Handle type cabinet door opening method and device, computer equipment and readable storage medium

Abstract

The application relates to a handle type cabinet door opening method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a normal contact force corresponding to a pressing force, a current displacement of an end of a mechanical arm under the pressing force and a door handle image under the pressing force in a process of applying the pressing force to a door handle of a target handle type cabinet door by a mechanical arm of a control inspection robot; acquiring clamping data of a gripper of the mechanical arm in a case where it is determined that the door handle is popped out based on the normal contact force, the displacement of the end of the mechanical arm and the door handle image; and performing a rotating operation on the door handle by the gripper until the target handle type cabinet door is in an open state in a case where it is verified that the gripper is in an expected clamping state based on the clamping data. The method can control the control inspection robot to open the handle type cabinet door.

Description

Technical Field

[0001] This application relates to the field of power inspection technology, and in particular to a handle-type cabinet door opening method, device, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] The doors of cabinets such as substation terminal boxes, control cabinets, and mechanism boxes often use handle-type or pop-out handle structures. These types of doors usually require pressing the lock head or the handle area to make the handle pop out from the door surface, then the robotic arm grips or contacts the handle and rotates to unlock it, and finally the door is pulled open. It is a continuous process that includes pressing, popping out, gripping, rotating, and pulling open.

[0003] Currently, the inspection robot can complete each individual action in the aforementioned continuous operation through force control, vision guidance, and other methods. However, due to the lack of real-time monitoring and judgment of the state transition conditions at each stage of the entire task process during the continuous operation of the inspection robot to open the handle-type cabinet door, the execution of the handle-type cabinet door opening task is easily interrupted. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for opening a handle-type cabinet door, which can monitor and judge the state transition conditions at each stage of the entire process of an inspection robot performing a handle-type door opening task in real time, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a handle-type cabinet door opening method, including:

[0006] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0007] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0008] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0009] In one embodiment, before acquiring the normal contact force corresponding to the pressing force, the current displacement of the robotic arm end under the pressing force, and the image of the door handle under the pressing force during the process of controlling the robotic arm to apply pressing pressure to the door handle of the target handle-type cabinet door, the method further includes:

[0010] The robotic arm of the inspection robot is controlled to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction;

[0011] Based on the positional error between the end effector of the robotic arm and the door handle area, and after determining that the handle pressing conditions are met, the robotic arm is controlled to begin applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

[0012] In one embodiment, the method further includes:

[0013] Perform outward convex contour detection on the door handle image;

[0014] If the door handle image contains a protruding profile of the door handle, the system determines whether the door handle of the target handle-type cabinet door will pop out based on the normal contact force and the displacement of the robotic arm end effector.

[0015] In one embodiment, the clamping data includes gripper closing displacement and clamping reaction force; the method further includes:

[0016] Based on the clamping displacement and clamping reaction force, and after verifying that the clamping is in a clamping state, the clamping is rotated at a preset clamping rotation angle to obtain the rotation test result. The preset clamping rotation angle is less than the clamping angle threshold.

[0017] Based on the rotation test results, determine whether the gripper is in the desired gripping state.

[0018] In one embodiment, the method further includes:

[0019] During the process of controlling the gripper to perform a closing operation on the door handle, data is collected on the gripper to obtain the gripper closing displacement and clamping reaction force;

[0020] When the gripper's closing displacement is within the target range, and the gripping reaction force is greater than the first preset reaction force threshold and less than the second preset reaction force threshold, the gripper is determined to be in a gripping state.

[0021] In one embodiment, the method further includes:

[0022] Based on the hinge direction of the target handle-type cabinet door, control the robotic arm of the inspection robot to perform the cabinet door opening operation until the target handle-type cabinet door is opened to the target angle;

[0023] Upon receiving a request to take photos inside the cabinet, the system acquires the current opening degree of the target handle-type cabinet door, the end effector pose of the robotic arm, and information on the visible area inside the cabinet.

[0024] Based on the current cabinet door opening, end pose, and visible area inside the cabinet, the inspection robot is controlled to perform a shooting operation.

[0025] Secondly, this application also provides a handle-type cabinet door opening device, comprising:

[0026] The pressing module is used to acquire the normal contact force corresponding to the pressing force, the current displacement of the end of the robotic arm under the pressing force, and the image of the door handle under the pressing force during the process of controlling the robotic arm of the inspection robot to apply pressing force to the door handle of the target handle-type cabinet door.

[0027] The gripping module is used to acquire gripping data of the gripper of the robotic arm when the door handle is determined to be in the pop-out state based on the normal contact force, the displacement of the end of the robotic arm and the image of the door handle. The gripping data is acquired by collecting data from the gripper when controlling the gripper of the inspection robot to grasp the door handle.

[0028] The rotation module is used to control the gripper to rotate the door handle when the gripper is in the desired gripping state based on the clamping data verification, until the target handle-type cabinet door is in the open state.

[0029] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0030] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0031] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0032] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0033] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0034] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0035] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0036] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0038] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0039] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0040] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0041] The aforementioned handle-type cabinet door opening method, device, computer equipment, computer-readable storage medium, and computer program product, during the process of controlling the robotic arm of the inspection robot to apply pressing pressure to the door handle of the target handle-type cabinet door, acquire the normal contact force corresponding to the pressing pressure, the current displacement of the robotic arm end under the pressing pressure, and the door handle image under the pressing pressure; when it is determined that the door handle is in the pop-out state based on the normal contact force, the displacement of the robotic arm end, and the door handle image, acquire the gripping data of the gripper of the robotic arm, which is obtained by data acquisition of the gripper when controlling the gripper of the inspection robot to grasp the door handle; when it is verified that the gripper is in the desired gripping state based on the gripping data, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state. Through the above process, the entire process of the inspection robot performing the task of opening the handle-type cabinet door can achieve multi-dimensional verification and confirmation of the door handle pop-out state after pressing and the gripper holding state after grabbing. This ensures that the state transition can be accurately completed between each action stage, effectively reducing the probability of door opening operation interruption due to misjudgment of door handle pop-out or non-compliant gripping state. This improves the success rate and stability of the inspection robot automatically opening the handle-type cabinet door, thereby ensuring the continuous automatic progress of power inspection operations and improving the overall automation level of substation inspection operations. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is an application environment diagram of a handle-type cabinet door opening method in one embodiment;

[0044] Figure 2 This is a flowchart illustrating a handle-type cabinet door opening method in one embodiment;

[0045] Figure 3 This is a flowchart illustrating the handle-type cabinet door opening method in another embodiment;

[0046] Figure 4 This is a flowchart illustrating the confirmation step in one embodiment;

[0047] Figure 5 This is a flowchart illustrating the desired clamping state confirmation step in one embodiment;

[0048] Figure 6 This is a flowchart illustrating the rotation release step in one embodiment;

[0049] Figure 7 This is a flowchart illustrating the steps for determining the abnormal rollback strategy in an abnormal rollback state in one embodiment.

[0050] Figure 8 This is a structural block diagram of a handle-type cabinet door opening device in one embodiment;

[0051] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0054] The handle-type cabinet door opening method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, the inspection robot 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104 or placed in the cloud or on another network server. During the process of controlling the robotic arm of the inspection robot 102 to apply pressure to the door handle of the target handle-type cabinet door, the server 104 acquires the normal contact force corresponding to the pressure, the current displacement of the robotic arm end effector under the pressure, and an image of the door handle under the pressure. When the server 104 determines that the door handle is in the pop-out state based on the normal contact force, the displacement of the robotic arm end effector, and the door handle image, it acquires the gripping data of the gripper of the robotic arm of the inspection robot 102. This gripping data is obtained by collecting data from the gripper when controlling the gripper of the inspection robot 102 to grasp the door handle. When the server 104 verifies that the gripper is in the desired gripping state based on the gripping data, it controls the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state. The inspection robot 102 can be, but is not limited to, a quadruped inspection robot, a wheeled inspection robot, a tracked inspection robot, or other mobile platforms capable of carrying a robotic arm. For example, a quadruped inspection robot can be equipped with a single robotic arm to perform the task of opening a handle-type cabinet door. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0055] In one exemplary embodiment, such as Figure 2 As shown, a handle-type cabinet door opening method is provided, which is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0056] Step 202: During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, acquire the normal contact force corresponding to the pressure, the current displacement of the end of the robotic arm under the pressure, and the image of the door handle under the pressure.

[0057] The inspection robot is equipped with a six-degree-of-freedom robotic arm, with a two-finger gripper, a pressing contact, a six-dimensional force / torque sensor, and an end-effector camera at the end of the arm. The pressing force is the force applied to the door handle, and the normal contact force is the force applied by the door handle to the pressing contact of the robotic arm.

[0058] Optionally, the inspection robot may have at least one robotic arm. For example, an auxiliary robotic arm may be installed on the inspection robot to resist wind and keep the cabinet door in a stable state.

[0059] For example, before the robotic arm of the inspection robot applies pressure to the door handle of the target handle-type cabinet door, the handle recognition module of the inspection robot identifies the door handle of the target handle-type cabinet door to determine the door handle type and door handle structural parameters; based on the door handle type and door handle structural parameters, the inspection robot performs parameter template matching to determine the preset approach direction, pressing pressure threshold, gripping offset, rotation angle and torque limit of the robotic arm.

[0060] For example, force control or impedance control is used to control the pressing contact at the end of the robotic arm of the inspection robot to apply pressing force to the door handle of the target handle-type cabinet door. At this time, the inspection robot is in the normal pressing state.

[0061] For example, during the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the data acquisition module of the inspection robot can acquire the normal contact force corresponding to the pressure, the current displacement of the end of the robotic arm under the pressure, and the image of the door handle under the pressure.

[0062] Step 204: Based on the normal contact force, the displacement of the robotic arm end effector and the door handle image, it is determined that the door handle is in the pop-out state. The gripping data of the robotic arm's gripper is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0063] The clamping data includes the jaw closing displacement and clamping reaction force.

[0064] Optionally, if it is determined that the door handle is not in the pop-out position based on the normal contact force, the displacement of the robotic arm's end effector, and the door handle image, the process can return to the step of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door. Alternatively, if it is determined that the door handle is not in the pop-out position based on the normal contact force, the displacement of the robotic arm's end effector, and the door handle image, the process can return to the step of determining that the door handle is in the pop-out position. Alternatively, if it is determined that the door handle is not in the pop-out position based on the normal contact force, the displacement of the robotic arm's end effector, and the door handle image, the process can control the robotic arm of the inspection robot to release the force and retract the door handle of the target handle-type cabinet door.

[0065] For example, when the door handle is determined to be in the pop-out position based on the normal contact force, the displacement of the robotic arm end effector, and the door handle image, the gripper of the inspection robot is controlled to grasp the door handle; during the process of controlling the gripper of the inspection robot to grasp the door handle, data is collected from the gripper to obtain the gripping data of the robotic arm's gripper.

[0066] Step 206: If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0067] The rotation operation includes a rotation pre-tightening operation and a rotation release operation. The rotation pre-tightening operation is used to detect the rotation direction and initial rotation resistance of the gripper. The rotation release operation is used to rotate the door handle according to the rotation direction and initial rotation resistance until the target handle-type cabinet door is in the open state.

[0068] For example, if the gripper is not found to be in the desired gripping state based on the gripping data, the gripper is controlled to open the door handle and the gripping operation is re-executed.

[0069] Optionally, if the gripper is found to be in the desired gripping state based on the gripping data, the gripper is controlled to perform a rotation pre-tightening operation and a rotation release operation on the door handle in sequence until the target handle-type cabinet door is in the open state.

[0070] Furthermore, based on the low angular velocity and small torque, the gripper is controlled to perform a rotational pre-tensioning operation on the door handle to detect the rotation direction, initial rotational resistance, and mechanical limit of the door handle. At this time, the inspection robot is in the rotational pre-tensioning state.

[0071] For example, the gripper is controlled to perform a rotational release operation on the door handle according to the target angle and upper limit of torque; during the process of controlling the gripper to perform the rotational release operation on the door handle, the rotation angle, rotation torque, angular velocity change and cabinet door micro-opening displacement are acquired; when a latch release event is detected based on the rotation angle, rotation torque, angular velocity change and cabinet door micro-opening displacement, the rotational release operation is stopped by stopping the further increase of rotation torque.

[0072] For example, the process of controlling the gripper to perform a rotational release operation on the door handle according to the target angle and upper limit of torque includes a main rotation stage, a rotational release determination stage, and a slow release stage: the main rotation stage is used to complete the main rotation angle; the rotational release determination stage determines whether the latch is released by torque reduction, sudden change in angular velocity, slight opening displacement of the cabinet door, or end torque fluctuation; the slow release stage is used to reduce residual torque and avoid impact caused by handle rebound.

[0073] In the above-mentioned method for opening a handle-type cabinet door, during the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure, the current displacement of the robotic arm end under the pressure, and the image of the door handle under the pressure are acquired; when it is determined that the door handle is in the pop-out state based on the normal contact force, the displacement of the robotic arm end, and the door handle image, the gripping data of the gripper of the robotic arm is acquired. The gripping data is obtained by collecting data from the gripper when controlling the gripper of the inspection robot to grasp the door handle; when it is verified that the gripper is in the desired gripping state based on the gripping data, the gripper is controlled to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state. Through the above process, the entire process of the inspection robot performing the task of opening the handle-type cabinet door can achieve multi-dimensional verification and confirmation of the door handle pop-out state after pressing and the gripper holding state after grabbing. This ensures that the state transition can be accurately completed between each action stage, effectively reducing the probability of door opening operation interruption due to misjudgment of door handle pop-out or non-compliant gripping state. This improves the success rate and stability of the inspection robot automatically opening the handle-type cabinet door, thereby ensuring the continuous automatic progress of power inspection operations and improving the overall automation level of substation inspection operations.

[0074] In an exemplary embodiment, before acquiring the normal contact force corresponding to the pressing force, the current displacement of the robotic arm end under the pressing force, and the door handle image under the pressing force during the process of controlling the robotic arm of the inspection robot to apply pressing pressure to the door handle of the target handle-type cabinet door, the method further includes: controlling the robotic arm end of the inspection robot to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; and, if it is determined that the handle pressing condition is met based on the positional error between the robotic arm end and the door handle area, controlling the robotic arm to start applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

[0075] The handle pressing condition is that the positional error between the end of the robotic arm and the door handle area is less than or equal to a preset positional error threshold. The preset approach direction is the normal to the target handle-type cabinet door.

[0076] For example, the end effector of the inspection robot's robotic arm is controlled to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; during the process of controlling the end effector of the inspection robot's robotic arm to approach the door handle area of ​​the target handle-type cabinet door along the preset approach direction, it is detected whether the positional error between the end effector of the robotic arm and the door handle area meets the handle pressing condition; if it is determined that the handle pressing condition is not met based on the positional error between the end effector of the robotic arm and the door handle area, the robotic arm of the inspection robot is fine-tuned through the six-dimensional force / torque sensor and end effector camera of the inspection robot until it is determined that the handle pressing condition is met based on the positional error between the end effector of the robotic arm and the door handle area.

[0077] In this embodiment, by adjusting the initial working position of the robotic arm end in advance, it is ensured that the subsequent pressing operation can be accurately applied to the door handle area, avoiding incomplete pressing due to excessive positional deviation, and providing an accurate initial operating basis for the door handle pop-out detection.

[0078] In one embodiment, the method further includes: detecting the outward protrusion of the handle in the door handle image; and, if the outward protrusion of the handle exists in the door handle image, determining whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the robotic arm end effector.

[0079] For example, the door handle image is subjected to handle protrusion contour detection; if the door handle image contains a handle protrusion contour that separates from the cabinet door plane, force detection is performed on the normal contact force and the displacement of the robotic arm end effector; if the normal contact force changes from rising to falling abruptly, and the displacement of the robotic arm end effector shows a slight forward movement or rebound, it is determined that the door handle of the target handle-type cabinet door is in the pop-out state. At this time, the inspection robot is in the pop-out confirmation state.

[0080] For example, based on the detected outward protrusion of the handle, the gripper posture and gripping offset are adjusted to control the gripper to align with the grippable area of ​​the door handle. At this time, the inspection robot is in the gripping alignment state.

[0081] Optionally, if the door handle image contains a convex profile of the handle and the convex profile is not separated from the cabinet door plane, force detection is performed on the normal contact force and the displacement of the robotic arm end effector. If the normal contact force changes from rising to falling suddenly, and the displacement of the robotic arm end effector shows a slight forward movement or rebound, the inspection robot is controlled to reduce the applied pressing force and return to the steps in the process of controlling the robotic arm of the inspection robot to apply pressing force to the door handle of the target handle-type cabinet door.

[0082] In this embodiment, a multimodal judgment method combining image visual detection and force displacement detection is used to avoid misjudgments caused by light and occlusion interference from single visual detection, and also avoids the problem that single force displacement detection cannot distinguish between door handle deformation and actual pop-out state, effectively improving the accuracy of door handle pop-out state judgment.

[0083] In one embodiment, the clamping data includes the jaw closing displacement and clamping reaction force; the method further includes: when the jaw is found to be in a clamping state based on the jaw closing displacement and clamping reaction force, performing a rotation test on the jaw by a preset jaw rotation angle to obtain a rotation test result, wherein the preset jaw rotation angle is less than a jaw angle threshold; and determining whether the jaw is in the desired clamping state based on the rotation test result.

[0084] The clamping state refers to the state where the grippers are not completely empty and the door handle is not excessively squeezed. The desired clamping state refers to the state where the grippers are not completely empty, the door handle is not excessively squeezed, and the grippers can move synchronously with the outer contour of the handle.

[0085] For example, if the gripper is not in the desired gripping state based on the rotation test results, the gripper is controlled to retract at a small angle or the rotation operation is terminated.

[0086] In this embodiment, the clamping state of the gripper is verified from multiple dimensions by measuring the clamping displacement, clamping reaction force, and rotation test results. This can prevent the gripper from missing its grip and causing subsequent rotation operation failure, and can also prevent the gripper from excessively squeezing the door handle and causing equipment damage. This ensures accurate clamping position and appropriate force, and improves the success rate of subsequent rotating door opening operations.

[0087] In an exemplary embodiment, the method further includes: during the process of controlling the gripper to perform a closing operation on the door handle, collecting data on the gripper to obtain the gripper closing displacement and clamping reaction force; and determining that the gripper is in a clamping state when the gripper closing displacement is within the target range and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold.

[0088] The first preset reaction force threshold and the second preset reaction force threshold are preset according to the clamping reaction force range of the inspection robot.

[0089] For example, if the gripper closing displacement is not within the target range, or if the gripping reaction force is less than or equal to the first preset reaction force threshold and greater than or equal to the second preset reaction force threshold, the gripper of the inspection robot is controlled to open, and visual positioning is performed again to determine the outward protrusion of the door handle, and the graspable area is reconfirmed based on the outward protrusion of the handle.

[0090] In this embodiment, by combining the two dimensions of gripper closing displacement and gripping reaction force, abnormal gripping conditions such as gripper missing or excessive squeezing can be quickly identified, and non-compliant gripping results can be screened out in advance to avoid subsequent door opening actions failing due to gripping misalignment, thereby further improving the smoothness of door opening operations.

[0091] In one embodiment, the method further includes: controlling the robotic arm of the inspection robot to perform a door-opening operation based on the hinge direction of the target handle-type cabinet door until the target handle-type cabinet door is opened to the target angle; upon receiving a request to take pictures inside the cabinet, acquiring the current door opening degree of the target handle-type cabinet door, the end-effector pose of the robotic arm, and the visible area information inside the cabinet; and controlling the inspection robot to perform a picture-taking operation based on the current door opening degree, end-effector pose, and visible area information inside the cabinet.

[0092] At this time, the inspection robot is in the door-opening and pulling state.

[0093] For example, based on the hinge direction and opening trajectory of the target handle-type cabinet door, the robotic arm of the inspection robot is controlled to perform the cabinet door opening operation until the target handle-type cabinet door is detected to be opened to the target angle based on the door opening degree, pulling force, end displacement and visual feedback.

[0094] For example, based on the current cabinet door opening, end pose, and visible area inside the cabinet, the inspection robot is controlled to perform a shooting operation by controlling the cabinet-side shooting module; if the inspection robot fails to perform the shooting operation, the reason for the failure is recorded and an abnormal rollback process is initiated.

[0095] In this embodiment, by pre-adjusting the opening range of the cabinet door in conjunction with the hinge direction, the viewing angle requirements for inspection and shooting inside the cabinet are met, ensuring that image data of the equipment inside the target cabinet can be clearly collected. This provides accurate raw data support for subsequent equipment status identification and fault diagnosis, further improving the full-process automation capability of substation inspection operations.

[0096] In one of the most specific embodiments, such as Figure 3 As shown, the handle-type cabinet door opening method described in this application is applied to an inspection robot. The states of the inspection robot when performing the handle-type cabinet door opening task include: approach alignment state, normal pressing state, pop-out confirmation state, grasping alignment state, clamping confirmation state, rotation pre-tensioning state, rotation release state, door opening and pulling state, and abnormal retraction state. Table 1 shows the correspondence between each state, the inspection robot's control mode, and the feedback quantity.

[0097] When the inspection robot is in a near-alignment state, the robot's robotic arm tip moves towards the door handle area of ​​the target handle-type cabinet door along a preset approach direction. If, based on the positional error between the robotic arm tip and the door handle area, the handle pressing condition is met, the robotic arm begins applying pressure to the door handle area of ​​the target handle-type cabinet door and enters a normal pressing state. If, based on the positional error between the robotic arm tip and the door handle area, the handle pressing condition is not met, the robot enters an abnormal retreat state.

[0098] When the inspection robot is in the normal pressing state, during the process of controlling the robot's robotic arm to apply pressing pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressing pressure, the current displacement of the robotic arm end under the pressing pressure, and the door handle image under the pressing pressure are acquired, and then the pop-up confirmation state is entered.

[0099] When the inspection robot is in the pop-up confirmation state, such as Figure 4As shown, the system detects the outward protrusion of the door handle in the image. If the outward protrusion of the door handle is present in the image, it determines whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the robotic arm end effector. If the door handle is determined to be popped out based on the normal contact force, the displacement of the robotic arm end effector, and the door handle image, the gripping data of the robotic arm's gripper is acquired. This gripping data is collected from the gripper when the inspection robot's gripper grasps the door handle, and the system enters a gripping confirmation state; otherwise, it enters an abnormal retreat state.

[0100] Table 1. Correspondence between various states, control modes of the inspection robot, and feedback quantities.

[0101]

[0102] When the inspection robot is in the gripping confirmation state, during the process of controlling the gripper to perform a closing operation on the door handle, data is collected on the gripper to obtain the gripper closing displacement and gripping reaction force; if the gripper closing displacement is within the target range, and the gripping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold, the gripper is determined to be in a gripping state; for example Figure 5 As shown, based on the clamping displacement and clamping reaction force, and after verifying that the clamp is in a clamping state, a rotation test is performed on the clamp at a preset clamping rotation angle to obtain the rotation test result. The preset clamping rotation angle is less than the clamping angle threshold. Based on the rotation test result, it is determined whether the clamp is in the desired clamping state. If the clamp is in the desired clamping state, it enters the rotation release state; otherwise, it enters the abnormal retreat state.

[0103] When the inspection robot is in the rotation release state, such as Figure 6 As shown, when the gripper is in the desired gripping state, the gripper is controlled to rotate the door handle until the target handle-type cabinet door is open. Then, according to the target angle and upper limit of torque, the gripper is controlled to rotate and release the door handle. During this rotation and release operation, the rotation angle, rotation torque, angular velocity changes, and the slight opening displacement of the cabinet door are acquired. When a latch release event is detected based on the rotation angle, rotation torque, angular velocity changes, and the slight opening displacement of the cabinet door, the rotation and release operation is stopped by ceasing further increase in rotation torque, and the door opening and pulling state is entered. Otherwise, an abnormal retreat state is entered.

[0104] When the inspection robot is in the open / pull-out state, based on the hinge direction of the target handle-type cabinet door, the robot's robotic arm is controlled to pull the door open until it reaches the target angle. Upon receiving a request to take a picture inside the cabinet, the robot acquires the current door opening degree, the end effector pose of the robotic arm, and the visible area inside the cabinet. Based on the current door opening degree, end effector pose, and visible area information, the robot is controlled to perform the picture-taking operation. If the robot fails to perform the picture-taking operation, the reason for the failure is recorded and the robot enters an abnormal rollback state.

[0105] When the inspection robot is in an abnormal retreat state, such as Figure 7 As shown, the system determines the anomaly's state and, based on the anomaly type, determines the corresponding anomaly rollback strategy. For example, if the anomaly is confirmed to be in the pop-up confirmation state (i.e., the door handle has not popped out based on the normal contact force, the robotic arm's end displacement, and the door handle image), the inspection robot is controlled to unload and retract, and it is determined whether a retry is needed. If so, the robot is re-aligned and the pressing force is applied; otherwise, the anomaly is recorded, and the handle-type cabinet door opening task is terminated.

[0106] Specifically, when any state is abnormal, the corresponding abnormal rollback strategy is executed according to the abnormality type: Handle not popped out: Remove the normal force, retreat to the preset distance, and press again; Clamping failure: Open the gripper and re-visually reposition the gripping edge; Excessive rotational resistance: Reduce the angular velocity and check if the torque limit has been reached, and retreat and terminate if necessary; Lock tongue not released: Perform small-angle reciprocating probe or enter manual verification; Cabinet door stuck: Stop the door pulling action and record the abnormal cabinet door resistance; Excessive wind disturbance: Transfer the task to the auxiliary stabilizing arm control module or suspend door opening.

[0107] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0108] Based on the same inventive concept, this application also provides a handle-type cabinet door opening device for implementing the handle-type cabinet door opening method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more handle-type cabinet door opening device embodiments provided below can be found in the limitations of the handle-type cabinet door opening method above, and will not be repeated here.

[0109] In one exemplary embodiment, such as Figure 8 As shown, a handle-type cabinet door opening device 800 is provided, including: a pressing module 802, a clamping module 804, and a rotating module 806, wherein:

[0110] The pressing module 802 is used to acquire the normal contact force corresponding to the pressing force, the current displacement of the end of the robotic arm under the pressing force, and the image of the door handle under the pressing force during the process of controlling the robotic arm of the inspection robot to apply pressing force to the door handle of the target handle-type cabinet door.

[0111] The gripping module 804 is used to acquire gripping data of the gripper of the robotic arm when the door handle is determined to be in the pop-out position based on the normal contact force, the displacement of the robotic arm end effector and the door handle image. The gripping data is acquired by collecting data from the gripper when controlling the gripper of the inspection robot to grasp the door handle.

[0112] The rotation module 806 is used to control the gripper to perform a rotation operation on the door handle when the gripper is in the desired gripping state based on the clamping data verification, until the target handle-type cabinet door is in the open state.

[0113] In one embodiment, the pressing module 802 is further configured to control the end of the robotic arm of the inspection robot to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; and, based on the positional error between the end of the robotic arm and the door handle area, determine that the handle pressing condition is met, control the robotic arm to begin applying pressing force to the door handle area of ​​the target handle-type cabinet door.

[0114] In one embodiment, the clamping module 804 is further configured to detect the outward protrusion of the door handle in the door handle image; if the outward protrusion of the door handle exists in the door handle image, it is determined whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the end of the robotic arm.

[0115] In one embodiment, the clamping module 804 is further configured to, based on the clamping jaw closing displacement and clamping reaction force, verify that the clamping jaw is in a clamping state, perform a rotation test on the clamping jaw by a preset clamping jaw rotation angle to obtain a rotation test result, wherein the preset clamping jaw rotation angle is less than a clamping jaw angle threshold; and determine whether the clamping jaw is in the desired clamping state based on the rotation test result.

[0116] In one embodiment, the clamping module 804 is further configured to collect data on the clamp during the process of controlling the clamp to perform a closing operation on the door handle, and obtain the clamp closing displacement and clamping reaction force; and determine that the clamp is in a clamping state when the clamp closing displacement is within the target range and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold.

[0117] In one embodiment, the handle-type cabinet door opening device 800 further includes a shooting module. The shooting module is used to control the robotic arm of the inspection robot to perform a cabinet door opening operation based on the hinge direction of the target handle-type cabinet door until the target handle-type cabinet door is opened to the target angle. When a cabinet interior shooting request is received, the module acquires the current cabinet door opening degree, the end effector pose of the robotic arm, and the visible area information inside the cabinet. Based on the current cabinet door opening degree, end effector pose, and visible area information inside the cabinet, the module controls the inspection robot to perform a shooting operation.

[0118] Each module in the aforementioned handle-type cabinet door opening device 800 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0119] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores clamping data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a handle-type cabinet door opening method.

[0120] Those skilled in the art will understand that Figure 9The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0121] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0122] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0123] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0124] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0125] In one embodiment, when the processor executes the computer program, it further implements the following steps: controlling the end of the robotic arm of the inspection robot to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; and, based on the positional error between the end of the robotic arm and the door handle area, determining that the handle pressing condition is met, controlling the robotic arm to begin applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

[0126] In one embodiment, when the processor executes the computer program, it further performs the following steps: detecting the outward protrusion of the door handle in the door handle image; and, if the outward protrusion of the door handle exists in the door handle image, determining whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the robotic arm end effector.

[0127] In one embodiment, when the processor executes the computer program, it further implements the following steps: when the gripper is in a clamping state based on the gripper closing displacement and clamping reaction force, the gripper is rotated at a preset gripper rotation angle to obtain the rotation test result, wherein the preset gripper rotation angle is less than the gripper angle threshold; and based on the rotation test result, it is determined whether the gripper is in the desired clamping state.

[0128] In one embodiment, when the processor executes the computer program, it further implements the following steps: during the process of controlling the gripper to perform a closing operation on the door handle, data is collected on the gripper to obtain the gripper closing displacement and clamping reaction force; when the gripper closing displacement is within the target range and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold, it is determined that the gripper is in a clamping state.

[0129] In one embodiment, when the processor executes the computer program, it further implements the following steps: based on the hinge direction of the target handle-type cabinet door, it controls the robotic arm of the inspection robot to perform a cabinet door opening operation until the target handle-type cabinet door is opened to the target angle; upon receiving a request to take pictures inside the cabinet, it acquires the current cabinet door opening degree, the end effector pose of the robotic arm, and the information of the visible area inside the cabinet; based on the current cabinet door opening degree, end effector pose, and the information of the visible area inside the cabinet, it controls the inspection robot to perform a picture-taking operation.

[0130] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0131] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0132] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0133] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0134] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: controlling the end of the robotic arm of the inspection robot to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; and, based on the positional error between the end of the robotic arm and the door handle area, determining that the handle pressing condition is met, controlling the robotic arm to begin applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

[0135] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: detecting the outward protrusion of the door handle in the door handle image; and, if the outward protrusion of the door handle exists in the door handle image, determining whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the robotic arm end effector.

[0136] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the gripper is in a clamping state based on the gripper closing displacement and clamping reaction force, the gripper is rotated at a preset gripper rotation angle to obtain the rotation test result, wherein the preset gripper rotation angle is less than the gripper angle threshold; and based on the rotation test result, it is determined whether the gripper is in the desired clamping state.

[0137] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: during the process of controlling the gripper to perform a closing operation on the door handle, data is collected on the gripper to obtain the gripper closing displacement and clamping reaction force; when the gripper closing displacement is within the target range and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold, it is determined that the gripper is in a clamping state.

[0138] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: based on the hinge direction of the target handle-type cabinet door, controlling the robotic arm of the inspection robot to perform a cabinet door opening operation until the target handle-type cabinet door is opened to the target angle; upon receiving a request to take pictures inside the cabinet, acquiring the current cabinet door opening degree, the end effector pose of the robotic arm, and the visible area information inside the cabinet; based on the current cabinet door opening degree, end effector pose, and visible area information inside the cabinet, controlling the inspection robot to perform a picture-taking operation.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0140] During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired.

[0141] Based on the normal contact force, the displacement of the robotic arm end effector and the image of the door handle, the gripping data of the robotic arm's gripper is obtained. The gripping data is obtained by collecting data from the gripper when controlling the inspection robot's gripper to grasp the door handle.

[0142] If the gripper is in the desired gripping state based on the gripping data verification, control the gripper to perform a rotation operation on the door handle until the target handle-type cabinet door is in the open state.

[0143] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: controlling the end of the robotic arm of the inspection robot to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; and, based on the positional error between the end of the robotic arm and the door handle area, determining that the handle pressing condition is met, controlling the robotic arm to begin applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

[0144] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: detecting the outward protrusion of the door handle in the door handle image; and, if the outward protrusion of the door handle exists in the door handle image, determining whether the door handle of the target handle-type cabinet door has popped out based on the normal contact force and the displacement of the robotic arm end effector.

[0145] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the gripper is in a clamping state based on the gripper closing displacement and clamping reaction force, the gripper is rotated at a preset gripper rotation angle to obtain the rotation test result, wherein the preset gripper rotation angle is less than the gripper angle threshold; and based on the rotation test result, it is determined whether the gripper is in the desired clamping state.

[0146] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: during the process of controlling the gripper to perform a closing operation on the door handle, data is collected on the gripper to obtain the gripper closing displacement and clamping reaction force; when the gripper closing displacement is within the target range and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold, it is determined that the gripper is in a clamping state.

[0147] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: based on the hinge direction of the target handle-type cabinet door, controlling the robotic arm of the inspection robot to perform a cabinet door opening operation until the target handle-type cabinet door is opened to the target angle; upon receiving a request to take pictures inside the cabinet, acquiring the current cabinet door opening degree, the end effector pose of the robotic arm, and the visible area information inside the cabinet; based on the current cabinet door opening degree, end effector pose, and visible area information inside the cabinet, controlling the inspection robot to perform a picture-taking operation.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0149] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 application.

[0151] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for opening a cabinet door with a handle, characterized in that, The method includes: During the process of controlling the robotic arm of the inspection robot to apply pressure to the door handle of the target handle-type cabinet door, the normal contact force corresponding to the pressure is acquired, the current displacement of the end of the robotic arm under the pressure is acquired, and the door handle image under the pressure is acquired. When the door handle is determined to be in the pop-out state based on the normal contact force, the displacement of the end of the robotic arm, and the image of the door handle, the gripping data of the gripper of the robotic arm is obtained. The gripping data is obtained by collecting data from the gripper when controlling the gripper of the inspection robot to grasp the door handle. If the gripper is found to be in the desired gripping state based on the gripping data, the gripper is controlled to rotate the door handle until the target handle-type cabinet door is in the open state.

2. The method according to claim 1, characterized in that, Before acquiring the normal contact force corresponding to the pressing force, the current displacement of the robotic arm end under the pressing force, and the image of the door handle under the pressing force during the process of controlling the inspection robot's robotic arm to apply pressing pressure to the door handle of the target handle-type cabinet door, the method further includes: The robotic arm of the inspection robot is controlled to approach the door handle area of ​​the target handle-type cabinet door along a preset approach direction; Based on the positional error between the end of the robotic arm and the door handle area, and after determining that the handle pressing conditions are met, the robotic arm is controlled to begin applying pressing pressure to the door handle area of ​​the target handle-type cabinet door.

3. The method according to claim 1, characterized in that, The method further includes: Perform handle convex contour detection on the door handle image; If the door handle image contains the outwardly protruding profile of the door handle, it is determined whether the door handle of the target handle-type cabinet door will pop out based on the normal contact force and the displacement of the end of the robotic arm.

4. The method according to claim 1, characterized in that, The clamping data includes the jaw closing displacement and clamping reaction force; the method further includes: Based on the clamping displacement and the clamping reaction force, and after verifying that the clamping jaw is in a clamping state, a rotation test is performed on the clamping jaw according to a preset clamping jaw rotation angle to obtain the rotation test result. The preset clamping jaw rotation angle is less than the clamping jaw angle threshold. Based on the rotation test results, it is determined whether the gripper is in the desired gripping state.

5. The method according to claim 4, characterized in that, The method further includes: During the process of controlling the gripper to perform a closing operation on the door handle, data is collected from the gripper to obtain the gripper closing displacement and clamping reaction force; When the clamping jaw's closing displacement is within the target range, and the clamping reaction force is greater than a first preset reaction force threshold and less than a second preset reaction force threshold, the clamping jaw is determined to be in a clamping state.

6. The method according to claim 1, characterized in that, The method further includes: Based on the hinge direction of the target handle-type cabinet door, the robotic arm of the inspection robot is controlled to perform the cabinet door opening operation until the target handle-type cabinet door is opened to the target angle; Upon receiving a request to take photos inside the cabinet, the system acquires the current opening degree of the target handle-type cabinet door, the end effector pose of the robotic arm, and information on the visible area inside the cabinet. Based on the current cabinet door opening, the end pose, and the visible area inside the cabinet, the inspection robot is controlled to perform a shooting operation.

7. A handle-type cabinet door opening device, characterized in that, The device includes: The pressing module is used to acquire the normal contact force corresponding to the pressing force, the current displacement of the end of the robotic arm under the pressing force, and the image of the door handle under the pressing force during the process of controlling the robotic arm of the inspection robot to apply pressing force to the door handle of the target handle-type cabinet door. The gripping module is used to acquire gripping data of the gripper of the robotic arm when the door handle is determined to be in the pop-out position based on the normal contact force, the displacement of the end of the robotic arm, and the image of the door handle. The gripping data is obtained by collecting data from the gripper when controlling the gripper of the inspection robot to grasp the door handle. The rotation module is used to control the gripper to perform a rotation operation on the door handle when the gripper is in the desired gripping state based on the clamping data verification, until the target handle-type cabinet door is in the open state.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images