Grabbing method, robot arm and robot
By collecting real-time contact information on the machine's hands and adjusting the grasping posture, the problem of gripping inaccuracy caused by inaccurate object size is solved, and higher gripping accuracy is achieved.
Patent Information
- Application Number
- CN202411204331.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-19
AI Technical Summary
When existing robots grab objects, due to inaccurate object size, the manipulator's grasping posture does not match the object, which reduces the accuracy of grabbing.
By collecting real-time contact information at the tactile sensor and palm of the robot, adjusting the gripping posture of at least two finger mechanisms to match the predicted contact information, ensuring a suitable gripping posture to improve gripping accuracy.
Improves the accuracy of the robot when grabbing objects, ensuring that the robot can effectively grasp the target object.
Smart Images

Figure CN118977261A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of robotics technology, and in particular to a grasping method, a robotic arm, and a robot. Background Art
[0002] With the improvement of intelligence, people set up manipulators on robots to grab objects. In the related art, when a manipulator is needed to grab an object, it is often necessary to first determine the size of the object, and then control the manipulator to grab the object according to the size of the object. However, the problem with this solution is that when the size of the object is not accurately determined, the posture of the manipulator grabbing the object will not match the object itself, resulting in low accuracy in grabbing the object. Summary of the invention
[0003] In view of this, the embodiments of the present application at least provide a grasping method, a robotic arm, and a robot.
[0004] The technical solution of the embodiment of the present application is implemented as follows:
[0005] In a first aspect, an embodiment of the present application provides a grasping method, which is applied to a controller of a robot arm; the method comprises:
[0006] In the process of the robot arm grasping the target object, obtaining real-time contact information generated when the robot arm grasps the target object;
[0007] Based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robot hand so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information;
[0008] The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
[0009] In a second aspect, an embodiment of the present application provides a grasping method, which is applied to a controller of a robot including a robotic arm; the method comprises:
[0010] Get the size information of the target object;
[0011] Determining robot hand posture information of the robot hand based on the size information of the target object, and sending the robot hand posture information to a controller of the robot hand;
[0012] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0013] In a third aspect, an embodiment of the present application provides a robotic hand, including a controller, at least two finger mechanisms, and a palm; wherein:
[0014] The controller of the robot arm is used to obtain real-time contact information generated when the robot arm grasps the target object during the process of the robot arm grasping the target object;
[0015] The controller of the robot hand is used to adjust the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information;
[0016] The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
[0017] In a fourth aspect, an embodiment of the present application provides a robot, comprising a controller and a robot arm;
[0018] The controller of the robot is used to obtain the size information of the target object;
[0019] The controller of the robot is used to determine the robot hand posture information of the robot hand based on the size information of the target object, and send the robot hand posture information to the controller of the robot hand;
[0020] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0021] In a fifth aspect, an embodiment of the present application provides a grasping device, which is applied to a controller of a robot arm; the grasping device includes:
[0022] A first acquisition unit, used for acquiring real-time contact information generated when the robot arm grasps the target object during the process of the robot arm grasping the target object;
[0023] an adjustment unit, configured to adjust the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information;
[0024] The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
[0025] In a sixth aspect, an embodiment of the present application provides a grasping device, which is applied to a controller of a robot including a manipulator; the grasping device includes:
[0026] A second acquisition unit, used to acquire size information of the target object;
[0027] a determining unit, configured to determine robot hand posture information of the robot hand based on the size information of the target object;
[0028] A sending unit, used for sending the robot arm posture information to a controller of the robot arm;
[0029] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0030] In a seventh aspect, an embodiment of the present application provides a robot comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements some or all of the steps in the above method when executing the program.
[0031] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements some or all of the steps in the above method when executed by a processor.
[0032] In a ninth aspect, an embodiment of the present application provides a computer program product, including a computer program or instructions, which implement some or all of the steps in the above method when executed by a processor.
[0033] In the embodiment of the present application, during the process of the robot grasping the target object, the controller of the robot can obtain the real-time contact information generated when grasping the target object; and adjust the current grasping posture of at least two finger mechanisms of the robot through the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information. In this way, the current grasping posture of at least two finger mechanisms can be adjusted through the predicted contact information and the real-time contact information, and finally the contact information generated by the at least two finger mechanisms after the posture adjustment when grasping the object matches the predicted contact information, so that the robot can grasp the target object with a suitable grasping posture, thereby improving the accuracy of the robot grasping the object.
[0034] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.
[0036] Figure 1 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 1 ;
[0037] Figure 2a Schematic diagram of the structure of the robot arm provided in the embodiment of the present application Figure 1 ;
[0038] Figure 2b A second schematic diagram of the structure of the robot arm provided in the embodiment of the present application;
[0039] Figure 2c A second schematic diagram of an implementation flow of a grabbing method provided in an embodiment of the present application;
[0040] Figure 3 A schematic diagram of the structure of the finger mechanism provided in the embodiment of the present application Figure 1 ;
[0041] Figure 4 A second structural diagram of the finger mechanism provided in an embodiment of the present application;
[0042] Figure 5 A schematic diagram of the structure of the finger mechanism provided in the embodiment of the present application Figure 3 ;
[0043] Figure 6 A schematic diagram of the structure of the finger mechanism provided in the embodiment of the present application Figure 4 ;
[0044] Figure 7 A schematic diagram of the structure of the finger mechanism provided in the embodiment of the present application Figure 5 ;
[0045] Figure 8 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 3 ;
[0046] Fig. 9 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 4 ;
[0047] Fig.10 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 5 ;
[0048] Fig.11 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 6 ;
[0049] Fig.12 A schematic diagram of the implementation process of a grabbing method provided in an embodiment of the present application Figure 7 ;
[0050] Fig.13 Schematic diagram of the structure of the robot arm provided in the embodiment of the present application Figure 3 ;
[0051] Fig.14 A schematic diagram of the structure of the robot provided in an embodiment of the present application.
[0052] Reference numerals:
[0053] 1-manipulator; 11-body; 12-palmar-finger mechanism; 121-palmar-finger drive assembly; 1211-connecting seat; 1212-power push rod group; 12121-first power push rod; 12122-second power push rod; 122-palmar-finger connecting rod assembly; 1221-first connecting rod; 1222-second connecting rod; 1223-third connecting rod; 1224-fourth connecting rod; 123-palmar-finger knuckle assembly; 1231-proximal knuckle of the metacarpophalangeal finger; 1232-middle knuckle of the first metacarpophalangeal finger; 1233-middle knuckle of the second metacarpophalangeal finger; 1234-terminal knuckle of the metacarpophalangeal finger; 124-fixing plate; 13-thumb mechanism; 131-thumb drive assembly; 132-thumb knuckle group Components; 1321-proximal knuckle of thumb; 1322-middle knuckle of first thumb; 1323-middle knuckle of second thumb; 1324-terminal knuckle of thumb; 14-first rotating shaft; 15-second rotating shaft; 16-third rotating shaft; 17-fourth rotating shaft; 18-fifth rotating shaft; 19-sixth rotating shaft; 20-seventh rotating shaft; 21-eighth rotating shaft; 22-ninth rotating shaft; 23-tenth rotating shaft; 24-eleventh rotating shaft; 25-twelfth rotating shaft; 261-distance acquisition device; 271-image acquisition device; 272-fill light component; 28-tactile sensor; 1302-finger mechanism; 1303-palm; 1400-robot; 1401-controller. DETAILED DESCRIPTION
[0054] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0055] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
[0056] The terms "first / second / third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first / second / third" can be interchanged with a specific order or sequence where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing this application and are not intended to limit this application.
[0058] In order to solve the technical problem of low accuracy in grasping objects in the related art, an embodiment of the present application provides a grasping method, which can be applied to a controller of a robot arm. Figure 1 As shown, the method includes step S101 and step S102:
[0059] Step S101 , in the process of the robot arm grasping the target object, real-time contact information generated when the robot arm grasps the target object is obtained.
[0060] Here, the target object is the object to be grasped by the robot. In some embodiments, the target object can be determined based on the environmental image information around the robot. Exemplarily, after acquiring the environmental image information, the controller of the robot can determine the size of each object when it recognizes that there are objects in the environmental image information, and determine the target object based on the size of each object. It is understandable that due to the limitation of the size of the robot itself, the robot can grasp objects corresponding to the size of the robot, so the target object can be determined based on the size of each object. In other embodiments, the subject that determines the target object can be the controller of a robot, which includes the above-mentioned robot. Usually the robot has a robotic arm, and the robotic arm is deployed at the end of the robotic arm. Of course, the robotic arm can also be deployed on the robot in other ways, which is not limited here.
[0061] In some embodiments, the robot arm can grasp the target object using a preset grasping posture. The preset grasping posture may be a grasping posture pre-set in the controller of the robot arm or the controller of the robot, or a grasping posture that can be obtained from other terminals, servers, cloud storage areas, etc. through data transmission methods such as networks. It is understandable that a plurality of historical grasping postures are stored in the controller of the robot arm or the controller of the robot, and the preset grasping posture may be the grasping posture with the highest frequency of use or the highest success rate in similar scenarios among the plurality of historical grasping postures. In other embodiments, the robot arm may also grasp the target object using a real-time grasping posture. The real-time grasping posture may be determined in real time by the controller of the robot arm or the controller of the robot according to the size information of the target object.
[0062] In an embodiment of the present application, the robot hand includes at least two finger mechanisms and a palm, wherein the at least two finger mechanisms are respectively connected to the palm, and each of the at least two finger mechanisms and the palm may be provided with a tactile sensor. Exemplarily, the tactile sensor may be at least one of the following: a contact sensor, a force-torque sensor, a pressure sensor, and a slip sensor.
[0063] In some embodiments, the real-time contact information generated when the robotic arm grasps the target object can be collected by tactile sensors arranged on at least two finger mechanisms, or by tactile sensors arranged on at least two finger mechanisms and tactile sensors arranged on the palm of the robotic arm, or by tactile sensors arranged on the palm of the robotic arm.
[0064] It is understandable that the tactile sensor that collects real-time contact information is related to the current gripping posture of the robot hand grasping the target object. If the current gripping posture represents the gripping of the target object by at least two finger mechanisms, the tactile sensor that collects real-time contact information is a tactile sensor disposed on the at least two finger mechanisms; if the current gripping posture represents the gripping of the target object by at least two finger mechanisms and the palm, the tactile sensor that collects real-time contact information is a tactile sensor disposed on the at least two finger mechanisms and a tactile sensor disposed on the palm of the robot hand; if the current gripping posture represents the gripping of the target object by the palm, the tactile sensor that collects real-time contact information is a tactile sensor disposed on the palm of the robot hand. It is understandable that when the palm includes at least two movable connected parts, the object can be gripped only by the palm.
[0065] In some embodiments, if the current grasping posture represents grasping the target object by at least two finger mechanisms and a palm, but because the current grasping posture has a low match with the size information of the target object, or the position of the robot hand does not correspond to the position of the target object, it may happen that when the current grasping posture is used to grasp the target object, only the finger mechanisms or only the palm touches the target object. At this time, even if the current grasping posture represents grasping the target object by at least two finger mechanisms and a palm, the tactile sensor for collecting real-time contact information may be a tactile sensor arranged on at least two finger mechanisms, or a tactile sensor arranged on the palm of the robot hand.
[0066] Step S102: Based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robot hand so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information.
[0067] Here, the predicted contact information may be obtained based on the image information of the target object and the size information of the target object.
[0068] It is understandable that the size information can characterize the size of the target object. For target objects of different sizes, the degree of opening of at least two finger mechanisms of the robot hand can be different; and the material of the target object can be identified through image information. For objects of the same size but different materials, the grasping force output by at least two finger mechanisms of the robot hand is also different. Both the grasping force and the degree of opening of at least two finger mechanisms of the robot hand can be reflected by the contact information generated when the robot hand grasps the target object. Therefore, the predicted contact information obtained through the image information of the target object and the size information of the target object can correct the current grasping posture of at least two finger mechanisms of the robot hand, so that the robot hand can grasp the target object with a suitable grasping posture.
[0069] Among them, identifying the material of the target object through image information may include: inputting the image information into a trained neural network model to obtain the material of the target object. The training process of the neural network model may include: constructing a sample set; the sample set includes image information of objects of different materials, and each image information contains label information representing the material type of the object, and training the neural network model through the sample set to obtain a trained neural network model.
[0070] In some embodiments, the deviation information between the real-time contact information and the predicted contact information can be determined first, and then the movement information of at least two finger mechanisms can be determined based on the deviation information, and the at least two finger mechanisms can be controlled to move according to the movement information, and it can be determined whether the contact information generated by the at least two finger mechanisms after the movement matches the predicted contact information. If they match, the adjustment is completed; if they do not match, the at least two finger mechanisms are adjusted again according to the above method until the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information.
[0071] In some embodiments, the determination of the predicted contact information based on the image information of the target object and the size information of the target object may be performed by the controller of the manipulator or the controller of the robot. After the controller of the robot determines the predicted contact information, the predicted contact information may be sent to the controller of the manipulator, so that the controller of the manipulator can adjust the current grasping posture of at least two finger mechanisms of the manipulator based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information.
[0072] In some embodiments, the predicted contact information includes contact information corresponding to different tactile sensors. After obtaining the predicted contact information, the controller of the robot hand can continuously adjust the current grasping posture of at least two finger mechanisms of the robot hand so that the real-time contact information generated by the tactile sensors distributed at different positions of the robot hand matches the contact information corresponding to different tactile sensors in the predicted contact information.
[0073] In the embodiment of the present application, the controller of the robot hand acquires the real-time contact information generated when the robot hand grasps the target object during the process of grasping the target object by the robot hand; then the controller of the robot hand adjusts the current grasping posture of at least two finger mechanisms of the robot hand through the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information. In this way, the current grasping posture of the at least two finger mechanisms can be adjusted through the predicted contact information and the real-time contact information, and finally the contact information generated by the at least two finger mechanisms after the posture adjustment when grasping the object matches the predicted contact information, so that the robot hand can grasp the target object with a suitable grasping posture, thereby improving the accuracy of the robot hand grasping the object.
[0074] like Figure 2a As shown, the manipulator 1 includes a body 11 and at least two finger mechanisms; wherein the at least two finger mechanisms include a palm-finger mechanism 12 and a thumb mechanism 13. Figure 2a At least two finger mechanisms are shown to include three palm-finger mechanisms 12 and a thumb mechanism 13. In other embodiments, the number of palm-finger mechanisms 12 may also be 4. The embodiment of the present application does not limit the number of palm-finger mechanisms. The body 11 includes a palm portion (not shown), and at least two finger mechanisms are movably connected to the palm portion. Tactile sensors 28 are provided on at least two finger mechanisms and the palm portion. When the finger mechanisms and / or the palm portion grasp the target object, contact information can be collected through the tactile sensor 28.
[0075] In some embodiments, each of the at least two finger mechanisms includes a finger drive component and a finger knuckle component. When the finger mechanism is a palm-finger mechanism, the palm-finger mechanism includes a palm-finger drive component and a palm-finger knuckle component; when the finger mechanism is a thumb mechanism, the thumb mechanism includes a thumb drive component and a thumb knuckle component. Figure 2b As shown, the palm-finger mechanism 12 includes a palm-finger driving assembly 121 and a palm-finger knuckle assembly 123 , and the thumb mechanism 13 includes a thumb driving assembly 131 and a thumb knuckle assembly 132 .
[0076] In the present application embodiment, Figure 2c As shown, based on Figure 2a and Figure 2bThe above grabbing method can also be implemented through steps S201 to S203:
[0077] Step S201, receiving robot hand posture information sent by the robot controller; the robot hand posture information is determined by the robot controller based on the size information of the target object; the robot hand posture information includes the joint rotation information of the finger knuckle assembly of each finger mechanism.
[0078] Here, the robot hand posture information is the grasping posture initially adopted by the robot hand when grasping the target object, and the robot hand posture information is determined by the robot through the size information of the target object.
[0079] It is understandable that the contact information can represent the gripping force and opening degree of the robot hand when grasping the target object, that is, the accuracy of the robot hand grasping the target object can be determined through the contact information. When the robot hand approaches the target object and has not yet started to grasp the object, the contact information cannot be obtained because the robot hand has not touched the target object. At this time, it is necessary to determine the initial grasping posture (i.e., the above-mentioned robot hand posture information) adopted by the robot hand when grasping the target object. This grasping posture is not the final grasping posture of the robot hand, and the grasping posture needs to be adjusted according to the real-time contact information until the real-time contact information matches the predicted contact information.
[0080] In an embodiment of the present application, the robot controller stores correspondence between size information of different objects and different robot arm posture information. Through the size information of the target object, the robot arm posture information corresponding to the size information of the target object can be determined from multiple correspondences.
[0081] In the embodiment of the present application, the robot hand posture information includes the joint rotation information of the finger knuckle assembly of each finger mechanism. It can be understood that when the robot hand grasps an object, it actually outputs the grasping force through the rotation of the finger knuckle assembly. Therefore, the grasping posture of the robot hand can be characterized by the joint rotation information of the finger knuckle assembly.
[0082] Step S202: for each of the finger mechanisms, based on the joint rotation information of the finger knuckle assembly of the finger mechanism, determine the motion information of the finger driving assembly of the finger mechanism.
[0083] In the embodiment of the present application, the movement of the finger drive assembly can drive the rotation of the finger knuckle assembly, and the controller of the robot can control the movement of the finger drive assembly. Therefore, after obtaining the joint rotation information of the finger knuckle assembly, the controller of the robot needs to convert the joint rotation information of the finger knuckle assembly into the movement information of the finger drive assembly.
[0084] In an embodiment of the present application, the joint rotation information of the finger knuckle assembly includes the joint rotation direction, the joint rotation angle and the joint rotation speed, and the movement information of the finger drive assembly includes the movement direction, the movement distance and the movement speed. The joint rotation direction of the finger knuckle assembly corresponds to the movement direction of the finger drive assembly, the joint rotation angle of the finger knuckle assembly corresponds to the movement distance of the finger drive assembly, and the joint rotation speed of the finger knuckle assembly corresponds to the movement speed of the finger drive assembly.
[0085] Exemplarily, when the joint rotation direction of the finger knuckle assembly is clockwise, the movement direction of the finger drive assembly may be a direction close to the finger knuckle assembly; when the joint rotation direction of the finger knuckle assembly is counterclockwise, the movement direction of the finger drive assembly may be a direction away from the finger knuckle assembly.
[0086] Step S203, for each of the finger mechanisms, controlling the finger driving component of the finger mechanism to move according to the motion information, so as to drive the finger knuckle component of the finger mechanism to rotate according to the joint rotation information.
[0087] It is understandable that the motion information of the finger drive assembly of the finger mechanism includes the motion direction, motion distance and motion speed, and the motion information of the finger drive assemblies of different finger mechanisms may be the same or different. Therefore, the controller of the robot hand can control the finger drive assemblies of different finger mechanisms to move according to the motion information of the finger drive assemblies of different finger mechanisms, so as to drive the finger knuckle assemblies of different finger mechanisms to rotate according to their own joint rotation information, thereby making the posture of the robot hand in a grasping posture for grasping the target object.
[0088] In the embodiment of the present application, the joint rotation information of the finger knuckle assembly of each finger mechanism determined by the size information of the target object can be converted to obtain the motion information of the finger drive assembly of each finger mechanism, and then the finger drive assembly of each finger mechanism is controlled to move according to the motion information to drive the finger knuckle assembly of each finger mechanism to rotate according to the joint rotation information. In this way, through data conversion, the finger knuckle assembly of each finger mechanism can be converted according to the joint rotation information into the motion information of the finger drive assembly that can be controlled by the controller of the robot hand, so that the finger knuckle assembly can be driven by the finger drive assembly to rotate according to the joint rotation information, thereby improving the accuracy of controlling the robot hand to grasp the target object.
[0089] Reference Figure 2b , Figure 3 , Figure 4The palm-finger driving assembly 121 includes a connecting seat 1211 and a power push rod group 1212. The connecting seat 1211 is fixed to one side of the protective part along the second direction. A sliding groove group is provided on the connecting seat 1211. The power push rod group 1212 is located in the sliding groove group and slides relative to the sliding groove group to drive the palm-finger knuckle assembly 123 to grab the object to be grabbed. The power push rod group 1212 includes a first power push rod 12121. The sliding groove group includes a first sliding groove extending along the first direction provided on the connecting seat 1211. The first power push rod 12121 is provided in the first sliding groove. The palm-finger connecting rod assembly 122 includes a first connecting rod 1221 and a second connecting rod 1222. The joint assembly 123 includes a proximal metacarpophalangeal joint 1231, the first connecting rod 1221 is connected to the first power push rod 12121 through the first rotating shaft 14, and is connected to the proximal metacarpophalangeal joint 1231 on both sides along the third direction through the second rotating shaft 15, the second connecting rod 1222 is connected to the proximal metacarpophalangeal joint 1231 on both sides along the third direction through the third rotating shaft 16, and the second connecting rod 1222 is connected to the connecting part through the fourth rotating shaft 17; wherein, the third direction has an angle with the first direction and the second direction, the axial directions of the first rotating shaft 14, the second rotating shaft 15 and the third rotating shaft 16 are parallel to the third direction, and the axial direction of the fourth rotating shaft 17 is parallel to the direction away from the palm 111.
[0090] In the present application embodiment, based on Figure 2b , Figure 3 and Figure 4 The "controlling the finger driving component of the finger mechanism to move according to the movement information" in the above step S203 can be implemented by step S2031:
[0091] Step S2031, controlling the two first power push rods to move simultaneously along the movement direction close to the finger knuckle assembly, driving the proximal knuckles of the fingers to rotate around the first rotation axis, so that the proximal knuckles of the fingers bend toward the side close to the palm.
[0092] For example, the palm-finger mechanism is used as an example to illustrate step S2031. Figure 5 As shown, the two first power push rods 121121 of the palm-finger driving assembly of the palm-finger mechanism 12 are pushed out at the same speed at the same time in the direction close to the palm-finger knuckle assembly (i.e. Figure 5 In the direction C), at this time, the proximal metacarpophalangeal joint 1231 rotates clockwise around the axial direction of the third rotating shaft 16, thereby driving the proximal metacarpophalangeal joint 1231 to bend toward the palm side. Among them, the third rotating shaft 16 is the first rotating shaft in step S2031.
[0093] It can be understood that step S2031 is a step in which the controller of the robot arm controls the movement of a finger mechanism. Figure 5It is the finger posture presented by one of the at least two finger mechanisms after being controlled by the controller of the robot. If the at least two finger mechanisms include a thumb mechanism, since the thumb mechanism and the palm-finger mechanism have the same structure, the thumb mechanism can be controlled by referring to the steps of controlling the palm-finger mechanism. Figure 2b As shown, the thumb mechanism 13 includes a thumb drive component 131 and a thumb knuckle component 132. The thumb knuckle component 132 includes a thumb proximal knuckle 1321, a first thumb middle knuckle 1322, a second thumb middle knuckle 1323 and a thumb terminal knuckle 1324. The thumb drive component 131 can drive the thumb proximal knuckle 1321 to bend toward the palm, and drive the thumb proximal knuckle 1321 to swing along the extension direction of the plane where the palm is located.
[0094] In the embodiment of the present application, the controller of the robot arm controls the two first power push rods to move simultaneously in the direction of movement close to the finger knuckle assembly, driving the proximal knuckles of the fingers to rotate around the third rotation axis, so that the proximal knuckles of the fingers are bent toward the side close to the palm. In this way, by controlling the movement of the two first power push rods, the proximal knuckles of the fingers can be bent, so that the target object can be grasped by the bent proximal knuckles of the fingers and the palm.
[0095] Reference Figure 2b , Figure 3 and Figure 4The power push rod group 1212 includes a second power push rod 12122, the sliding groove group includes a second sliding groove extending along the first direction between two symmetrical first sliding grooves on the connecting seat 1211, and the first sliding groove is higher than the first sliding groove in the direction away from the palm 111. The palm-finger connecting rod assembly 122 includes a third connecting rod 1223 and a fourth connecting rod 1224. The third connecting rod 1223 is connected to the second power push rod 12122 through a fifth rotating shaft 18, and the third connecting rod 1223 is connected to the second connecting rod 12122 through a fifth rotating shaft 18. The rod 1222 is connected by the sixth rotating shaft 19, the outer contours of the fifth rotating shaft 18 and the sixth rotating shaft 19 are both spherical, the third connecting rod 1223 and the fourth connecting rod 1224 are connected by the seventh rotating shaft 20, the proximal metacarpophalangeal joint 1231 forms a first accommodating cavity with an opening arranged along the first direction, the third connecting rod 1223 and the fourth connecting rod 1224 are located in the first accommodating cavity, and the metacarpophalangeal joint assembly 123 includes a first metacarpophalangeal middle end joint 1232, a second metacarpophalangeal middle end joint 1233 and a terminal metacarpophalangeal joint The first metacarpal finger middle end knuckle 1232 is connected to the metacarpal finger proximal end knuckle 1231 on both sides along the third direction via the eighth rotating shaft 21, the first metacarpal finger middle end knuckle 1232 is connected to the metacarpal finger terminal knuckle 1234 on both sides along the third direction via the ninth rotating shaft 22, the first metacarpal finger middle end knuckle 1232 forms a second accommodating cavity having an opening arranged along the first direction, at least a portion of the second metacarpal finger middle end knuckle 1233 is located in the second accommodating cavity, the second metacarpal finger middle end knuckle 1233 and the metacarpal finger proximal knuckle 1234 are connected to each other via the ninth rotating shaft 22. The two sides of the fourth connecting rod 1224 and the second metacarpophalangeal middle knuckle 1233 are connected through the eleventh rotating shaft 24, and the two sides of the second metacarpophalangeal middle knuckle 1233 and the terminal metacarpophalangeal knuckle along the third direction are connected through the twelfth rotating shaft 25; wherein, the axial directions of the fifth rotating shaft 18, the sixth rotating shaft 19, the seventh rotating shaft 20, the eighth rotating shaft 21, the ninth rotating shaft 22, the tenth rotating shaft 23, the eleventh rotating shaft 24 and the twelfth rotating shaft 25 are all the same as the third direction.
[0096] When the second power push rod 12122 slides along the second sliding groove, the metacarpophalangeal terminal knuckle 1234 drives the first metacarpophalangeal middle knuckle 1232, the second metacarpophalangeal middle knuckle 1233 and the metacarpophalangeal terminal knuckle 1234 to move clockwise or counterclockwise under the rotation of the fifth rotating shaft 18, the sixth rotating shaft 19, the seventh rotating shaft 20, the eighth rotating shaft 21, the ninth rotating shaft 22, the tenth rotating shaft 23, the eleventh rotating shaft 24 and the second rotating shaft 15, thereby driving the metacarpophalangeal terminal knuckle 1234 to bend, similar to the bending of the second knuckle of a human being, so as to realize the bendable freedom of the metacarpophalangeal terminal knuckle 1234 in the metacarpophalangeal finger mechanism. In an achievable manner provided in an embodiment of the present application, the bending angle of the metacarpophalangeal terminal knuckle 1234 is from 0 degrees to a preset acute angle. Exemplarily, the preset acute angle can be 76.3 degrees.
[0097] In some embodiments, based on Figure 2b , Figure 3 and Figure 4 The "controlling the finger driving component of the finger mechanism to move according to the movement information" in the above step S203 can also be implemented by step S2032:
[0098] Step S2032, controlling the movement direction of the second power push rod away from the finger knuckle assembly, driving the first connecting member of the finger mechanism to move counterclockwise around the first rotation axis of the finger mechanism, so that the second connecting member of the finger mechanism moves in a direction away from the metacarpophalangeal knuckle assembly.
[0099] Among them, the second connecting member drives the middle knuckle of the first metacarpophalangeal to rotate clockwise around the axial direction of the second rotation axis of the finger mechanism, and the middle knuckle of the second metacarpophalangeal to rotate clockwise around the axial direction of the third rotation axis of the finger mechanism, thereby driving the terminal knuckle of the metacarpophalangeal to rotate clockwise around the axial direction of the fourth rotation axis of the finger mechanism and the fifth rotation axis of the finger mechanism, so as to bend the terminal knuckle of the metacarpophalangeal.
[0100] For example, the palm-finger mechanism is used as an example to illustrate step S2032. Figure 3 , Figure 4 and Figure 6 As shown, when the second power push rod 12122 moves in the direction away from the metacarpophalangeal knuckle assembly 123, the third connecting rod 1223 moves in the direction away from the metacarpophalangeal knuckle assembly 123. At this time, the third connecting rod 1223 moves counterclockwise around the third rotating shaft 16. At this time, the fourth connecting rod 1224 moves in the direction away from the metacarpophalangeal knuckle assembly 123. The first metacarpophalangeal middle-end knuckle 1232 rotates clockwise around the axial direction of the eighth rotating shaft 21, and the second metacarpophalangeal middle-end knuckle 1233 rotates clockwise around the axial direction of the tenth rotating shaft 23, thereby driving the metacarpophalangeal terminal knuckle 1234 to rotate clockwise around the axial direction of the ninth rotating shaft 22 and the twelfth rotating shaft 25 to achieve the bending of the metacarpophalangeal terminal knuckle 1234. Among them, the third connecting rod 1223 is the first connecting member in step S2032, the third rotating shaft 16 is the first rotating shaft in step S2032, the fourth connecting rod 1224 is the second connecting member in step S2032, the eighth rotating shaft 21 is the second rotating shaft in step S2032, the tenth rotating shaft 23 is the third rotating shaft in step S2032, the ninth rotating shaft 22 is the fourth rotating shaft in step S2032, and the twelfth rotating shaft 25 is the fifth rotating shaft in step S2032.
[0101] Reference Figure 2b , Figure 3 and Figure 4Furthermore, the power push rod group 1212 includes two first power push rods 12121, the sliding groove group includes first sliding grooves symmetrically arranged along the third direction on the connecting seat 1211, the two first power push rods 12121 are respectively arranged in the two first sliding grooves, the two first connecting rods 1221 are respectively connected to the two first power push rods 12121 through the first rotating shaft 14, and are respectively connected to the two sides of the proximal knuckles 1231 of the metacarpophalangeal along the third direction through the second rotating shaft 15, the second connecting rod 1222 is connected to the two sides of the proximal knuckles along the third direction through the third rotating shaft 16, the second connecting rod 1222 is connected to the connecting fixing plate 124 through the fourth rotating shaft 17, and the outer contours of the first rotating shaft 14 and the second rotating shaft 15 are both spherical.
[0102] Since the outer contours of the first rotating shaft 14 and the second rotating shaft 15 are both spherical, in other words, the two first connecting rods 1221 are spherically hinged to the two first power push rods 12121 and the metacarpophalangeal proximal knuckle 1231 respectively. Here, the first connecting rod 1221 can be axially deflected and swung relative to the first power push rod 12121 along the first rotating shaft 14, and correspondingly, the first connecting rod 1221 can also be axially deflected and swung relative to the metacarpophalangeal proximal knuckle 1231 along the second rotating shaft 15, so as to realize the freedom of deflection and swing of the metacarpophalangeal proximal knuckle 1231 in the metacarpophalangeal finger mechanism. When the two first power push rods 12121 are pushed out at the same speed and in opposite directions at the same time, the metacarpophalangeal proximal knuckle 1231 rotates relative to the fourth rotating shaft 17, and the rotation angle is plus or minus 27 degrees.
[0103] In some embodiments, based on Figure 2b , Figure 3 and Figure 4 The "controlling the finger driving component of the finger mechanism to move according to the movement information" in the above step S203 can also be implemented by step S2033:
[0104] Step S2033, control one of the two first power push rods to move in a direction close to the finger knuckle assembly, and the other first power push rod to move in a direction close to the finger knuckle assembly, so that the third connecting member connected to the first power push rod moving in a direction close to the finger knuckle assembly and the third connecting member of the first power push rod moving in a direction away from the finger knuckle assembly are deflected and swung.
[0105] Wherein, the deflection and swing of the third connecting members respectively corresponding to the two first power push rods can drive the proximal knuckles of the fingers to deflect and swing.
[0106] For example, the palm-finger mechanism is used as an example to illustrate step S2032. Figure 7As shown, when one of the first power push rods 12121 moves in a direction close to the proximal metacarpophalangeal joint 1231 and the other power push rod moves in a direction away from the proximal metacarpophalangeal joint 1231, the first connecting rod 1221 connected to the first power push rod 12121 moving in a direction close to the proximal metacarpophalangeal joint 1231 deflects and swings toward the other first connecting rod 1221, and the other first connecting rod 1221 also deflects and swings in the same direction. At this time, the proximal metacarpophalangeal joint 1231 rotates axially relative to the fourth rotating shaft 17, thereby achieving its deflection. Here, it should be supplemented that the direction of the deflection swing is always toward the side where the first power push rod 12121 moves in a direction away from the proximal metacarpophalangeal joint 1231. Among them, the first connecting rod 1221 is the third connecting member in step S2033.
[0107] In the embodiment of the present application, by controlling the two first power push rods, the proximal knuckles of the corresponding fingers can be deflected and swung, so that the target object can be clamped by at least two finger mechanisms that are deflected and swung.
[0108] It can be understood that when the target object is clamped by two finger mechanisms, the movement directions of the first power push rods of the two finger mechanisms are opposite, so that the deflection directions of the two finger mechanisms are opposite.
[0109] In some embodiments, Figure 8 As shown, the "adjusting the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information" in the above step S102 can also be implemented through steps S801 to S803:
[0110] Step S801: sending the real-time contact information to the controller of the robot.
[0111] Step S802, receiving robot arm posture adjustment information sent by the controller of the robot; the robot arm posture adjustment information is determined based on the real-time contact information and the predicted contact information; the predicted contact information is obtained by inputting the size information of the target object and the image information of the target object into the trained grasping model.
[0112] It is understandable that the controller of the robotic arm is a control chip with low computing power (such as MCU) and cannot perform complex algorithms. Therefore, the controller of the robotic arm needs to send real-time contact information to the controller of the robot, and the robot's controller determines the robotic arm posture adjustment information based on the real-time contact information and predicted contact information.
[0113] In some embodiments, the trained grasping model can output predicted contact information that matches the size and material of the target object based on the size information of the target object and the image information of the target object. In the embodiment of the present application, the trained grasping model can first determine the material of the target object through the image information of the target object, and then output predicted contact information that matches the size and material of the target object through the size and material of the target object.
[0114] Step S803: adjusting the current grasping posture of the at least two finger mechanisms based on the robot hand posture adjustment information.
[0115] In an embodiment of the present application, the robot arm posture adjustment information includes the joint rotation adjustment information of the finger knuckle assembly of each finger mechanism. The controller of the robot arm first converts the joint rotation adjustment information of the finger knuckle assembly of each finger mechanism to obtain the motion adjustment information of the finger driving assembly of each finger mechanism, and then controls the finger driving assembly of each finger mechanism to move according to the motion adjustment information to drive the finger knuckle assembly of the finger mechanism to rotate according to the joint rotation adjustment information.
[0116] In the embodiment of the present application, relatively accurate predicted contact information can be predicted through the size information of the target object and the image information of the target object, and then the robot hand posture adjustment information that the robot hand needs to adjust is obtained through the predicted contact information and the real-time contact information generated by the robot hand grasping the target object, and finally the current grasping posture of at least two finger mechanisms is adjusted according to the robot hand posture adjustment information. Because the robot hand posture adjustment information is determined based on the predicted contact information and the real-time contact information, the posture can be adjusted based on the current grasping posture of at least two finger mechanisms, thereby reducing the time for at least two finger mechanisms to move again and improving the efficiency of the robot hand grasping the target object. In addition, the predicted contact information is determined by the size information of the target object and the image information of the target object, so the robot hand posture adjustment information can conform to the attribute information of the target object, thereby improving the accuracy of the robot hand grasping the target object.
[0117] The present application also provides a grasping method, which is applied to a controller of a robot, wherein the robot includes the robot hand in the above embodiment. Fig. 9 As shown, the crawling method can be implemented through step S901 and step S902:
[0118] Step S901, obtaining size information of the target object.
[0119] Step S902: determining robot hand posture information of the robot hand based on the size information of the target object, and sending the robot hand posture information to a controller of the robot hand.
[0120] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0121] In an embodiment of the present application, the controller of the robot first determines the robot arm posture information of the robot arm when initially grasping the target object based on the size information of the target object, and then adjusts the robot arm posture information through the real-time contact information generated when the robot arm grasps the target object, so that the robot arm can accurately grasp the object.
[0122] In some embodiments, Fig.10 As shown, the above grabbing method can also be implemented through steps S1001 to S1005:
[0123] Step S1001, obtaining environmental image information corresponding to the robotic hand; the environmental image information is collected by an image collection device disposed on the back of the robotic hand.
[0124] Here, the environmental image information may be three-dimensional image information, and the three-dimensional image information may be acquired by an image acquisition device disposed on the back of the robot hand, wherein the image acquisition device may be a depth camera.
[0125] like Figure 2b As shown, the image acquisition device 271 is arranged on the back of the hand (not shown in the figure) of the manipulator 1.
[0126] Step S1002: determining a target object and a motion trajectory between the robot arm and the target object based on the environmental image information.
[0127] In an embodiment of the present application, the controller of the robot can perform semantic analysis on the environmental image information to determine the target object. Then, the scene is reconstructed in three dimensions based on the environmental image information, and the three-dimensional coordinates of the target object are determined in the virtual three-dimensional scene. Finally, based on the three-dimensional coordinates of the robot hand and the three-dimensional coordinates of the target object, the motion trajectory between the robot hand and the target object is obtained through a trajectory generation algorithm. Exemplarily, the trajectory generation algorithm can be based on optimization-based trajectory planning.
[0128] Step S1003, in the process of controlling the robot arm to move along the motion trajectory, based on the real-time image information acquired by the image acquisition device and the distance information between the target object and the robot arm, the motion trajectory is corrected.
[0129] Here, the distance information is collected by a distance collection device disposed in the accommodation space of the palm of the robot hand. Exemplarily, the distance collection device may be a laser distance measuring device or a time of flight (ToF) sensor.
[0130] like Figure 2a As shown, the manipulator 1 includes a body 11, the body 11 forms a receiving space, and the distance acquisition device 261 is arranged in the receiving space.
[0131] It is understandable that when the distance between the manipulator and the target object is relatively far, the image acquisition device provided on the back of the manipulator can acquire real-time image information of the target object, so that when the manipulator moves along the motion trajectory, the motion trajectory can be corrected based on the real-time image information acquired by the image acquisition device. The real-time image information includes the target object and the surrounding environment of the target object, so the motion trajectory can be corrected in real time during the movement process through the real-time image information to avoid obstacles in the surrounding environment.
[0132] When the manipulator approaches the target object, that is, the distance between the manipulator and the target object is close, since the image acquisition device is set on the back of the manipulator, it may not be possible to acquire real-time image information including the target object. At this time, the distance acquisition device set in the palm can be used to acquire the distance information between the target object and the manipulator, and the motion trajectory can be corrected again based on the distance information until the manipulator is in a space where it can grasp the target object.
[0133] In the embodiment of the present application, the motion trajectory can be updated in real time by using the real-time image information collected by the image acquisition device disposed on the back of the robot hand and the distance information between the target object and the robot hand collected by the distance acquisition device disposed in the accommodation space of the palm of the robot hand. In this way, the robot hand can avoid obstacles in the surrounding environment during movement, so that the robot hand can smoothly reach the space where it can grab the target object.
[0134] In some embodiments, the above step S1003 of “correcting the motion trajectory based on the real-time image information acquired by the image acquisition device and the distance information between the target object and the robot arm” can be implemented through steps S10031 and S10032:
[0135] Step S10031, based on the real-time image information acquired by the image acquisition device, correct the motion trajectory.
[0136] It can be understood that correcting the motion trajectory by real-time image information means that the distance between the robot and the target object is relatively far, and the real-time image information collected by the image acquisition device contains the target object. Therefore, in this stage, the motion trajectory of the robot can be corrected by the real-time image information collected by the image acquisition device.
[0137] In some embodiments, Figure 2b As shown, the robot arm 1 further includes a fill light 272, which is disposed on the top of the image acquisition device 271. Exemplarily, the fill light 272 may be an LED fill light. When the robot arm grasps an object in a dark environment, the fill light may be turned on, so that the image acquisition device can also acquire clearer real-time image information in a dark environment.
[0138] Step S10032: When the target object cannot be identified based on the real-time image information, the motion trajectory is corrected again based on the distance information between the target object and the robot arm.
[0139] It is understandable that, in general, when the robot arm grasps an object, the palm of the robot arm faces the object, and the image acquisition device is set on the back of the robot arm. When the robot arm approaches the target object, the image acquisition device cannot capture the image of the target object due to the occlusion of the palm. Therefore, when the target object cannot be identified based on the real-time image information, it means that the robot arm has approached the target object. At this time, because the real-time image information collected by the image acquisition device cannot recognize the target object, it is no longer possible to continue to correct the motion trajectory based on the real-time image information. Therefore, it is necessary to collect the distance information between the target object and the robot arm through the distance acquisition device set on the palm, and continue the motion trajectory through the distance information between the target object and the robot arm until the robot arm is in a space where it can grasp the target object.
[0140] Step S1004, determining whether the robot arm is in a space where it can grasp the target object.
[0141] Step S1005: controlling the robot arm to grasp the target object.
[0142] In the embodiment of the present application, after the motion trajectory is corrected, the robot hand can be controlled to move along the corrected motion trajectory, and it is determined in real time whether the robot hand is in a space where the target object can be grasped. If the robot hand is not in a space where the target object can be grasped, the above step S1003 is executed, and if the robot hand is in a space where the target object can be grasped, step S1005 is executed.
[0143] In the embodiment of the present application, the distance information between the target object and the robot arm can be used to determine whether the robot arm is in a space where the target object can be grasped. When the distance information is less than or equal to the preset distance information, it is determined that the robot arm is in a space where the target object can be grasped; when the distance information is greater than the preset distance information, it is determined that the robot arm is not in a space where the target object can be grasped.
[0144] In an embodiment of the present application, the controller of the robot can send a preset grasping posture to the controller of the robotic arm, so that the controller of the robotic arm adopts the preset grasping posture to control the two finger mechanisms and the palm of the robotic arm to grasp the target object.
[0145] In the embodiment of the present application, in the initial stage of the robot grasping the target object, the real-time image information can be used to correct the motion trajectory. When the robot approaches the target object, that is, the real-time image information cannot identify the target object, the distance information between the target object and the robot can be used to correct the motion trajectory again. In this way, different data can be used to correct the motion trajectory of the robot at different stages of the robot grasping the target object, thereby improving the accuracy of the corrected motion trajectory.
[0146] In some embodiments, Fig.11 As shown, the above grabbing method can also be implemented through steps S1101 to S1104:
[0147] Step S1101, receiving real-time contact information sent by a controller of the robotic arm when the robotic arm grasps a target object.
[0148] Step S1102: input the size information of the target object and the image information of the target object into the trained grasping model to obtain predicted contact information.
[0149] It is understandable that objects of different materials have different weights even if they are of the same size. Similarly, objects of different sizes have different weights even if they are of the same material. For objects of different weights, the robot arm needs to use different contact pressures to grasp objects of different weights.
[0150] Therefore, in the embodiment of the present application, a first sample set and a second sample set can be constructed, wherein the image sample set includes a plurality of sample images, and each sample image contains a label representing the material of the object in the sample image, and the grasping model can be trained through the image sample set, so that the grasping model after training can determine the material of the target image based on the image information of the target object. The second sample set includes sample information of different materials and different sizes, and contact information of each sample information, and the grasping model can be trained through the second sample set, so that the grasping model after training can determine the predicted contact information based on the size information and material of the target object.
[0151] In the embodiment of the present application, the predicted contact information includes contact information corresponding to different contact positions. It is understandable that when the robot grasps an object, different parts of the robot need to output contact pressure. Therefore, the contact position in the predicted contact information can correspond to the part of the robot that needs to output contact pressure.
[0152] Step S1103: compare the predicted contact information with the real-time contact information to obtain contact difference information.
[0153] In an embodiment of the present application, the real-time contact information also includes the contact pressures corresponding to different contact positions. When comparing the predicted contact information with the real-time contact information, it is necessary to compare the predicted contact information and the real-time contact information of the corresponding positions, that is, the contact difference information includes the contact difference information corresponding to different contact positions. Exemplarily, the predicted contact information includes that the contact pressure at position 1 is 2Pa, the contact pressure at position 2 is 3Pa, and the contact pressure at position 3 is 4Pa, and the real-time contact information includes that the contact pressure at position 1 is 0.5Pa, and the contact pressure at position 3 is 2Pa, then the contact difference information can include: the contact difference information at position 1 is 1.5Pa, the contact pressure at position 2 is 3Pa, and the contact pressure at position 3 is 2Pa.
[0154] Step S1104: generating the robot arm posture adjustment information based on the contact difference information, and sending the robot arm posture adjustment information to the controller of the robot arm.
[0155] In the embodiment of the present application, the robot hand posture adjustment information includes the joint rotation adjustment information of the finger knuckle assembly of the target finger mechanism in at least two finger mechanisms, wherein the target finger mechanism refers to the finger mechanism that needs posture adjustment.
[0156] It can be understood that the contact position in the contact difference information refers to the distribution position information of the tactile sensors distributed on the robot hand. Therefore, the target finger mechanism among the at least two finger mechanisms can be determined by the contact position in the contact difference information. Exemplarily, when the at least two finger mechanisms include finger mechanism 1, finger mechanism 2, finger mechanism 3 and finger mechanism 4, if the contact position in the contact difference information is position 1, position 2 and position 3, if the tactile sensors corresponding to position 1 and position 2 are on finger mechanism 1, and the tactile sensor corresponding to position 3 is on finger mechanism 2, then finger mechanism 1 and finger mechanism 2 can be determined as target finger mechanisms.
[0157] As for the joint rotation adjustment information, since different contact pressures correspond to the rotation information of the finger knuckle assembly, the rotation information of the finger knuckle assembly can be determined by the contact pressure in the contact difference information.
[0158] In an embodiment of the present application, the predicted contact information can be determined based on the size information of the target object and the image information of the target object through the trained grasping model. In this way, the predicted contact information that matches the material and size of the target object can be accurately determined through the trained grasping model. Then the contact difference information between the predicted contact information and the real-time contact information is determined. Finally, based on the contact difference information, the robot hand posture adjustment information is generated. In this way, by converting the contact difference information between the predicted contact information and the real-time contact information, the posture adjustment information that the robot hand needs to adjust can be obtained, so that the target object can be accurately grasped.
[0159] In some embodiments, Fig.12 As shown, the above grabbing method can also be implemented through steps S1201 to S1214:
[0160] In step S1201, the controller of the dexterous hand obtains RGB images and depth image information of the surrounding environment of the dexterous hand through a depth camera.
[0161] Among them, the LED fill light on the back of the hand is turned on in dark environments to compensate for image problems caused by insufficient light.
[0162] In step S1202, the controller of the dexterous hand sends the RGB image and depth image information of the surrounding environment of the dexterous hand to the robot body controller.
[0163] Among them, the image information can be fed back to the robot body controller in real time through a high-speed USB data cable.
[0164] In step S1203, the robot body controller reconstructs the scene in three dimensions based on the RGB image and depth image information of the surrounding environment, and performs semantic analysis on the RGB image and depth image information of the surrounding environment to determine the grasped objects in the surrounding environment and identify the names of the objects in the scene.
[0165] In step S1204, the robot body controller calculates the distance information from the object to the camera, and calculates the three-dimensional coordinates of the pixel points corresponding to the features of the grasped object in the virtual three-dimensional space in combination with the coordinates in the 2D plane.
[0166] Step S1205: The robot body controller calculates the motion trajectory between the dexterous hand coordinate system and the object coordinate system according to the obtained three-dimensional coordinates.
[0167] Step S1206: During the movement along the motion trajectory, the robot body controller uses the images collected in real time by the depth camera to identify obstacles in the path, allowing the dexterous hand to avoid them, thereby guiding the dexterous hand to reach the vicinity of the target object.
[0168] Step S1207: When no object can be identified in the image captured by the depth camera, the robot body controller sends an instruction to the controller of the dexterous hand for obtaining object distance information and three-dimensional data of the measured object.
[0169] Step S1208: The controller of the dexterous hand responds to the instruction, obtains the object distance information and the three-dimensional data of the measured object collected by the TOF sensor, and sends the object distance information and the three-dimensional data of the measured object to the robot body controller.
[0170] Step S1209: During the movement of the dexterous hand, the robot body controller continuously corrects the motion trajectory based on the object distance information obtained by the TOF sensor and the three-dimensional data of the object being measured, and adjusts the moving position and speed of the dexterous hand in real time to make the dexterous hand approach the object.
[0171] Step S1210, when the grasping space of the dexterous hand is aligned with the shape space of the target object, the robot body controller sends a grasping posture corresponding to the size of the grasped object to the controller of the dexterous hand.
[0172] In step S1211, the controller of the dexterous hand starts the closing movement of the dexterous hand based on the grasping posture corresponding to the size of the grasped object sent by the robot body controller, and encloses the object in the palm.
[0173] Here, the alignment of the grasping space of the dexterous hand with the shape space of the target object means that the coordinates of the dexterous hand coincide with the coordinates of the object, the coordinates of the dexterous hand are at the end coordinates of the motion trajectory, and at least one of the object and the dexterous hand are in contact.
[0174] Step S1212: The controller of the dexterous hand obtains the contact pressure information collected by the tactile sensor and sends the contact pressure information to the robot body controller.
[0175] In step S1213, the robot body controller compares the contact pressure information with the grasping data set to obtain a contact difference portion, and sends the contact difference portion to the controller of the dexterous hand.
[0176] Wherein, step S1213 can be implemented by the following steps:
[0177] In step S12131, the robot body controller inputs the size information and image information of the object into the grasping model to obtain a relatively appropriate contact force for each contact point.
[0178] In step S12132, the robot body controller compares the contact pressure information collected by the sensor with the contact force output by the grasping large model to obtain the contact difference part, and sends the contact difference part to the controller of the dexterous hand.
[0179] Step S1214: The controller of the dexterous hand controls the angle of each movable joint of the dexterous hand based on the contact difference part, and adjusts the contact pressure of the tactile sensors at various parts.
[0180] In the embodiment of the present application, the controller of the dexterous hand adjusts the contact pressure of the tactile sensors in various parts, so that the grasping force of the dexterous hand for objects of different materials and shapes can be reasonably controllable, ensuring a steady and safe grasp.
[0181] In some embodiments, Fig.13 As shown, the embodiment of the present application also provides a robot hand 1, which includes a controller 1301, at least two finger mechanisms 1302 ( Fig.13 Two finger mechanisms 1302) and a palm portion 1303 are shown, wherein:
[0182] The controller 1301 of the robot arm is used to obtain real-time contact information generated when the robot arm grasps the target object during the process of the robot arm grasping the target object;
[0183] The controller 1301 of the robot hand is used to adjust the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information;
[0184] The real-time contact information is collected by the tactile sensors arranged on the at least two finger mechanisms 1302, or the real-time contact information is collected jointly by the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm 1303 of the robot hand.
[0185] In some embodiments, the controller 1301 of the robotic arm is also used to receive robotic arm posture information sent by the controller of the robot; the robotic arm posture information is determined by the controller of the robot based on the size information of the target object; the robotic arm posture information includes joint rotation information of the finger knuckle assembly of each of the finger mechanisms; for each of the finger mechanisms, based on the joint rotation information of the finger knuckle assembly of the finger mechanism, the motion information of the finger driving assembly of the finger mechanism is determined; for each of the finger mechanisms, the finger driving assembly of the finger mechanism is controlled to move according to the motion information to drive the finger knuckle assembly of the finger mechanism to rotate according to the joint rotation information.
[0186] In some embodiments, the finger drive assembly includes two first power push rods; the finger knuckle assembly includes proximal finger knuckles; the motion information includes a motion direction close to the finger knuckle assembly; the controller 1301 of the robot arm is also used to control the two first power push rods to move simultaneously along the motion direction close to the finger knuckle assembly, driving the proximal finger knuckles to rotate around the first rotation axis, so that the proximal finger knuckles are bent toward the side close to the palm.
[0187] In some embodiments, the finger knuckle assembly includes a first metacarpophalangeal middle knuckle, a second metacarpophalangeal middle knuckle and a terminal knuckle; the finger drive assembly includes a second power push rod; the motion information includes a motion direction away from the finger knuckle assembly; the controller 1301 of the robot arm is also used to control the motion direction of the second power push rod away from the finger knuckle assembly, driving the first connecting member of the finger mechanism to move counterclockwise around the first rotation axis of the finger mechanism, so that the second connecting member of the finger mechanism moves in a direction away from the metacarpophalangeal knuckle assembly; wherein, the second connecting member drives the first metacarpophalangeal middle knuckle to rotate clockwise around the axial direction of the second rotation axis of the finger mechanism, and the second metacarpophalangeal middle knuckle to rotate clockwise around the axial direction of the third rotation axis of the finger mechanism, thereby driving the terminal metacarpophalangeal knuckle to rotate clockwise around the axial direction of the fourth rotation axis of the finger mechanism and the axial direction of the fifth rotation axis of the finger mechanism, so that the terminal metacarpophalangeal knuckle is bent.
[0188] In some embodiments, the motion information includes a direction away from the finger knuckle assembly; the controller 1301 of the robot arm is also used to control one of the two first power push rods to move in a direction close to the finger knuckle assembly, and the other first power push rod to move in a direction away from the finger knuckle assembly, so that the third connecting member connected to the first power push rod moving in the direction close to the finger knuckle assembly and the third connecting member of the first power push rod moving in the direction away from the finger knuckle assembly deflect and swing; wherein the deflection and swing of the third connecting members corresponding to the two first power push rods respectively can drive the deflection and swing of the proximal knuckles of the fingers.
[0189] In some embodiments, the controller 1301 of the robotic arm is also used to send the real-time contact information to the controller of the robot; receive the robotic arm posture adjustment information sent by the controller of the robot; the robotic arm posture adjustment information is determined based on the real-time contact information and the predicted contact information; the predicted contact information is obtained by inputting the size information of the target object and the image information of the target object into the trained grasping model; based on the robotic arm posture adjustment information, adjust the current grasping posture of the at least two finger mechanisms.
[0190] In some embodiments, Fig.14 As shown, the embodiment of the present application further provides a robot 1400, the robot 1400 includes a controller 1401 and a robot hand 1, wherein:
[0191] The controller 1401 of the robot is used to obtain the size information of the target object;
[0192] The controller 1401 of the robot is used to determine the robot hand posture information of the robot hand based on the size information of the target object, and send the robot hand posture information to the controller of the robot hand;
[0193] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0194] The controller 1401 of the robot is also used to obtain environmental image information corresponding to the robot hand; the environmental image information is collected by an image acquisition device arranged on the back of the robot hand; based on the environmental image information, the target object and the motion trajectory between the robot hand and the target object are determined; in the process of controlling the robot hand to move along the motion trajectory, based on the real-time image information collected by the image acquisition device and the distance information between the target object and the robot hand, the motion trajectory is corrected until the robot hand is in a space where it can grasp the target object; the distance information is collected by a distance acquisition device arranged in the accommodating space of the palm of the robot hand.
[0195] The controller 1401 of the robot is also used to correct the motion trajectory based on the real-time image information collected by the image acquisition device; when the target object cannot be identified based on the real-time image information, the motion trajectory is corrected again based on the distance information between the target object and the robot arm.
[0196] The controller 1401 of the robot is also used to receive real-time contact information sent by the controller of the robot arm when the robot arm grasps the target object; input the size information of the target object and the image information of the target object into the trained grasping model to obtain predicted contact information; compare the predicted contact information with the real-time contact information to obtain contact difference information; generate the robot arm posture adjustment information based on the contact difference information, and send the robot arm posture adjustment information to the controller of the robot arm.
[0197] The embodiment of the present application provides a gripping device, which is applied to a controller of a robot arm; the gripping device comprises:
[0198] A first acquisition unit, used for acquiring real-time contact information generated when the robot arm grasps the target object during the process of the robot arm grasping the target object;
[0199] an adjustment unit, configured to adjust the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information;
[0200] The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
[0201] The present application provides a grasping device, which is applied to a controller of a robot including a manipulator; the grasping device includes:
[0202] A second acquisition unit, used to acquire size information of the target object;
[0203] a determining unit, configured to determine robot hand posture information of the robot hand based on the size information of the target object;
[0204] A sending unit, used for sending the robot arm posture information to a controller of the robot arm;
[0205] Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
[0206] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.
[0207] It should be noted that in the embodiment of the present application, if the above-mentioned data processing method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.
[0208] An embodiment of the present application provides a robot, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.
[0209] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.
[0210] The embodiment of the present application provides a computer program, including a computer readable code, and when the computer readable code is executed in a computer device, a processor in the computer device executes some or all of the steps in the above method. The computer device may be a robot or a device deployed on the robot, which is not limited here.
[0211] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.
[0212] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.
[0213] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.
[0214] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0215] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A grasping method, characterized in that: The grasping method is applied to a controller of a robot arm; the method comprises: In the process of the robot arm grasping the target object, obtaining real-time contact information generated when the robot arm grasps the target object; Based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robot hand so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
2. The grasping method according to claim 1, characterized in that: Each of the at least two finger mechanisms comprises a finger drive assembly and a finger knuckle assembly; the method further comprises: Receiving robot hand posture information sent by a controller of the robot; the robot hand posture information is determined by the controller of the robot based on the size information of the target object; the robot hand posture information includes joint rotation information of the finger knuckle assembly of each finger mechanism; For each of the finger mechanisms, based on the joint rotation information of the finger knuckle assembly of the finger mechanism, determining the motion information of the finger driving assembly of the finger mechanism; For each of the finger mechanisms, a finger driving component of the finger mechanism is controlled to move according to the motion information, so as to drive a finger knuckle component of the finger mechanism to rotate according to the joint rotation information.
3. The grasping method according to claim 2, characterized in that: The finger drive assembly includes at least one of the following: two first power push rods, and a second power push rod; the finger knuckle assembly includes a proximal knuckle of a finger, and / or the finger knuckle assembly includes a first metacarpal middle knuckle, a second metacarpal middle knuckle and a terminal knuckle; The finger driving component controlling the finger mechanism to move according to the motion information includes at least one of the following: In the case where the motion information includes a motion direction close to the finger knuckle assembly, the two first power push rods are controlled to move simultaneously along the motion direction close to the finger knuckle assembly, driving the proximal knuckles of the fingers to rotate around the first rotation axis, so that the proximal knuckles of the fingers are bent toward a side close to the palm; When the motion information includes the motion direction away from the finger knuckle assembly, the second power push rod is controlled to move away from the finger knuckle assembly, driving the first connecting member of the finger mechanism to move counterclockwise around the first rotation axis of the finger mechanism, so that the second connecting member of the finger mechanism moves in the direction away from the metacarpophalangeal knuckle assembly; wherein the second connecting member drives the middle-end knuckle of the first metacarpophalangeal to rotate clockwise around the axial direction of the second rotation axis of the finger mechanism, and the middle-end knuckle of the second metacarpophalangeal to rotate clockwise around the axial direction of the third rotation axis of the finger mechanism, thereby driving the terminal knuckle of the metacarpophalangeal to rotate clockwise around the axial direction of the fourth rotation axis of the finger mechanism and the axial direction of the fifth rotation axis of the finger mechanism, so that the terminal knuckle of the metacarpophalangeal is bent.
4. The grasping method according to claim 3, characterized in that: The motion information includes a direction away from the finger knuckle assembly; The finger driving component controlling the finger mechanism to move according to the motion information includes: Control one of the two first power push rods to move in a direction close to the finger knuckle assembly and the other first power push rod to move in a direction away from the finger knuckle assembly, so that the third connecting member connected to the first power push rod moving in the direction close to the finger knuckle assembly and the third connecting member connected to the first power push rod moving in the direction away from the finger knuckle assembly deflect and swing; Wherein, the deflection and swing of the third connecting members respectively corresponding to the two first power push rods can drive the proximal knuckles of the fingers to deflect and swing.
5. The grasping method according to any one of claims 1 to 4, characterized in that: The adjusting the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information includes: sending the real-time contact information to a controller of the robot; receiving robot hand posture adjustment information sent by the controller of the robot; the robot hand posture adjustment information is determined based on the real-time contact information and the predicted contact information; the predicted contact information is obtained by inputting the size information of the target object and the image information of the target object into the trained grasping model; Based on the robot hand posture adjustment information, the current grasping posture of the at least two finger mechanisms is adjusted.
6. A grasping method, characterized in that: The grasping method is applied to a controller of a robot including a robot hand; the method comprises: Get the size information of the target object; Determining robot hand posture information of the robot hand based on the size information of the target object, and sending the robot hand posture information to a controller of the robot hand; Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
7. The grasping method according to claim 6, characterized in that: The method further comprises at least one of the following: Acquire environmental image information corresponding to the robotic hand; the environmental image information is collected by an image acquisition device disposed on the back of the robotic hand; based on the environmental image information, determine a target object and a motion trajectory between the robotic hand and the target object; In the process of controlling the robot hand to move along the motion trajectory, based on the real-time image information collected by the image acquisition device and the distance information between the target object and the robot hand, the motion trajectory is corrected until the robot hand is in a space where the target object can be grasped; the distance information is collected by the distance acquisition device set in the accommodation space of the palm of the robot hand; Receive real-time contact information generated when the robot grasps a target object, which is sent by the controller of the robot; input the size information of the target object and the image information of the target object into the trained grasping model to obtain predicted contact information; compare the predicted contact information with the real-time contact information to obtain contact difference information; generate the robot posture adjustment information based on the contact difference information, and send the robot posture adjustment information to the controller of the robot.
8. The grasping method according to claim 7, characterized in that: The correcting the motion trajectory based on the real-time image information collected by the image acquisition device and the distance information between the target object and the robot arm includes: Based on the real-time image information collected by the image acquisition device, correct the motion trajectory; In the case where the target object cannot be identified based on the real-time image information, the motion trajectory is corrected again based on the distance information between the target object and the robot arm.
9. A robot arm, characterized in that: The robotic hand comprises a controller, at least two finger mechanisms and a palm portion; The controller of the robot arm is used to obtain real-time contact information generated when the robot arm grasps the target object during the process of the robot arm grasping the target object; The controller of the robot hand is used to adjust the current grasping posture of at least two finger mechanisms of the robot hand based on the real-time contact information, so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; The real-time contact information is collected by at least one of a tactile sensor arranged on the at least two finger mechanisms and a tactile sensor arranged on the palm of the robot hand.
10. A robot, characterized in that: The robot comprises a controller and a robot arm; The controller of the robot is used to obtain the size information of the target object; The controller of the robot is used to determine the robot hand posture information of the robot hand based on the size information of the target object, and send the robot hand posture information to the controller of the robot hand; Among them, the controller of the robotic arm is used to obtain real-time contact information generated when the robotic arm grasps the target object in the process of grasping the target object based on the robotic arm posture information; based on the real-time contact information, adjust the current grasping posture of at least two finger mechanisms of the robotic arm so that the contact information generated by the at least two finger mechanisms after the posture adjustment matches the predicted contact information; the real-time contact information is collected by at least one of the tactile sensors arranged on the at least two finger mechanisms and the tactile sensors arranged on the palm of the robotic arm.
Citation Information
Cited By
Manipulator grabbing alignment method and system and storage medium
CN119458379A
Manipulator grasping alignment method, system and storage medium
CN119458379B
Bionic hand control method and device, bionic hand and robot
CN120715916A
Finger mechanism and robot
WO2026045995A1
Gripping method, robotic arm, and robot
WO2026046162A1
