Grabbing device and grasping method

Abstract

The present application provides a grasping device and a grasping method. The method first obtains each detection point in a first link joint on a robot arm to obtain a first up-range coordinate group and a first down-range coordinate group; performs deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robot arm; obtains the time series coordinates of each detection point in a second link joint on the robot arm in a grasping coordinate system to obtain a second up-range coordinate group and a second down-range coordinate group for deviation detection to obtain a second grasping phase deviation of the robot arm; performs joint deviation measurement on the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the joint center of gravity influence of the robot arm; finally, obtains target object parameter information, and determines the working mode of the robot arm according to the joint center of gravity influence and the target object parameter information, thereby reducing the vibration of the robot arm caused by the change of the center of gravity of the robot arm and improving the grasping accuracy of the robot arm.

Description

Technical Field

[0001] The present application relates to the technical field of robotic arms, and more specifically, to a grasping device and a grasping method. Background Art

[0002] A robotic arm is a mechanical device that can simulate the functions of a human arm. It is usually composed of multiple connected rigid arm segments and joints. It can perform various movements in space to complete specific tasks. The robotic arm achieves high-precision position control and movement through precise control systems and sensors. It can accurately locate and grasp target objects, thereby ensuring stability and reliability in complex environments. Especially on production lines that require repetitive actions, robotic arms are widely used in industrial automation and other fields.

[0003] In the existing robotic arm grasping method, the power output is mainly controlled by a preset program to enable the robotic arm to complete the desired grasping action. However, the robotic arm's own weight has different effects on the corresponding grasping action in different directions. When grasping upward, the robotic arm's own weight will cause the position of the joint to sink slightly, affecting the position of the grasped object. When grasping downward, especially when the robotic arm grasps a heavier object, the robotic arm's own weight and the weight of the object will cause the center of gravity of the robotic arm to change, causing the robotic arm's joints to accelerate during the falling process, causing the robotic arm to vibrate, greatly reducing the robotic arm's grasping accuracy in a small space. Summary of the invention

[0004] The present application provides a grasping device and a grasping method to reduce the deadweight of the robotic arm or the vibration of the robotic arm caused by the change of the center of gravity of the robotic arm when the grasped object is too heavy, thereby improving the grasping accuracy of the robotic arm.

[0005] In a first aspect, the present application provides a capture method, which may be executed by a network device, or may be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes:

[0007] Starting the robot arm control and determining the grasping coordinate system according to the calibrated grasping direction of the robot arm;

[0008] Obtaining the time-series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and performing time-series classification to obtain a first up-process coordinate group and a first down-process coordinate group;

[0009] Performing deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robotic arm;

[0010] Acquire the time-series coordinates of each detection point in the second link joint of the robot arm in the grasping coordinate system to obtain a second up-range coordinate group and a second down-range coordinate group, perform deviation detection on the second up-range coordinate group and the second down-range coordinate group to obtain a second grasping phase deviation of the robot arm;

[0011] Performing joint deviation measurement on a first grasping phase deviation and a second grasping phase deviation of the robotic arm to obtain a joint center of gravity influence degree of the robotic arm;

[0012] Acquire parameter information of the target object, determine the working mode of the robot arm according to the influence of the joint center of gravity and the parameter information of the target object, and control the robot arm to grasp according to the determined working mode.

[0013] In combination with the first aspect, in some implementations of the first aspect, determining the grasping coordinate system according to the calibrated grasping direction of the robot arm specifically includes:

[0014] Determining a detection reference point of the robotic arm according to a calibrated grasping direction of the robotic arm;

[0015] A grasping coordinate system is constructed according to the calibrated grasping direction of the robot arm and the detection reference point, and each link joint of the robot arm is set to an initial position in the grasping coordinate system.

[0016] In combination with the first aspect, in some implementations of the first aspect, obtaining the time-series coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system and performing time-series classification to obtain the first up-process coordinate group and the first down-process coordinate group specifically includes:

[0017] The three-dimensional coordinates corresponding to each detection point of the first link joint on the robot arm when grasping upward and grasping downward are respectively collected, and all the three-dimensional coordinates are converted into two-dimensional coordinates in the grasping coordinate system;

[0018] Sorting the detection moments corresponding to the two-dimensional coordinates to obtain a set of time series coordinates corresponding to the detection points of the first link joint;

[0019] The upward grasping time period and the downward grasping time period of the robot arm are obtained, and each time series coordinate is classified according to the corresponding grasping time period and the detection time, so as to obtain multiple upward coordinate values ​​and multiple downward coordinate values ​​and store them in the first upward coordinate group and the first downward coordinate group respectively.

[0020] In combination with the first aspect, in some implementations of the first aspect, performing deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain the first grasping phase deviation of the robot arm specifically includes:

[0021] Determine a first upstream path value according to the first upstream coordinate group;

[0022] Determine a first downstream path value according to the first downstream coordinate group;

[0023] The detection point distribution distance is obtained, and the first grasping phase deviation of the robot arm is determined according to the detection point distribution distance, the first up-path value, and the first down-path value.

[0024] In combination with the first aspect, in certain implementations of the first aspect, determining the working mode of the robot arm according to the joint center of gravity influence and the target object parameter information specifically includes:

[0025] Obtaining the weight of the target object through the target object parameter information;

[0026] Determining a gravity center influence threshold according to the gravity center influence degree of the joint, and setting the robot arm to operate in a first working mode when the weight of the target object is lower than the gravity center influence threshold;

[0027] When the weight of the target object is higher than the center of gravity influence threshold, the robotic arm is set to operate in the second working mode.

[0028] In combination with the first aspect, in some implementations of the first aspect, an acceleration threshold of the second working mode of the robotic arm is higher than an acceleration threshold of the first working mode.

[0029] In combination with the first aspect, in certain implementations of the first aspect, a visual sensor is used to obtain the temporal coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system.

[0030] In a second aspect, the present application provides a gripping device, including a gripping control unit, wherein the gripping control unit includes:

[0031] A detection module, used to start the control of the robot arm and determine the grasping coordinate system according to the calibrated grasping direction of the robot arm;

[0032] A processing module, used for obtaining the time series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and performing time series classification to obtain a first up-process coordinate group and a first down-process coordinate group;

[0033] The processing module is further used to perform deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robotic arm;

[0034] The processing module is further used to obtain the time-series coordinates of each detection point in the second link joint of the robot arm in the grasping coordinate system, obtain a second upper coordinate group and a second lower coordinate group, and perform deviation detection on the second upper coordinate group and the second lower coordinate group to obtain a second grasping phase deviation of the robot arm;

[0035] The processing module is further used to measure the joint deviation of the first grasping phase deviation and the second grasping phase deviation of the robotic arm to obtain the influence of the joint center of gravity of the robotic arm;

[0036] The execution module is used to obtain parameter information of the target object, determine the working mode of the robot arm according to the influence degree of the joint center of gravity and the parameter information of the target object, and control the robot arm to grasp according to the determined working mode.

[0037] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned crawling method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned crawling method.

[0039] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0040] In a grasping device and grasping method provided by the present application, the robot arm control is first started, and the grasping coordinate system is determined according to the calibrated grasping direction of the robot arm; the time coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system are obtained and time classification is performed to obtain a first up-range coordinate group and a first down-range coordinate group; the first up-range coordinate group and the first down-range coordinate group are used to perform deviation detection to obtain a first grasping phase deviation of the robot arm; the time coordinates of each detection point in the second link joint on the robot arm in the grasping coordinate system are obtained to obtain a second up-range coordinate group and a second down-range coordinate group, and the second up-range coordinate group and the second down-range coordinate group are used to perform deviation detection to obtain a second grasping phase deviation of the robot arm; the joint deviation is measured for the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the joint center of gravity influence of the robot arm; finally, the target object parameter information is obtained, and the working mode of the robot arm is determined according to the joint center of gravity influence and the target object parameter information.

[0041] It can be seen that the present application determines the degree of deviation of the robot arm's own weight on the first link joint and the second link joint when grasping in different directions, and obtains the first grasping phase deviation and the second grasping phase deviation, that is, divides the position information of different link joints into upstroke (ascending process) and downstroke (descending process) coordinate groups, so as to analyze the dynamic behavior of the robot arm when moving in different directions, and then determines the influence of the joint center of gravity of the robot arm according to the first grasping phase deviation and the second grasping phase deviation of the robot arm, so as to determine the influence of the center of gravity of the robot arm on the overall movement of the robot arm during movement. The center of gravity offset will cause instability and vibration of the robot arm during the grasping process. Finally, the working mode of the robot arm is adjusted according to the influence of the joint center of gravity. At different joint center of gravity influences and object parameters, the robot arm is in the working mode (for example, adjusting the acceleration limit of the robot arm in different working modes), thereby reducing the vibration of the robot arm caused by the change of the center of gravity of the robot arm and improving the grasping accuracy of the robot arm. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an exemplary flow chart of a crawling method according to some embodiments of the present application;

[0043] Figure 2 is a schematic diagram of exemplary hardware and / or software of a gripping control unit according to some embodiments of the present application;

[0044] Figure 3 It is a structural schematic diagram of a computer terminal device for implementing a crawling method according to some embodiments of the present application. DETAILED DESCRIPTION

[0045] The present application first starts the robot arm control and determines the grasping coordinate system according to the calibrated grasping direction of the robot arm; obtains the time coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system and performs time classification to obtain the first up-range coordinate group and the first down-range coordinate group; performs deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain the first grasping phase deviation of the robot arm; obtains the time coordinates of each detection point in the second link joint on the robot arm in the grasping coordinate system to obtain the second up-range coordinate group and the second down-range coordinate group, performs deviation detection on the second up-range coordinate group and the second down-range coordinate group to obtain the second grasping phase deviation of the robot arm; performs joint deviation measurement on the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the joint center of gravity influence of the robot arm; finally, obtains the target object parameter information, and determines the working mode of the robot arm according to the joint center of gravity influence and the target object parameter information, thereby reducing the vibration of the robot arm caused by the change of the center of gravity of the robot arm and improving the grasping accuracy of the robot arm.

[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a grasping method according to some embodiments of the present application, and the grasping method 100 mainly includes the following steps:

[0047] In step S101, the robot arm control is started, and a grasping coordinate system is determined according to the calibrated grasping direction of the robot arm.

[0048] It should be noted that the grasping coordinate system is a two-dimensional coordinate system with the calibrated grasping direction as the grasping plane, which is used to test the grasping ability of the robotic arm. In some embodiments, in order to facilitate determining the impact of the self-weight on the various link joints in the robotic arm, when setting the grasping coordinate system, the coordinate plane of the grasping coordinate system can be set perpendicular to the ground.

[0049] Optionally, in some embodiments, the calibrated grasping direction is a preset grasping direction. In specific implementation, any vector direction perpendicular to the space Z-axis in the standard space coordinate system can be used as the calibrated grasping direction. In specific implementation, the direction of the space environment with relatively open space can be selected as the calibrated grasping direction based on the surrounding environment of the robot arm.

[0050] Optionally, in some embodiments, determining the grasping coordinate system according to the calibrated grasping direction of the robot arm specifically includes:

[0051] The detection reference point of the robotic arm is determined according to the calibrated grasping direction of the robotic arm. In a specific implementation, the position of the base of the robotic arm in the calibrated grasping direction can be used as the reference point of the robotic arm.

[0052] A grasping coordinate system is constructed according to the calibrated grasping direction of the robotic arm and the detection reference point, and each link joint of the robotic arm is set to an initial position in the grasping coordinate system. In specific implementation, the detection reference point can be set as the coordinate origin of the grasping coordinate system, the first coordinate axis direction of the grasping coordinate system is the calibrated grasping direction, the second coordinate axis direction of the grasping coordinate system is the Z-axis direction in the standard space coordinate system, and the initial position of each link joint in the grasping coordinate system is determined according to the spatial position of each link joint in the robotic arm.

[0053] In step S102, the time-series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system are obtained and time-series classification is performed to obtain a first upstream coordinate group and a first downstream coordinate group.

[0054] It should be noted that the first link joint of the robot arm refers to the first movable part or joint of the robot arm, which connects the base of the robot arm and the second joint. In a multi-joint robot arm, each joint allows the robot arm to move in different directions, thereby achieving complex spatial movement and operation.

[0055] It should be noted that the first up-range coordinate group and the first down-range coordinate group are respectively composed of up-range coordinate values ​​and down-range coordinate values ​​corresponding to each detection point, wherein the up-range coordinate value represents the coordinates of each detection point in the first link joint in the grasping coordinate system when the robotic arm grasps upward, and the down-range coordinate value represents the coordinates of each detection point in the first link joint in the grasping coordinate system when the robotic arm grasps downward.

[0056] Optionally, in some embodiments, the number of detection points in the first link joint is preset to a constant, and the detection points in the first link joint are evenly distributed on the connecting rod between the first link joint and the robot arm base.

[0057] Optionally, in some embodiments, a visual sensor may be used to collect coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system to obtain a first up-range coordinate group and a first down-range coordinate group.

[0058] Optionally, in some embodiments, obtaining the time-series coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system and performing time-series classification to obtain the first up-process coordinate group and the first down-process coordinate group specifically includes:

[0059] The three-dimensional coordinates corresponding to each detection point of the first link joint on the robot arm when grasping upward and grasping downward are respectively collected, and all the three-dimensional coordinates are converted into two-dimensional coordinates in the grasping coordinate system;

[0060] Sorting the detection moments corresponding to the two-dimensional coordinates to obtain a set of time series coordinates corresponding to the detection points of the first link joint;

[0061] The upward grasping time period and the downward grasping time period of the robot arm are obtained, and each time series coordinate is classified according to the corresponding grasping time period and the detection time, so as to obtain multiple upward coordinate values ​​and multiple downward coordinate values ​​and store them in the first upward coordinate group and the first downward coordinate group respectively.

[0062] In step S103, a deviation detection is performed on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robot arm.

[0063] It should be noted that the first grasping phase deviation represents a quantified value of the grasping deviation of the first link joint of the robot arm due to the weight of the robot arm, and is determined according to the path value deviation of the first link joint of the robot arm when grasping upward and downward under the same environment. Optionally, in some embodiments, the first upward coordinate group and the first downward coordinate group are used to perform deviation detection to obtain the first grasping phase deviation of the robot arm, which specifically includes:

[0064] Determine a first upstream path value according to the first upstream coordinate group;

[0065] Determine a first downstream path value according to the first downstream coordinate group;

[0066] The detection point distribution distance is obtained, and the first grasping phase deviation of the robot arm is determined according to the detection point distribution distance, the first up-path value, and the first down-path value.

[0067] In specific implementation, the first upstream path value is the coordinate distance value between the first time series coordinate and the last time series coordinate in the first upstream coordinate group, the first downstream path value is the coordinate distance value between the first time series coordinate and the last time series coordinate in the first downstream coordinate group, and the detection point distribution distance is the average distance value between each detection point in the first link joint. In some embodiments, the first grasping phase deviation sum = (the first downstream path value - the first upstream path value) / 2pi×the detection point distribution distance, where pi is the natural pi.

[0068] In step S104, the time coordinates of each detection point in the second link joint on the robot arm in the grasping coordinate system are obtained to obtain a second up-range coordinate group and a second down-range coordinate group. The deviation is detected by the second up-range coordinate group and the second down-range coordinate group to obtain the second grasping phase deviation of the robot arm.

[0069] It should be noted that the second link joint of the robotic arm refers to the second joint component connected after the first link joint. In a multi-joint robotic arm, each joint can move in different directions. Through the combination and coordination of these joints, the robotic arm can complete complex spatial movement and operation tasks.

[0070] Optionally, in some embodiments, obtaining the time-series coordinates of each detection point in the second link joint on the robot arm in the grasping coordinate system to obtain the second up-range coordinate group and the second down-range coordinate group specifically includes:

[0071] The three-dimensional coordinates corresponding to each detection point of the second link joint on the robot arm when grasping upward and grasping downward are respectively collected, and all the three-dimensional coordinates are converted into two-dimensional coordinates in the grasping coordinate system;

[0072] Sorting the detection moments corresponding to the two-dimensional coordinates to obtain a set of time series coordinates corresponding to the detection points of the second link joint;

[0073] The upward grasping time period and the downward grasping time period of the robot arm are obtained, and each time series coordinate is classified according to the corresponding grasping time period and the detection time to obtain multiple upward coordinate values ​​and multiple downward coordinate values ​​and store them in the second upward coordinate group and the second downward coordinate group respectively.

[0074] Optionally, in some embodiments, performing deviation detection on the second up-range coordinate group and the second down-range coordinate group to obtain the second grasping phase deviation of the robotic arm specifically includes:

[0075] Determine a second upstream path value according to the second upstream coordinate group;

[0076] Determine a second downstream path value according to the second downstream coordinate group;

[0077] The detection point distribution distance of the second link joint is obtained, and the second grasping phase deviation of the robot arm is determined according to the detection point distribution distance of the second link joint, the second up-path value and the second down-path value.

[0078] In specific implementation, the second up-path value is the coordinate distance value between the second time coordinate and the last time coordinate in the second up-path coordinate group, the second down-path value is the coordinate distance value between the second time coordinate and the last time coordinate in the second down-path coordinate group, the detection point distribution distance of the second link joint is the average distance value between each detection point in the second link joint, and in some embodiments, the second grasping phase deviation sum = (the second down-path value - the second up-path value) / 2pi×the detection point distribution distance.

[0079] In step S105, joint deviation measurement is performed on the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the influence degree of the joint center of gravity of the robot arm.

[0080] It should be noted that the joint center of gravity influence degree is the degree of influence of the link joints of the manipulator with different extension lengths relative to the base under the same working link of the manipulator, which is determined according to the first grasping phase deviation and the second grasping phase deviation of the manipulator. Optionally, in some embodiments, the joint deviation measurement is performed on the first grasping phase deviation and the second grasping phase deviation of the manipulator to obtain the joint center of gravity influence degree of the manipulator, which specifically includes:

[0081] Get the first link length and the second link length;

[0082] Determining an initial joint center of gravity influence of the robotic arm according to the first link length, the second link length, the first grasping phase deviation, and the second grasping phase deviation;

[0083] Determining an upstream related adjustment coefficient based on the first upstream coordinate group and the second upstream coordinate group;

[0084] Determining a down-process related adjustment coefficient based on the first down-process coordinate group and the second down-process coordinate group;

[0085] The initial joint center of gravity influence degree is subjected to correlation correction according to the upper range correlation adjustment coefficient and the lower range correlation adjustment coefficient to obtain the joint center of gravity influence degree of the robotic arm.

[0086] Optionally, in some embodiments, the first link length is the Euclidean distance value between the first link joint and the robot arm base, and the second link length is the Euclidean distance value between the first link joint and the second link joint. In specific implementation, the initial joint center of gravity influence = (first grasping phase deviation × second link length) / (second grasping phase deviation × first link length).

[0087] It should be noted that the up-range related adjustment coefficient and the down-range related adjustment coefficient are used to correct the influence of the joint center of gravity of the robot arm. By determining the correlation coefficient of the coordinate changes of the first link joint and the second link joint during movement, and adjusting the influence of the initial joint center of gravity of the robot arm according to the correlation coefficient, possible external interference that may affect the movement of the robot arm is eliminated.

[0088] Preferably, in some embodiments, the upstream correlation adjustment coefficient is the Pearson correlation coefficient between the first upstream coordinate group and the second upstream coordinate group, and the downstream correlation adjustment coefficient is the Pearson correlation coefficient between the first downstream coordinate group and the second downstream coordinate group. In specific implementation, the joint center of gravity influence = initial joint center of gravity influence × (upward correlation adjustment coefficient / downward correlation adjustment coefficient).

[0089] In step S106, the target object parameter information is obtained, the working mode of the robot arm is determined according to the joint center of gravity influence and the target object parameter information, and the robot arm is controlled to grasp according to the determined working mode.

[0090] It should be noted that the joint center of gravity influence degree refers to the degree of influence of the deadweight of the connecting joints of the robotic arm with different extension lengths relative to the base under the same working link. The extension length of the robotic arm is the largest when grasping the target object, and the center of gravity change caused by the weight of the object is the largest. Therefore, when the joint center of gravity influence degree is greater, the robotic arm is more likely to vibrate due to excessive acceleration when the robotic arm grasps downward due to changes in the center of gravity. At this time, it is necessary to adjust the working mode of the robotic arm according to the joint center of gravity influence degree of the robotic arm and the parameter information of the target object. When the robotic arm is greatly affected by its own weight or the weight of the grasped object is too high, the working mode of the robotic arm can be changed, such as limiting the acceleration of the robotic arm in different working modes, so as to avoid excessive acceleration of the robotic arm due to changes in the center, thereby achieving the purpose of reducing the vibration of the robotic arm when falling.

[0091] Optionally, in some embodiments, determining the working mode of the robot arm according to the influence of the joint center of gravity and the target object parameter information specifically includes:

[0092] Obtaining the weight of the target object through the target object parameter information;

[0093] Determining a gravity center influence threshold according to the gravity center influence degree of the joint, and setting the robot arm to operate in a first working mode when the weight of the target object is lower than the gravity center influence threshold;

[0094] When the weight of the target object is higher than the center of gravity influence threshold, the robotic arm is set to operate in the second working mode.

[0095] In the present application, after the working mode of the robot arm is determined, the robot arm can be controlled to perform grasping according to the determined working mode. Optionally, in some embodiments, according to the threshold interval where the joint center of gravity influence degree is located, the joint center of gravity influence degree is mapped to the corresponding center of gravity influence threshold value according to the threshold interval where the joint center of gravity influence degree is located. In specific implementation, the first working mode is the rated working mode of the robot arm, and the second working mode is the acceleration limiting mode of the robot arm. In specific implementation, for example, a proportional-integral-differential control algorithm is used to control the movement of the robot arm, wherein in the first working mode, the proportional control coefficient of the robot arm is 1, the integral control coefficient is 0.1, and the differential control coefficient is 0. The number is 0.01. In the second working mode, the robotic arm adds an acceleration feedback module. When the acceleration of the robotic arm is higher than the preset threshold, the nonlinear dead zone is connected in the forward path of the control circuit of the robotic arm through the logic circuit to realize the acceleration limitation of the robotic arm. In some embodiments, the acceleration preset threshold of the second working mode of the robotic arm is higher than the acceleration preset threshold of the first working mode. Therefore, when the robotic arm is greatly affected by its own weight or the weight of the grasped object is too high, the working mode of the robotic arm is changed, that is, the acceleration of the robotic arm is limited to avoid excessive acceleration of the robotic arm due to the change of the center, so as to achieve the purpose of reducing the vibration of the robotic arm when falling.

[0096] Preferably, in some embodiments, when the robotic arm is controlled to grasp according to the second working mode, the acceleration threshold of the robotic arm is adjusted according to the influence of the joint center of gravity. In specific implementation, the ratio between the joint center of gravity influence and the standard joint center of gravity influence can be used as an adjustment coefficient, and the acceleration threshold of the robotic arm in the second working mode is adjusted according to the adjustment coefficient, for example, the original acceleration threshold is multiplied by the adjustment coefficient.

[0097] In addition, in another aspect of the present application, in some embodiments, the present application provides a grasping device, including a grasping control unit, referring to Figure 2 , which is a schematic diagram of exemplary hardware and / or software of a grasping control unit according to some embodiments of the present application, the grasping control unit 200 includes: a processing module 201 and an execution module 202, which are described as follows:

[0098] Detection module 201, in some specific embodiments of the present application, the detection module 201 is used to start the robot arm control and determine the grasping coordinate system according to the calibrated grasping direction of the robot arm;

[0099] Processing module 202, in some specific embodiments of the present application, the processing module 202 is used to obtain the time-series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and perform time-series classification to obtain a first up-process coordinate group and a first down-process coordinate group;

[0100] The processing module 202 is further configured to perform deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robot arm;

[0101] The processing module 202 is further used to obtain the time-series coordinates of each detection point in the second link joint of the robot arm in the grasping coordinate system, obtain a second upper coordinate group and a second lower coordinate group, and perform deviation detection on the second upper coordinate group and the second lower coordinate group to obtain a second grasping phase deviation of the robot arm;

[0102] The processing module 202 is further used to measure the joint deviation of the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the influence of the joint center of gravity of the robot arm;

[0103] Execution module 203. In some specific embodiments of the present application, the execution module 202 is mainly used to obtain parameter information of the target object, determine the working mode of the robotic arm according to the influence of the joint center of gravity and the parameter information of the target object, and control the robotic arm to grasp according to the determined working mode.

[0104] The above describes in detail an example of a grasping device and a grasping method provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to executing each function.

[0105] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned capture method.

[0107] In some embodiments, reference Figure 3, which is a schematic diagram of the structure of a computer terminal device using a grabbing method according to some embodiments of the present application. Figure 3 The computer terminal device 300 shown in the figure is implemented, and the computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303 and a memory 304.

[0108] The processor 303 may be a general-purpose central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more processors for controlling the execution of a capture method in the present application.

[0109] The communication bus 301 may include a path for transmitting information between the above-mentioned components.

[0110] The memory 304 may be a read only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read only memory (EEPROM), a compact disc read only memory (CD ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 304 may exist independently and be connected to the processor 303 via the communication bus 301. The memory 304 may also be integrated with the processor 303.

[0111] The memory 304 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 303. The processor 303 is used to execute the program code stored in the memory 304. The program code may include one or more software modules. The determination of the first grasping phase deviation in the above embodiment can be implemented by the processor 303 and one or more software modules in the program code in the memory 304.

[0112] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0113] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0114] In a specific implementation, as an embodiment, a computer terminal device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0115] The above-mentioned computer terminal device may be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer terminal device.

[0116] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned crawling method.

[0117] In summary, in a grasping device and grasping method disclosed in an embodiment of the present application, the robot arm control is first started, and the grasping coordinate system is determined according to the calibrated grasping direction of the robot arm; the time series coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system are obtained and time series classification is performed to obtain a first up-range coordinate group and a first down-range coordinate group; the first up-range coordinate group and the first down-range coordinate group are used to perform deviation detection to obtain a first grasping phase deviation of the robot arm; the time series coordinates of each detection point in the second link joint on the robot arm in the grasping coordinate system are obtained to obtain a second up-range coordinate group and a second down-range coordinate group, and the second up-range coordinate group and the second down-range coordinate group are used to perform deviation detection to obtain a second grasping phase deviation of the robot arm; the joint deviation measurement is performed on the first grasping phase deviation and the second grasping phase deviation of the robot arm to obtain the joint center of gravity influence of the robot arm; finally, the target object parameter information is obtained, and the working mode of the robot arm is determined according to the joint center of gravity influence and the target object parameter information, thereby reducing the vibration of the robot arm caused by the change of the center of gravity of the robot arm and improving the grasping accuracy of the robot arm.

[0118] The above is only an embodiment of the present application, and the common knowledge such as the specific technical scheme or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical scheme of the present application, several modifications and improvements can be made, which should also be regarded as the scope of protection of the present application, and these will not affect the effect of the implementation of the present application and the practicality of the patent.

[0119] The scope of protection claimed by this application shall be based on the content of its claims. The specific implementation methods and other records in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include these modifications and variations.

Claims

1. A grasping method, characterized in that: include: Starting the robot arm control and determining the grasping coordinate system according to the calibrated grasping direction of the robot arm; Obtaining the time-series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and performing time-series classification to obtain a first up-process coordinate group and a first down-process coordinate group; Performing deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robotic arm; Acquire the time-series coordinates of each detection point in the second link joint of the robot arm in the grasping coordinate system to obtain a second up-range coordinate group and a second down-range coordinate group, perform deviation detection on the second up-range coordinate group and the second down-range coordinate group to obtain a second grasping phase deviation of the robot arm; Performing joint deviation measurement on a first grasping phase deviation and a second grasping phase deviation of the robotic arm to obtain a joint center of gravity influence degree of the robotic arm; Acquire parameter information of the target object, determine the working mode of the robot arm according to the influence of the joint center of gravity and the parameter information of the target object, and control the robot arm to grasp according to the determined working mode; The first upper coordinate group and the first lower coordinate group are used to perform deviation detection to obtain the first grasping phase deviation of the robotic arm, which specifically includes: Determine a first upstream path value according to the first upstream coordinate group; Determine a first downstream path value according to the first downstream coordinate group; Acquire a detection point distribution distance, and determine a first grasping phase deviation of the robot arm according to the detection point distribution distance, the first up-path value, and the first down-path value; The second upper coordinate group and the second lower coordinate group are used to perform deviation detection to obtain the second grasping phase deviation of the robot arm, which specifically includes: Determine a second upstream path value according to the second upstream coordinate group; Determine a second downstream path value according to the second downstream coordinate group; Acquire the detection point distribution distance of the second link joint, and determine the second grasping phase deviation of the robot arm according to the detection point distribution distance of the second link joint, the second up-path value, and the second down-path value; Among them, performing joint deviation measurement on the first grasping phase deviation and the second grasping phase deviation of the robotic arm to obtain the influence of the joint center of gravity of the robotic arm specifically includes: Get the first link length and the second link length; Determining an initial joint center of gravity influence of the robot arm according to the first link length, the second link length, the first grasping phase deviation, and the second grasping phase deviation; Determining an upstream related adjustment coefficient based on the first upstream coordinate group and the second upstream coordinate group; Determining a down-process related adjustment coefficient based on the first down-process coordinate group and the second down-process coordinate group; Performing correlation correction on the initial joint center of gravity influence degree according to the upper range correlation adjustment coefficient and the lower range correlation adjustment coefficient to obtain the joint center of gravity influence degree of the robotic arm; Wherein, the first grasping phase deviation = (the first downstream path value - the first upstream path value) / 2pi×the detection point distribution distance, the second grasping phase deviation = (the second downstream path value - the second upstream path value) / 2pi×the detection point distribution distance, where pi is the natural pi; Among them, the initial joint center of gravity influence = (first grasping phase deviation × second link length) / (second grasping phase deviation × first link length), the joint center of gravity influence = initial joint center of gravity influence × (upper range related adjustment coefficient / lower range related adjustment coefficient).

2. The method according to claim 1, characterized in that Determining the grasping coordinate system according to the calibrated grasping direction of the robot arm specifically includes: Determining a detection reference point of the robotic arm according to a calibrated grasping direction of the robotic arm; A grasping coordinate system is constructed according to the calibrated grasping direction of the robot arm and the detection reference point, and each link joint of the robot arm is set to an initial position in the grasping coordinate system.

3. The method according to claim 1, characterized in that Acquiring the time-series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and performing time-series classification to obtain the first up-process coordinate group and the first down-process coordinate group specifically includes: The three-dimensional coordinates corresponding to each detection point of the first link joint on the robot arm when grasping upward and grasping downward are respectively collected, and all the three-dimensional coordinates are converted into two-dimensional coordinates in the grasping coordinate system; Sorting the detection moments corresponding to the two-dimensional coordinates to obtain a set of time series coordinates corresponding to the detection points of the first link joint; The upward grasping time period and the downward grasping time period of the robot arm are obtained, and each time series coordinate is classified according to the corresponding grasping time period and the detection time, so as to obtain multiple upward coordinate values ​​and multiple downward coordinate values ​​and store them in the first upward coordinate group and the first downward coordinate group respectively.

4. The method according to claim 1, characterized in that Determining the working mode of the robot arm according to the influence of the joint center of gravity and the target object parameter information specifically includes: Obtaining the weight of the target object through the target object parameter information; Determining a gravity center influence threshold according to the gravity center influence degree of the joint, and setting the robot arm to operate in a first working mode when the weight of the target object is lower than the gravity center influence threshold; When the weight of the target object is higher than the center of gravity influence threshold, the robotic arm is set to operate in the second working mode.

5. The method according to claim 4, characterized in that The acceleration threshold of the second working mode of the robotic arm is higher than the acceleration threshold of the first working mode.

6. The method according to claim 1, characterized in that A visual sensor is used to obtain the time-series coordinates of each detection point in the first link joint on the robot arm in the grasping coordinate system.

7. A gripping device, which is gripped by the method according to any one of claims 1 to 6, and the gripping device comprises a gripping control unit, characterized in that: The grab control unit comprises: A detection module, used to start the control of the robot arm and determine the grasping coordinate system according to the calibrated grasping direction of the robot arm; A processing module, used for obtaining the time series coordinates of each detection point in the first link joint of the robot arm in the grasping coordinate system and performing time series classification to obtain a first up-process coordinate group and a first down-process coordinate group; The processing module is further used to perform deviation detection on the first up-range coordinate group and the first down-range coordinate group to obtain a first grasping phase deviation of the robotic arm; The processing module is further used to obtain the time-series coordinates of each detection point in the second link joint of the robot arm in the grasping coordinate system, obtain a second upper coordinate group and a second lower coordinate group, and perform deviation detection on the second upper coordinate group and the second lower coordinate group to obtain a second grasping phase deviation of the robot arm; The processing module is further used to measure the joint deviation of the first grasping phase deviation and the second grasping phase deviation of the robotic arm to obtain the influence of the joint center of gravity of the robotic arm; The execution module is used to obtain parameter information of the target object, determine the working mode of the robot arm according to the influence degree of the joint center of gravity and the parameter information of the target object, and control the robot arm to grasp according to the determined working mode.

8. A computer terminal device, characterized in that: The computer terminal device comprises a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the grabbing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the grasping method according to any one of claims 1 to 6.

Images