasonable conditions.

[0252] In this way, the present application detects the robot's posture status in real time during the process of the robot clamping the target object, and promptly identifies whether the robot is moved abnormally, an unexpected situation, thereby avoiding the subsequent execution control logic disorder due to lack of state perception, and improving the intelligence and safety of the robot's operation.

[0253] Secondly, after detecting abnormal movement, this application can suspend the execution of the current target task and enter standby state, effectively preventing the robotic arm from continuing to move or abnormally clamping, reducing the potential safety risks caused by conflicts between robotic arm operation and human movement, such as accidental injury to users, damage to clamped objects or the robot body, etc.

[0254] Furthermore, after confirming that the robot is in the state of contacting the surface, it can automatically execute the release operation of the clamped object. Through this processing logic, it can ensure that the clamped object in the abnormal process is released in a timely and safe manner, avoiding subsequent erroneous operations caused by the remaining clamping state. At the same time, it prevents the robot arm from getting stuck, load abnormalities or task process abnormalities caused by not releasing the clamped target object, which helps to improve the overall stability and task recovery capability of the robot.

[0255] In addition, this application also effectively suppresses false triggering caused by non-abnormal actions such as slight shaking or brief lifting while ensuring the timeliness of response by reasonably setting methods such as lift-off detection and landing judgment, such as the duration of being in the suspended state and the impact force detection of landing, thereby improving the accuracy and robustness of the robot's abnormality handling.

[0256] In summary, this application not only improves the robot's safety assurance capabilities during actual use through intelligent identification and processing of abnormal moving states, but also optimizes the human-computer interaction experience, enhances the robot's adaptability and reliability, and has good application prospects and use value.

[0257] For example, Figure 7 A flow chart of another robot control method provided in an embodiment of the present application is shown as follows: Figure 7 As shown, the robot control method is applied to Figure 1 and Figure 2 The robot shown; the control method of the robot comprises the following steps:

[0258] S701. In the process of a robotic arm gripping a target object and performing a target task, in response to a user's hijacking operation, obtain behavior information of the hijacking operation.

[0259] S702. Input the behavior information into a pre-trained machine learning model to determine whether the robot is in a suspended state; the trained machine learning model is obtained through training with multiple training samples, and the training samples include the behavior information of the user's hijacking operation and the state information corresponding to each behavior information, and the state information includes the suspended state and the contact surface state.

[0260] S703: When it is determined that the robot is in a suspended state, control the robot to continue to maintain the clamping state and suspend execution of the target task.

[0261] S704: After detecting that the robot is in a state of contacting the surface, control the robot to perform a release action to release the grip of the robot arm on the target object.

[0262] It should be noted that the process of S703-S704 is similar to the process of S401-S402 above. For details, please refer to the description of the above embodiment and will not be repeated here. Figure 7The embodiment shown and Figure 4 The embodiment shown differs in that Figure 7 In the embodiment shown, a method for determining whether the robot is in a suspended state is added, which is determined by adopting a pre-trained machine learning model. Accordingly, the training process and use process of the machine learning model have been described in the above embodiments. Therefore, the process description of S701-S702 can also refer to the description of the above embodiments and will not be repeated here.

[0263] It should also be noted that the series of operations performed when determining whether the robot is in a contact surface state or in a suspended state are similar to those described in the above embodiment. The above optional embodiments can be reused and will not be described in detail here.

[0264] Therefore, compared to traditional posture information and / or pressure information detection and threshold judgment methods to determine whether the robot is in a suspended state, this application uses a trained machine learning model to make the determination, and the corresponding determination result is more accurate. The machine learning model can quickly process the input behavior information and make judgments, improving the robot's real-time response capability and thus improving processing efficiency. In addition, accurate state recognition through machine learning models can reduce false positives and missed positives, improve the stability of overall operation, and help the robot take timely measures to prevent potential damage and safety hazards.

[0265] Furthermore, when the robot is determined to be in a suspended state due to being moved by the user, maintaining the grip can prevent the target object from falling during the move, thereby avoiding damage or loss. Pausing the task can also prevent the robot from performing actions in an unstable state, potentially damaging itself or the surrounding environment. It can also prevent operational logic confusion caused by sensor misreading or position changes, allowing the robot to resume the task after regaining stability, ensuring the integrity and continuity of the task. Furthermore, pausing the task in the suspended state can save power and other resources, extending the robot's operating time.

[0266] Furthermore, by confirming that the robot is in contact with the surface and then executing the release action, the robot arm automatically releases the grip of the target object, which can improve the accuracy and safety of object placement and avoid misplacement or accidental dropping. For example, releasing in a stable contact state can prevent the object from being damaged due to accidental dropping and protect the surrounding environment and equipment.

[0267] In the aforementioned embodiments, the control method of the robot provided in the embodiments of the present application is introduced. In order to implement the various functions of the method provided in the embodiments of the present application, the electronic device as the execution subject may include a hardware structure and / or a software module, and the aforementioned functions are implemented in the form of a hardware structure, a software module, or a hardware structure and a software module. Whether a particular function is implemented in the form of a hardware structure, a software module, or a hardware structure and a software module depends on the specific application and design constraints of the technical solution.

[0268] For example, Figure 8 A schematic diagram of the structure of a robot control device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the robot control device 800 is applied to the robot, and the robot is provided with a robotic arm, and the robotic arm is used to clamp the target object on the travel path; the robot control device 800 includes:

[0269] The first determining module 801 is configured to, in response to a user's hijacking operation, control the robot to maintain the gripping state and suspend the execution of the target task when the robot is determined to be in an airborne state during the process of the robot arm gripping the target object to perform the target task;

[0270] The first control module 802 is configured to control the robot to perform a release action after detecting that the robot is in a state of contacting a surface, so as to release the grip of the robot arm on the target object.

[0271] Optionally, the robot further includes a sensor system, which is used to detect the posture information and / or pressure information of the robot; the first determination module 801 is specifically used to:

[0272] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a suspended state.

[0273] Optionally, the sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a suspension detection unit, a distance detection unit, a lidar sensor, and a vision sensor; and determining that the robot is in a suspended state based on posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0274] The attitude and acceleration information detected by the inertial measurement unit (IMU) are within the abnormal threshold range;

[0275] The pressure sensor does not detect any pressure information between it and the contact surface;

[0276] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is greater than a preset distance threshold;

[0277] The visual sensor detects that the degree of difference in the change of the environmental characteristics of the contact surface does not meet the preset conditions.

[0278] Optionally, the robot further includes a sensor system, and the robot control device 800 further includes a fourth control module, the fourth control module being configured to:

[0279] When the robot is in a contact surface state, if the sensor system identifies the presence of a target object and determines that the target object needs to be clamped and moved to perform the target task, the robot arm is controlled to clamp the target object.

[0280] Optionally, the sensor system is further configured to detect the posture information and / or pressure information of the robot; the robot control device 800 further includes a detection module, which is configured to:

[0281] Based on the posture information and / or pressure information detected by the sensor system, it is determined that the robot is in a state of contacting the surface again.

[0282] Optionally, the sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a hover detection unit, a distance detection unit, a lidar sensor, and a vision sensor; and determining that the robot is in a state of contacting the surface again based on posture information and / or pressure information detected by the sensor system includes at least one of the following situations:

[0283] The attitude and acceleration information detected by the inertial measurement unit (IMU) are not within the abnormal threshold range;

[0284] The pressure sensor detects the pressure information between the contact surface and the contact surface;

[0285] At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is less than or equal to a preset distance threshold;

[0286] The visual sensor detects that the degree of difference in the environmental characteristics of the contact surface changes meets the preset conditions.

[0287] Optionally, the robotic arm has a two-finger gripper structure, and / or the sensor system includes a pressure feedback sensor, which is disposed on the robotic arm; the robot control device 800 further includes a fifth control module, which is configured to:

[0288] Based on the operating state of the two-finger gripper structure and / or the pressure information detected by the pressure feedback sensor, it is determined whether the target object is in a gripped state.

[0289] Optionally, the first control module 802 is specifically configured to:

[0290] When it is determined that the robot is in a suspended state and the duration of the suspended state is greater than a first threshold, controlling the robot to continue to maintain the clamping state and suspend execution of the target task;

[0291] Among them, when the robot suspends the execution of the target task, the robot is controlled to be in a standby state; in the standby state, the motor power of the robot is less than a preset cleaning power threshold.

[0292] Optionally, the robot control device 800 further includes a sixth control module, which is configured to:

[0293] When it is determined that the robot is in a suspended state and the duration of the suspended state is less than or equal to a first threshold, the robot is controlled to continue to perform the target task.

[0294] Optionally, the first control module 802 is specifically configured to:

[0295] After detecting that the robot is in a contact surface state, if it is determined that the impact force between the robot and the contact surface is greater than a second threshold, the robot is controlled to perform a release action.

[0296] Optionally, the robot control device 800 further includes a seventh control module, which is configured to:

[0297] After detecting that the robot is in a contact surface state, and determining that the impact force between the robot and the contact surface is less than or equal to a second threshold, the robot arm is controlled to continue gripping the target object and performing the target task.

[0298] Optionally, the first control module 802 is specifically configured to:

[0299] After detecting that the robot is in contact with the surface, the distance between the positions of the robot before and after being hijacked is obtained;

[0300] When it is determined that the distance is smaller than the third threshold, the robot is controlled to perform a release action, and the robot is controlled to continue to perform the target task.

[0301] Optionally, the robot control device 800 further includes an eighth control module, which is configured to:

[0302] When it is determined that the distance is greater than the third threshold, the robotic arm is controlled to continue to maintain the clamping state and suspend execution of the target task.

[0303] Optionally, after releasing the grip of the target object by the robotic arm, the method further includes at least one of the following situations:

[0304] Control the robot to perform other tasks;

[0305] Control the robot to be in standby mode;

[0306] Control the robot to grip the target object again to continue performing the target task;

[0307] Generates a prompt message to inform the user that the target task execution is abnormal.

[0308] Optionally, the first determining module 801 is specifically configured to:

[0309] Obtain behavioral information about the hijacking operation and input the behavioral information into a pre-trained machine learning model to determine whether the robot is in a suspended state;

[0310] Among them, the trained machine learning model is obtained through training with multiple training samples, and the training samples include the user's hijacking operation behavior information and the state information corresponding to each behavior information, and the state information includes the suspended state and the contact surface state.

[0311] Optionally, the first control module 802 is specifically configured to:

[0312] After detecting that the robot is in a state of contacting the surface, identifying a first position of the robot;

[0313] When it is determined that the first position is different from the second position where the robot was located before being hijacked, the robot is controlled to move to the second position, and after the robot is at the second position, the robot is controlled to perform a releasing action.

[0314] It should be noted that the specific implementation principles and effects of the control device 800 of the above-mentioned robot can be found in the relevant descriptions and effects corresponding to the above-mentioned embodiments, and will not be elaborated here.

[0315] Optional, Figure 9 A schematic diagram of the structure of another robot control device provided in an embodiment of the present application is shown in FIG. Figure 9 As shown, the robot control device 900 is applied to the robot, and the robot is provided with a robotic arm, and the robotic arm is used to clamp the target object on the travel path; the robot control device 900 includes:

[0316] An acquisition module 901 is configured to acquire behavior information of a hijacking operation in response to a user's hijacking operation during the process of the robotic arm gripping a target object and performing a target task;

[0317] The second determination module 902 is configured to input the behavior information into a pre-trained machine learning model to determine whether the robot is in a suspended state; the pre-trained machine learning model is trained using multiple training samples, the training samples including the user's hijacking operation behavior information and the state information corresponding to each behavior information, the state information including the suspended state and the contact surface state;

[0318] The second control module 903 is used to control the robot to continue to maintain the clamping state and suspend the execution of the target task when it is determined that the robot is in the suspended state;

[0319] The third control module 904 is configured to control the robot to perform a release action after detecting that the robot is in a state of contacting a surface, so as to release the grip of the robot arm on the target object.

[0320] It should be noted that the specific implementation principles and effects of the control device 900 of the above-mentioned robot can be found in the relevant descriptions and effects corresponding to the above-mentioned embodiments, and will not be elaborated here.

[0321] The embodiment of the present application also provides an electronic device, Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 10 As shown, the electronic device 1000 may include: a processor 1001 and a memory 1002 communicatively connected to the processor 1001; the memory 1002 stores a computer program; the processor 1001 executes the computer program stored in the memory 1002, so that the processor 1001 executes the method described in any of the above embodiments.

[0322] The memory 1002 and the processor 1001 may be connected via a bus 1003 .

[0323] An embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the method described in any of the aforementioned embodiments of the present application.

[0324] An embodiment of the present application further provides a chip for executing instructions, which is used to execute the method in any of the aforementioned embodiments as executed by an electronic device in any of the aforementioned embodiments of the present application.

[0325] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it can implement the method described in any of the aforementioned embodiments of the present application executed by an electronic device.

[0326] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0327] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these modules may be selected to implement the solution of this embodiment based on actual needs.

[0328] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each module may exist physically separately, or two or more modules may be integrated into a single unit. The above-mentioned modules may be implemented in the form of hardware or hardware plus software functional units.

[0329] The integrated modules implemented in the form of software functional modules can be stored in a computer-readable storage medium. The software functional modules stored in a storage medium include a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute some of the steps of the methods described in various embodiments of the present application.

[0330] It should be understood that the processor described above may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the application may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0331] The memory may include high-speed random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disk.

[0332] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0333] The above-mentioned storage medium can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0334] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium may be a component of the processor. The processor and storage medium may be located in an application-specific integrated circuit (ASIC). Alternatively, the processor and storage medium may be located as discrete components in an electronic device or a host control device.

[0335] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0336] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0337] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0338] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present application are indicated by the claims.

[0339] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A robot control method, characterized in that: The robot is provided with a mechanical arm, and the mechanical arm is used to clamp a target object on a travel path; the method comprises: In the process of the robot arm gripping the target object to perform the target task, in response to the user's hijacking operation, if it is determined that the robot is in a suspended state, controlling the robot to continue to maintain the gripping state and suspend the execution of the target task; After detecting that the robot is in a state of contacting a surface, the robot is controlled to perform a release action to release the grip of the robot arm on the target object.

2. The method according to claim 1, characterized in that The robot further includes a sensor system configured to detect posture information and / or pressure information of the robot; and determining that the robot is in a suspended state includes: Based on the posture information and / or the pressure information detected by the sensor system, it is determined that the robot is in a suspended state.

3. The method according to claim 2, characterized in that The sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a suspension detection unit, a distance detection unit, a lidar sensor, and a visual sensor; and determining that the robot is in a suspended state based on the posture information and / or the pressure information detected by the sensor system includes at least one of the following situations: The attitude and acceleration information detected by the inertial measurement unit (IMU) are within an abnormal threshold range; The pressure sensor does not detect any pressure information between the pressure sensor and the contact surface; At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is greater than a preset distance threshold; The visual sensor detects that the degree of difference in the change of the environmental characteristics of the contact surface does not meet a preset condition.

4. The method according to claim 1, wherein The robot further includes a sensor system, and the method further includes: When the robot is in a state of contacting a surface, if the sensor system recognizes the presence of the target object and determines that the target object needs to be clamped and moved to perform the target task, the robot arm is controlled to clamp the target object.

5. The method according to claim 4, characterized in that The sensor system is further configured to detect the position information and / or pressure information of the robot; the detecting that the robot is in a state of contacting a surface includes: Based on the posture information and / or the pressure information detected by the sensor system, it is determined that the robot is in the contact surface state again.

6. The method according to claim 5, characterized in that The sensor system includes at least one of an inertial measurement unit (IMU), a pressure sensor, a suspension detection unit, a distance detection unit, a lidar sensor, and a visual sensor; and determining that the robot is in the contact surface state again based on the posture information and / or the pressure information detected by the sensor system includes at least one of the following situations: The attitude and acceleration information detected by the inertial measurement unit (IMU) are not within an abnormal threshold range; The pressure sensor detects pressure information between the contact surface and the contact surface; At least one of the hovering detection unit, the distance detection unit, and the laser radar sensor detects that the separation distance from the contact surface is less than or equal to a preset distance threshold; The visual sensor detects that the degree of difference in the change of the environmental characteristics of the contact surface meets a preset condition.

7. The method according to claim 4, characterized in that The robotic arm is a two-finger gripper structure, and / or the sensor system includes a pressure feedback sensor, and the pressure feedback sensor is disposed on the robotic arm; the method further includes: Based on the operating state of the two-finger gripper structure and / or the pressure information detected by the pressure feedback sensor, it is determined whether the target object is in a gripped state.

8. The method according to claim 1, characterized in that When determining that the robot is in the suspended state, controlling the robot to continue to maintain the clamping state and suspend execution of the target task includes: When it is determined that the robot is in a suspended state and the duration of the suspended state is greater than a first threshold, controlling the robot to continue to maintain the clamping state and suspend execution of the target task; Wherein, when the robot suspends execution of the target task, the robot is controlled to be in a standby state; in the standby state, the motor power of the robot is less than a preset cleaning power threshold.

9. The method according to claim 8, characterized in that The method further comprises: When it is determined that the robot is in the suspended state and the duration of the suspended state is less than or equal to the first threshold, the robot is controlled to continue to perform the target task.

10. The method according to claim 1, characterized in that After detecting that the robot is in a state of contacting a surface, controlling the robot to perform a release action includes: After detecting that the robot is in the contact surface state, if it is determined that the impact force between the robot and the contact surface is greater than a second threshold, the robot is controlled to perform a release action.

11. The method according to claim 10, characterized in that The method further comprises: After detecting that the robot is in the contact surface state, and determining that the impact force between the robot and the contact surface is less than or equal to the second threshold, the robotic arm is controlled to continue clamping the target object to perform the target task.

12. The method according to claim 1, characterized in that After detecting that the robot is in a state of contacting a surface, controlling the robot to perform a release action includes: After detecting that the robot is in contact with a surface, obtaining the distance between the positions of the robot before and after being hijacked; When it is determined that the distance is smaller than a third threshold, the robot is controlled to perform a release action, and the robot is controlled to continue to perform the target task.

13. The method according to claim 12, characterized in that The method further comprises: When it is determined that the distance is greater than the third threshold, the robotic arm is controlled to continue to maintain the clamping state and suspend execution of the target task.

14. The method according to claim 1, wherein After releasing the grip of the target object by the robotic arm, the method further includes at least one of the following situations: Controlling the robot to perform other tasks; Controlling the robot to be in a standby state; controlling the robot to grip the target object again to continue performing the target task; Generate a prompt message to inform the user that the target task is executed abnormally.

15. The method according to claim 1, wherein Determining that the robot is in a suspended state includes: Obtaining behavioral information of the hijacking operation, inputting the behavioral information into a pre-trained machine learning model, and determining that the robot is in a suspended state; The trained machine learning model is obtained by training multiple training samples, and the training samples include behavioral information of the user's hijacking operation and state information corresponding to each behavioral information, and the state information includes a suspended state and a contact surface state.

16. The method according to claim 1, wherein After detecting that the robot is in a state of contacting a surface, controlling the robot to perform a release action includes: After detecting that the robot is in a state of contacting a surface, identifying a first position currently located by the robot; When it is determined that the first position is different from the second position where the robot was located before being hijacked, the robot is controlled to move to the second position, and after the robot is at the second position, the robot is controlled to perform the release action.

17. A robot control method, characterized in that: The robot is provided with a mechanical arm, and the mechanical arm is used to clamp a target object on a travel path; the method comprises: In the process of the robotic arm gripping the target object to perform the target task, in response to a user's hijacking operation, obtaining behavior information of the hijacking operation; Inputting the behavior information into a pre-trained machine learning model to determine whether the robot is in a suspended state; the trained machine learning model is obtained by training multiple training samples, the training samples including the user's hijacking operation behavior information and state information corresponding to each behavior information, the state information including the suspended state and the contact surface state; When it is determined that the robot is in the suspended state, controlling the robot to continue to maintain the clamping state and suspend execution of the target task; After detecting that the robot is in the contact surface state, the robot is controlled to perform a release action to release the grip of the robot arm on the target object.

18. A robot control device, characterized in that: The robot is provided with a mechanical arm, and the mechanical arm is used to clamp the target object on the travel path; the device includes: a first determining module, configured to, in response to a user's hijacking operation, control the robot to continue to maintain the gripping state and suspend the execution of the target task when determining that the robot is in a suspended state during the process of the robot arm gripping the target object to perform the target task; The first control module is used to control the robot to perform a release action after detecting that the robot is in a state of contacting a surface, so as to release the grip of the robot arm on the target object.

19. A robot control device, characterized in that: The robot is provided with a mechanical arm, and the mechanical arm is used to clamp the target object on the travel path; the device includes: An acquisition module, configured to acquire behavior information of a hijacking operation in response to a user's hijacking operation during the process of the robotic arm gripping the target object to perform a target task; a second determination module, configured to input the behavior information into a pre-trained machine learning model to determine whether the robot is in a suspended state; the pre-trained machine learning model is trained using a plurality of training samples, the training samples including the user's hijacking operation behavior information and state information corresponding to each behavior information, the state information including a suspended state and a contact surface state; a second control module, configured to control the robot to continue to maintain the clamping state and suspend the execution of the target task when determining that the robot is in the suspended state; The third control module is used to control the robot to perform a release action after detecting that the robot is in the contact surface state, so as to release the grip of the robot arm on the target object.

20. A robot, characterized in that: The robot is provided with a robotic arm and a controller, the robotic arm is used to clamp a target object on a travel path, and the controller is used to execute the method according to any one of claims 1 to 17.

21. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 17 when executed by a processor.

22. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 17 when being executed by a processor.

Images