Dexterous hand control method, dexterous hand control device, dexterous hand and robot

Abstract

The invention relates to the technical field of robots, in particular to a dexterous hand control method, a dexterous hand control device, a dexterous hand and a robot, and solves the problem of poor universality of the dexterous hand. The dexterous hand control method comprises the steps of firstly receiving teleoperation data, then determining a target angle of a driving motor according to first mapping data and the teleoperation data, and then sending the target angle of the driving motor to the driving motor to enable the driving motor to rotate to the target angle so as to enable the driving motor to drive a joint to move. Therefore, the fingers are made to move to the target position or the joints are made to rotate to the target angle, control over the joints is achieved, the dexterous hand is further controlled to achieve the teleoperation action, the purpose that the dexterous hand is controlled to achieve various actions through teleoperation equipment is achieved, and the universality of the dexterous hand is improved.

Description

Technical Field

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

[0002] With the continuous development of robotics technology, robots can be used to perform tasks in many environments that are unfavorable to humans. The dexterous hand is the end effector of the robot, which is used to perform tasks. Therefore, whether the dexterous hand is powerful or not is related to whether the task can be completed safely and accurately.

[0003] The dexterous hands in the related art can only complete specific instructions and perform specific actions, such as making a fist, stretching fingers, etc., and have poor versatility. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a dexterous hand control method, a dexterous hand control device, a dexterous hand and a robot, which solve the problem of poor versatility of the dexterous hand.

[0005] In a first aspect, an embodiment of the present application provides a dexterous hand control method, which is applied to a dexterous hand, wherein the dexterous hand includes a palm, at least one finger and at least one drive motor, the finger includes multiple joints and multiple knuckles, one knuckle of one finger is connected to the palm through one joint, and adjacent knuckles of one finger are connected through one joint, and the drive motor is connected to at least one joint and is configured to drive the joint to move so as to achieve the movement of the dexterous hand; wherein the dexterous hand control method includes: receiving remote operation data, the remote operation data includes target position data and / or target angle data, the target position data is used to characterize the target position data of the finger input by the remote operation device, and the target angle data is used to characterize the target angle data of the joint input by the remote operation device; based on a first mapping relationship and the remote operation data, determining the target angle of the drive motor, wherein the first mapping relationship is determined based on the structure of the dexterous hand; sending the target angle of the drive motor to the drive motor so that the drive motor rotates to the target angle.

[0006] In some embodiments, the first mapping relationship includes: a mapping relationship between the target position data and the target angle data and a mapping relationship between the target angle of the drive motor and the target angle of the joint; wherein, determining the target angle of the drive motor based on the first mapping relationship and the teleoperation data includes: when the teleoperation data includes the target position data, solving the target angle of the joint based on the mapping relationship between the target position data and the target angle data and the target position data, and determining a solution result; when the solution result is no solution, controlling the state of the drive motor to remain unchanged; when the solution result is a solution, determining the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

[0007] In some embodiments, based on the mapping relationship between the target position data and the target angle data and the target position data, solving the target angle of the joint and determining the solution result includes: scaling the target position data based on a scaling factor to obtain scaled target position data; based on the mapping relationship between the target position data and the target angle data and the scaled target position data, solving the target angle of the joint and determining the solution result.

[0008] In some embodiments, the remote operation device includes an operating glove; before the target position data is scaled based on the scaling factor to obtain the scaled target position data, it also includes: determining the first motion space data of the dexterous hand based on the geometric relationship between the joints and the knuckles and the coupling relationship between the joints, wherein the first motion space data of the dexterous hand is used to characterize the motion range of the dexterous hand; determining the scaling factor based on the first motion space data of the dexterous hand and the second motion space data of the operating glove.

[0009] In some embodiments, the number of fingers is multiple; when the solution result is a solution, the target angle of the drive motor is determined based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint, including: performing collision detection based on a collision detection algorithm and the target angles of each of the multiple joints to determine the collision detection result; when the collision detection result is a collision, controlling the state of the drive motor to remain unchanged; when the solution result is a solution and the collision detection result is no collision, determining the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

[0010] In some embodiments, the dexterous hand also includes a tactile sensor, which is arranged on the finger, and the tactile sensor is configured to detect the force condition of the finger and generate a sensing value; wherein, when the solution result is a solution and the collision detection result is no collision, the target angle of the drive motor is determined based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint, including: receiving the sensing value sent by the tactile sensor; when the sensing value is greater than a preset value, controlling the state of the drive motor to remain unchanged; when the solution result is a solution, the collision detection result is no collision and the sensing value is less than or equal to the preset value, based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint, determining the target angle of the drive motor.

[0011] In some embodiments, determining the target angle of the drive motor based on the first mapping relationship and the teleoperation data includes: when the teleoperation data includes the target angle data, normalizing and denormalizing the target angle data based on the second mapping relationship to determine the actual target angle of the joint, wherein the second mapping relationship is determined based on the motion range of the teleoperation device and the motion range of the dexterous hand; and determining the target angle of the drive motor based on the first mapping relationship and the actual target angle of the joint.

[0012] In some embodiments, the dexterous hand also includes at least one position sensor, at least one of the position sensors is connected to at least one of the joints, and the position sensor is configured to detect the current angle of the corresponding joint, wherein the dexterous hand control method also includes: receiving the current angle of the joint; determining the current angle of the drive motor based on a third mapping relationship and the current angle of the joint, wherein the third mapping relationship is determined based on the connection relationship between the drive motor and the joint; and sending the current angle of the drive motor to the drive motor.

[0013] In a second aspect, an embodiment of the present application provides a dexterous hand control device, which is applied to a dexterous hand, wherein the dexterous hand includes a palm, at least one finger and at least one drive motor, the finger includes multiple joints and multiple knuckles, one knuckle of one finger is connected to the palm through one joint, and the adjacent knuckles of one finger are connected through one joint, and the drive motor is connected to at least one joint and is configured to drive the joint to move so as to achieve the movement of the dexterous hand; wherein the dexterous hand control device includes: a receiving module, configured to receive teleoperation data, the teleoperation data includes target position data and / or target angle data, the target position data is used to characterize the target position data of the finger input by the teleoperation device, and the target angle data is used to characterize the target angle data of the joint input by the teleoperation device; a calculating module, configured to determine the target angle of the drive motor based on a first mapping relationship and the teleoperation data, wherein the first mapping relationship is determined based on the structure of the dexterous hand; a sending module, configured to send the target angle of the drive motor to the drive motor so that the drive motor rotates to the target angle.

[0014] In the third aspect, an embodiment of the present application provides a dexterous hand, comprising: a palm; at least one finger, the finger comprising multiple joints and multiple knuckles, one knuckle of the finger being connected to the palm via one joint, and adjacent knuckles of the finger being connected via one joint; at least one drive motor connected to at least one joint and configured to drive the joint to move; a controller, communicatively connected to the drive motor and configured to control the rotation of the drive motor using the dexterous hand control method mentioned in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a robot, comprising: a main body; and at least one dexterous hand mentioned in the third aspect, connected to the main body.

[0016] A dexterous hand control method provided in an embodiment of the present application first receives remote operation data, then determines the target angle of a drive motor based on first mapping data and the remote operation data, and then sends the target angle of the drive motor to the drive motor, so that the drive motor rotates to the target angle, so that the drive motor drives the joint to move, thereby moving the finger to the target position or rotating the joint to the target angle, thereby controlling the joint, and then controlling the dexterous hand to perform remote operation actions, thereby realizing the use of remote operation equipment to control the dexterous hand to perform various actions, such as picking up and placing objects, pressing switches, opening and closing doors, threading a needle, etc., thereby improving the versatility of the dexterous hand. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components.

[0018] Figure 1 Shown is a schematic diagram of an application scenario of the dexterous hand provided in one embodiment of the present application.

[0019] Figure 2 The figure is a flow chart of a dexterous hand control method provided in one embodiment of the present application.

[0020] Figure 3 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0021] Figure 4 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0022] Figure 5 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0023] Figure 6 Shown is a schematic diagram of the first motion space data of the dexterous hand provided by an embodiment of the present application.

[0024] Figure 7 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0025] Figure 8 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0026] Fig. 9 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0027] Fig.10 Shown is a flow chart of a dexterous hand control method provided in another embodiment of the present application.

[0028] Fig.11 Shown is a schematic structural diagram of a dexterous hand control device provided in one embodiment of the present application.

[0029] Fig.12 Shown is a schematic structural diagram of a robot provided in one embodiment of the present application.

[0030] Fig.13 Shown is a schematic structural diagram of an electronic device provided in one embodiment of the present application.

[0031] Reference numerals:

[0032] 1. Robot; 2. Main body; 3. Dexterous hand; 31. Palm; 32. Fingers; 321. Joints; 322. Knuckles; 33. Driving motor; 4. Controller; 5. Remote control equipment. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The dexterous hand in the related art can only complete specific instructions and realize specific actions, such as making a fist, stretching fingers, etc., and has poor versatility. The inventors have found that the dexterous hand can be controlled by a teleoperation device. For example, the teleoperation device can be made into the shape of a glove. The user wears the glove to do some actions, and then the dexterous hand imitates the action of the glove, so that the dexterous hand can realize various actions and improve the versatility of the dexterous hand.

[0035] The structure of the dexterous hand and the dexterous hand control method are described in detail below with reference to the accompanying drawings.

[0036] Figure 1 The figure shows a schematic diagram of an application scenario of the dexterous hand provided by an embodiment of the present application. Figure 1 As shown, the dexterous hand 3 includes a palm 31, at least one finger 32 and at least one driving motor 33. The finger 32 includes a plurality of joints 321 and a plurality of knuckles 322, one knuckle 322 of a finger 32 is connected to the palm 31 via a joint 321, and adjacent knuckles 322 of a finger 32 are connected via a joint 321. The driving motor 33 is connected to at least one joint 321 and is configured to drive the joint 321 to move so as to realize the movement of the dexterous hand 3.

[0037] Exemplarily, the execution subject of the dexterous hand control method is the controller 4. The controller 4 can receive data, process data and send data. The controller 4 can be a logic controller, a microprogram controller, a computer, a tablet, a mobile phone, a server, etc.

[0038] Exemplarily, the teleoperation device 5 may be an operation glove, an operation finger sleeve, etc. The controller 4 can be in communication connection with the teleoperation device 5 and the driving motor 33 of the dexterous hand 3 .

[0039] against Figure 1In the dexterous hand 3, the knuckles 322 are represented by a single-line rectangular frame, the joints 321 are represented by a circle, the driving motor 33 is represented by a double-line rectangular frame, and the palm 31 is represented by a thick solid-line rectangular frame.

[0040] Figure 2 FIG. 1 is a flow chart of a dexterous hand control method provided by an embodiment of the present application. Figure 2 As shown, the dexterous hand control method includes the following steps.

[0041] Step 100, receiving teleoperation data.

[0042] Specifically, the teleoperation data includes target position data and / or target angle data. For example, the teleoperation data may include only target position data, only target angle data, or both target position data and target angle data.

[0043] Exemplarily, the target position data is used to represent the target position of the finger 32 input by the teleoperation device 5. For example, the target position data may be the coordinates of the fingertip position of the finger 32, or may be the coordinates of other preset positions of the finger 32.

[0044] Exemplarily, the target angle data is used to represent the target angle data of the joint 321 input by the teleoperation device 5. For example, the target angle data may be the angle that the joint 321 needs to rotate. Specifically, if a user wears an operating glove and a joint of the user's finger rotates 30 degrees, the corresponding position of the operating glove will also bend 30 degrees, and 30 degrees may be the target angle data.

[0045] Step 200 : determining a target angle of the drive motor 33 based on the first mapping relationship and the teleoperation data.

[0046] Specifically, the first mapping relationship is determined based on the structure of the dexterous hand 3. In other words, each dexterous hand 3 corresponds to a unique first mapping relationship, and therefore, the first mapping relationship can be input into the controller 4 in advance.

[0047] Exemplarily, the drive motor 33 is connected to the joint 321, so there is a unique reduction ratio between the drive motor 33 and the joint 321, that is, there is a first mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321. When the target angle of the joint 321 is known, the target angle of the drive motor 33 can be determined according to the first mapping relationship and the target angle of the joint 321. In other words, when the teleoperation data includes target angle data, the first mapping relationship can be the reduction ratio of the drive motor 33 and the joint 321. For example, the joint 321 is directly driven by the drive motor 33, then the drive motor 33 rotates 10 degrees, and the joint 321 rotates 10 degrees. For another example, the reduction ratio of the drive motor 33 to the joint 321 is 2, then the drive motor 33 rotates 10 degrees, and the joint 321 rotates 5 degrees.

[0048] Exemplarily, in the case where the teleoperation data includes target position data, the target position data can be first converted into target angle data, and then the target angle data can be converted into the target angle of the drive motor 33. Specifically, since the mechanical structure of a dexterous hand 3 is unique, there is a mapping relationship between the target position data and the target angle data. Therefore, when the target position data is known, the target angle of the joint 321 can be determined based on the mapping relationship between the target position data and the target angle data. In other words, there is a unique functional relationship f between the target position data and the target angle data, and the target position data is equal to the product of f and the target angle data. The first mapping relationship can be the product of the reduction ratio of the drive motor 33 and the joint 321 and f.

[0049] Step 300 , sending the target angle of the driving motor 33 to the driving motor 33 , so that the driving motor 33 rotates to the target angle.

[0050] Exemplarily, after the target angle of the drive motor 33 is sent to the drive motor 33, the drive motor 33 can rotate according to the target angle, thereby rotating to the target angle. Exemplarily, the drive motor 33 generally knows the current angle. After the drive motor 33 receives the target angle, the target angle is subtracted from the current angle to obtain a relative angle. Then, after the drive motor 33 rotates the relative angle, it reaches the target angle.

[0051] The dexterous hand control method provided in the embodiment of the present application first receives remote operation data, then determines the target angle of the drive motor 33 based on the first mapping data and the remote operation data, and then sends the target angle of the drive motor 33 to the drive motor 33, so that the drive motor 33 rotates to the target angle, so that the drive motor 33 drives the joint 321 to move, thereby moving the finger 32 to the target position or rotating the joint 321 to the target angle, thereby controlling the joint 321, and then controlling the dexterous hand 3 to perform remote operation actions, thereby realizing the use of the remote operation device 5 to control the dexterous hand 3 to perform various actions, and improving the versatility of the dexterous hand 3.

[0052] Figure 3 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 2 The present application is extended based on the embodiment shown Figure 3 The embodiment shown is described below in detail. Figure 3 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0053] like Figure 3 As shown, based on the first mapping relationship and the teleoperation data, determining the target angle of the drive motor 33 includes the following steps.

[0054] Step 210, determining whether the teleoperation data includes target location data.

[0055] When the teleoperation data includes the target position data, step 220 is executed; when the teleoperation data does not include the target position data, step 260 is executed.

[0056] Specifically, the first mapping relationship includes: a mapping relationship between target position data and target angle data and a mapping relationship between a target angle of the drive motor 33 and a target angle of the joint 321. The mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 is equal to the mapping relationship between the rotation angle of the drive motor 33 and the rotation angle of the joint 321.

[0057] For example, the target position data is generally represented by coordinates, the target angle data is generally represented by angle values, and the data length of the target position data is generally different from the data length of the target angle data. The controller 4 can determine whether the received remote operation data is the target position data or the target angle data according to the data length of the received remote operation data.

[0058] Step 220, based on the mapping relationship between the target position data and the target angle data and the target position data, solve the target angle of the joint 321 and determine the solution result.

[0059] Specifically, the mechanical structure of the dexterous hand 3 is unique, so there is a mapping relationship between the target position data and the target angle data. Therefore, when the target position data is known, the target angle of the joint 321 can be determined according to the mapping relationship between the target position data and the target angle data.

[0060] Step 230, determine whether the solution has a solution.

[0061] Specifically, it is determined whether the solution result has a solution. If the solution result is that there is no solution, step 240 is executed. If the solution result is that there is a solution, step 250 is executed.

[0062] Step 240, controlling the state of the driving motor 33 to remain unchanged.

[0063] In actual application, when solving the target angle of the joint 321, it may be encountered that there is no solution. When there is no solution, it can be considered that the finger 32 cannot be controlled to reach the target position by rotating the joint 321, so the state of the control drive motor 33 can be kept unchanged to prevent damage to the dexterous hand 3.

[0064] Step 250 , determining the target angle of the drive motor 33 based on the mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 and the target angle of the joint 321 .

[0065] If the solution is found to be a solution, it means that the finger 32 can be controlled to reach the target position by rotating the joint 321 , so the target angle of the drive motor 33 can be determined based on the target angle of the joint 321 and the first mapping relationship.

[0066] Step 260 : determining a target angle of the drive motor 33 based on the target angle data and the first mapping relationship.

[0067] In practical applications, the teleoperation data is target position data or target angle data. When it is determined that the teleoperation data is not target position data, the teleoperation data is target angle data.

[0068] Figure 4 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 3 The present application is extended based on the embodiment shown Figure 4 The embodiment shown is described below in detail. Figure 4 The embodiment shown and Figure 3 The differences and similarities of the illustrated embodiments are not described in detail.

[0069] like Figure 4As shown, based on the mapping relationship between the target position data and the target angle data and the target position data, solving the target angle of the joint 321 and determining the solution result include the following steps.

[0070] Step 221 , scaling the target position data based on the scaling factor to obtain scaled target position data.

[0071] Exemplarily, the scaling factor may be determined according to the size of the dexterous hand 3 and the size of the teleoperation device 5. In practical applications, the scaling factor may be input into the controller 4 in advance.

[0072] Step 222, based on the mapping relationship between the target position data and the target angle data and the scaled target position data, solve the target angle of the joint 321 and determine the solution result.

[0073] Since the size of the remote control device 5 and the size of the dexterous hand 3 may be different, the scaled target position data is obtained by scaling the target position data, which facilitates the conversion of the position data of the remote control device 5 into the position data of the dexterous hand 3, and then facilitates the subsequent calculation of the rotation angle of the drive motor 33.

[0074] Figure 5 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 4 The present application is extended based on the embodiment shown Figure 5 The embodiment shown is described below in detail. Figure 5 The embodiment shown and Figure 4 The differences and similarities of the illustrated embodiments are not described in detail.

[0075] like Figure 5 As shown, before scaling the target position data based on the scaling factor to obtain the scaled target position data, the following steps are also included.

[0076] Step 400 , determining first motion space data of the dexterous hand 3 based on the geometric relationship between the joints 321 and the knuckles 322 and the coupling relationship between the joints 321 .

[0077] Exemplarily, the teleoperation device 5 includes an operation glove.

[0078] Exemplarily, the first motion space data of the dexterous hand 3 is used to characterize the motion range of the dexterous hand 3 .

[0079] Figure 6 FIG. 1 is a schematic diagram of the first motion space data of the dexterous hand provided by an embodiment of the present application. Figure 6As shown, blue represents the range of motion of the thumb of the dexterous hand 3, green represents the range of motion of the index finger of the dexterous hand 3, gray represents the range of motion of the middle finger of the dexterous hand 3, yellow represents the range of motion of the ring finger of the dexterous hand 3, and rose represents the range of motion of the little finger of the dexterous hand 3. In other words, Figure 6 In the figure, the four figures located at the top represent the motion range of the little finger of the dexterous hand 3, the motion range of the ring finger of the dexterous hand 3, the motion range of the middle finger of the dexterous hand 3, and the motion range of the index finger of the dexterous hand 3 from left to right, and the figure located at the lower right corner represents the motion range of the thumb of the dexterous hand 3. Figure 6 The units of the X-axis, Y-axis, and Z-axis are all meters.

[0080] Step 450 : determining a scaling factor based on the first motion space data of the dexterous hand 3 and the second motion space data of the operating glove.

[0081] Exemplarily, the second motion space data of the operating glove is an attribute of the operating glove, and each operating glove corresponds to unique second motion space data. The second motion space data of the operating glove is used to characterize the range of motion that the operating glove can achieve when the user is wearing the operating glove for exercise.

[0082] Exemplarily, determining the scaling factor based on the first motion spatial data of the dexterous hand 3 and the second motion spatial data of the operating glove can be performed as follows: calculating the ratio of the first motion spatial data of the dexterous hand 3 to the second motion spatial data of the operating glove, and determining the ratio as the scaling factor.

[0083] The zoom factor is determined by the first motion space data of the dexterous hand 3 and the second motion space data of the operating glove, and the zoom ratios of the dexterous hand 3 and the operating glove during the movement are compared to make the zoom factor more accurate.

[0084] Figure 7 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 3 The present application is extended based on the embodiment shown Figure 7 The embodiment shown is described below in detail. Figure 7 The embodiment shown and Figure 3 The differences and similarities of the illustrated embodiments are not described in detail.

[0085] like Figure 7 As shown, when the solution result is that there is a solution, based on the mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 and the target angle of the joint 321, the target angle of the drive motor 33 is determined, including the following steps.

[0086] Step 251 , performing collision detection based on the collision detection algorithm and the target angles of the plurality of joints 321 , and determining a collision detection result.

[0087] Exemplarily, there are multiple fingers 32 , and collision may occur between the multiple fingers 32 .

[0088] Exemplarily, the collision detection algorithm may be a Flexible Collision Library (FCL) collision detection algorithm or other collision detection algorithms, as long as it can detect whether a collision occurs between multiple fingers 32. Specifically, the FCL collision detection algorithm is an efficient collision detection library, which is mainly used to process collision detection problems between geometric bodies.

[0089] Step 252, determining whether there is a collision in the collision detection result.

[0090] When the collision detection result is that there is a collision, step 253 is executed. When the solution result is that there is a solution and the collision detection result is that there is no collision, step 254 is executed.

[0091] Step 253, controlling the state of the driving motor 33 to remain unchanged.

[0092] Step 254 , determining the target angle of the drive motor 33 based on the mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 and the target angle of the joint 321 .

[0093] By means of collision detection, collision between fingers 32 can be prevented, thereby preventing damage to the dexterous hand 3.

[0094] Figure 8 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 7 The present application is extended based on the embodiment shown Figure 8 The embodiment shown is described below in detail. Figure 8 The embodiment shown and Figure 7 The differences and similarities of the illustrated embodiments are not described in detail.

[0095] like Figure 8 As shown, when the solution result is a solution and the collision detection result is no collision, the target angle of the drive motor 33 is determined based on the mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 and the target angle of the joint 321, including the following steps.

[0096] Step 255, receiving the sensing value sent by the tactile sensor.

[0097] Exemplarily, the dexterous hand 3 further includes a tactile sensor, which is disposed on the finger 32 and configured to detect the force applied to the finger 32 and generate a sensing value, and then send the generated sensing value to the controller 4. The tactile sensor may be a force sensor, a strain gauge, or the like.

[0098] Step 256, determining whether the sensed value is greater than a preset value.

[0099] When the sensing value is greater than the preset value, step 257 is executed. When the solution result is that there is a solution, the collision detection result is that there is no collision, and the sensing value is less than or equal to the preset value, step 258 is executed.

[0100] Exemplarily, the preset value can be set according to actual requirements. For example, the preset value can be the maximum force value that the dexterous hand 3 can withstand. For example, the preset value can be 80% of the maximum force value that the dexterous hand 3 can withstand.

[0101] Step 257, controlling the state of the driving motor 33 to remain unchanged.

[0102] Step 258 , determining the target angle of the drive motor 33 based on the mapping relationship between the target angle of the drive motor 33 and the target angle of the joint 321 and the target angle of the joint 321 .

[0103] For example, when the sensed value is greater than a preset value, if the drive motor 33 continues to rotate, the dexterous hand 3 may be subjected to a greater force, resulting in damage to the dexterous hand 3. Therefore, it is necessary to control the state of the drive motor 33 to remain unchanged to prevent damage to the dexterous hand 3.

[0104] Fig. 9 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 2 The present application is extended based on the embodiment shown Fig. 9 The embodiment shown is described below in detail. Fig. 9 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0105] like Fig. 9 As shown, based on the first mapping relationship and the teleoperation data, determining the target angle of the drive motor 33 includes the following steps.

[0106] Step 500 , based on the second mapping relationship, normalize and denormalize the target angle data to determine the actual target angle of the joint 321 .

[0107] Exemplarily, it is possible to first determine whether the teleoperation data includes target angle data. If the teleoperation data includes target angle data, the target angle data is normalized and denormalized based on the second mapping relationship to determine the actual target angle of the joint 321.

[0108] For example, step 500 may also be performed when the teleoperation data does not include target position data.

[0109] Exemplarily, the second mapping relationship is determined based on the motion range of the teleoperation device 5 and the motion range of the dexterous hand 3. Exemplarily, the second mapping relationship may be a proportional relationship between the motion range of the teleoperation device 5 and the motion range of the dexterous hand 3. For example, the teleoperation device 5 is an operating glove, the user wears the operating glove, a certain joint of the user's finger rotates 30 degrees, and the joint 321 at the corresponding position of the dexterous hand 3 also rotates 30 degrees, then the second mapping relationship is that the teleoperation device 5 rotates 30 degrees, and the joint 321 at the corresponding position of the dexterous hand 3 also rotates 30 degrees. For example, the teleoperation device 5 is an operating glove, the user wears the operating glove, a certain joint of the user's finger rotates 60 degrees, and the joint 321 at the corresponding position of the dexterous hand 3 rotates 30 degrees, then the second mapping relationship is that the teleoperation device 5 rotates 60 degrees, and the joint 321 at the corresponding position of the dexterous hand 3 also rotates 30 degrees.

[0110] Exemplarily, the normalization process is to scale the target angle data according to the second mapping relationship so that the data falls into a specific interval. Denormalization is to scale the data within the specific interval according to the second mapping relationship so that the data within the specific interval is converted into the actual target angle of the joint 321. For example, if the second mapping relationship is that the target angle data is twice the actual target angle, then the normalization process can be reduced by one tenth of the ratio, and the denormalization process can be enlarged by 5 times the ratio. For example, if the target angle data is 60 degrees, it will be 6 degrees after normalization, and 30 degrees after denormalization.

[0111] Step 600 , determining a target angle of the drive motor 33 based on the first mapping relationship and the actual target angle of the joint 321 .

[0112] In actual applications, the motion ranges of the teleoperation device 5 and the dexterous hand 3 may be different, so normalization and denormalization are used to determine the actual target angle of the joint 321 to ensure that the target angle of the drive motor 33 is the actual target angle to which the drive motor 33 needs to rotate.

[0113] Fig.10 FIG. 1 is a flow chart of a dexterous hand control method provided by another embodiment of the present application. Figure 2 The present application is extended based on the embodiment shown Fig.10The embodiment shown is described below in detail. Fig.10 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0114] like Fig.10 As shown, the dexterous hand control method also includes the following steps.

[0115] Step 710 , receiving the current angle of the joint 321 .

[0116] Specifically, the dexterous hand 3 further includes at least one position sensor, and the at least one position sensor is connected to at least one joint 321 , and the position sensor is configured to detect the current angle of the corresponding joint 321 .

[0117] Step 720 , determining the current angle of the drive motor 33 based on the third mapping relationship and the current angle of the joint 321 .

[0118] Specifically, the third mapping relationship is determined based on the connection relationship between the driving motor 33 and the joint 321. In other words, each dexterous hand 3 corresponds to a unique third mapping relationship, and therefore, the third mapping relationship can be input into the controller 4 in advance.

[0119] Exemplarily, the drive motor 33 is connected to the joint 321, so there is a unique reduction ratio between the drive motor 33 and the joint 321, that is, there is a third mapping relationship between the current angle of the drive motor 33 and the current angle of the joint 321. When the current angle of the joint 321 is known, the current angle of the drive motor 33 can be determined based on the third mapping relationship and the current angle of the joint 321. In other words, the third mapping relationship can be the reduction ratio of the drive motor 33 and the joint 321. For example, the joint 321 is directly driven by the drive motor 33, then the drive motor 33 rotates 10 degrees, and the joint 321 rotates 10 degrees. For another example, the reduction ratio of the drive motor 33 to the joint 321 is 2, then the drive motor 33 rotates 10 degrees, and the joint 321 rotates 5 degrees. Exemplarily, the third mapping relationship is equal to the first mapping relationship.

[0120] Step 730 , sending the current angle of the drive motor 33 to the drive motor 33 .

[0121] In actual applications, the drive motor 33 can determine the current angle, and no other sensors or devices are required to provide the current angle of the drive motor 33. However, in some special cases, for example, when the drive motor 33 fails, the drive motor 33 cannot establish a mathematical relationship between the rotation of the joint 321 and the rotation of the motor. At this time, the drive motor 33 can refer to the current angle sent by the controller 4 to improve the accuracy of the rotation of the drive motor 33.

[0122] Exemplarily, the rotation angle of the driving motor 33 is a difference between a target angle of the driving motor 33 and a current angle of the driving motor 33 .

[0123] Fig.11 FIG. 1 is a schematic diagram of the structure of a dexterous hand control device provided by an embodiment of the present application. Fig.11 As shown, the dexterous hand control device 800 includes a receiving module 810 , a calculating module 820 and a sending module 830 .

[0124] A dexterous hand control device is applied to a dexterous hand, which includes a palm, at least one finger and at least one driving motor. The fingers include multiple joints and multiple knuckles. One knuckle of a finger is connected to the palm through a joint, and adjacent knuckles of a finger are connected through a joint. The driving motor is connected to at least one joint and is configured to drive the joint to move so as to realize the movement of the dexterous hand.

[0125] The receiving module 810 is configured to receive teleoperation data, the teleoperation data including target position data and / or target angle data, the target position data is used to characterize the target position data of the finger input by the teleoperation device, and the target angle data is used to characterize the target angle data of the joint input by the teleoperation device. The calculating module 820 is configured to determine the target angle of the driving motor based on the first mapping relationship and the teleoperation data, wherein the first mapping relationship is determined based on the structure of the dexterous hand. The sending module 830 is configured to send the target angle of the driving motor to the driving motor so that the driving motor rotates to the target angle.

[0126] In some embodiments, the first mapping relationship includes: a mapping relationship between target position data and target angle data and a mapping relationship between a target angle of a drive motor and a target angle of a joint. The computing module 820 is further configured to solve the target angle of a joint and determine a solution result based on the mapping relationship between the target position data and the target angle data and the target position data when the teleoperation data includes the target position data; when the solution result is that there is no solution, control the state of the drive motor to remain unchanged; when the solution result is that there is a solution, determine the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

[0127] In some embodiments, the calculation module 820 is further configured to scale the target position data based on the scaling factor to obtain the scaled target position data; based on the mapping relationship between the target position data and the target angle data and the scaled target position data, solve the target angle of the joint and determine the solution result.

[0128] In some embodiments, the teleoperation device includes an operation glove. The dexterous hand control device 800 further includes a motion space solving module 840 and a scaling factor solving module 850 .

[0129] The motion space solving module 840 is configured to determine the first motion space data of the dexterous hand based on the geometric relationship between the joints and the knuckles and the coupling relationship between the joints, and the first motion space data of the dexterous hand is used to characterize the motion range of the dexterous hand. The scaling factor solving module 850 is configured to determine the scaling factor based on the first motion space data of the dexterous hand and the second motion space data of the operating glove.

[0130] In some embodiments, the number of fingers is multiple. The calculation module 820 is further configured to perform collision detection based on the collision detection algorithm and the target angles of the multiple joints to determine the collision detection result; when the collision detection result is a collision, control the state of the drive motor to remain unchanged; when the solution result is a solution and the collision detection result is no collision, determine the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

[0131] In some embodiments, the dexterous hand further includes a tactile sensor, which is disposed on a finger, and is configured to detect the force applied to the finger and generate a sensing value. The calculation module 820 is further configured to receive the sensing value sent by the tactile sensor; when the sensing value is greater than a preset value, the state of the drive motor is controlled to remain unchanged; when the solution result is a solution, the collision detection result is no collision, and the sensing value is less than or equal to the preset value, the target angle of the drive motor is determined based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

[0132] In some embodiments, the computing module 820 is further configured to, when the teleoperation data includes target angle data, perform normalization and denormalization on the target angle data based on a second mapping relationship to determine the actual target angle of the joint, wherein the second mapping relationship is determined based on the motion range of the teleoperation device and the motion range of the dexterous hand; and determine the target angle of the drive motor based on the first mapping relationship and the actual target angle of the joint.

[0133] In some embodiments, the dexterous hand further comprises at least one position sensor, the at least one position sensor is connected to at least one joint, and the position sensor is configured to detect the current angle of the corresponding joint. The dexterous hand control device 800 further comprises a current angle receiving module 860, a current angle calculating module 870 and a current angle sending module 880.

[0134] The current angle receiving module 860 is configured to receive the current angle of the joint. The current angle calculating module 870 is configured to determine the current angle of the drive motor based on the third mapping relationship and the current angle of the joint, wherein the third mapping relationship is determined based on the connection relationship between the drive motor and the joint. The current angle sending module 880 is configured to send the current angle of the drive motor to the drive motor.

[0135] An embodiment of the present application also provides a dexterous hand. Figure 1 The dexterous hand shown includes: a palm 31 , at least one finger 32 , at least one driving motor 33 and a controller 4 .

[0136] The finger 32 includes a plurality of joints 321 and a plurality of knuckles 322. A knuckle 322 of a finger 32 is connected to the palm 31 via a joint 321, and adjacent knuckles 322 of a finger 32 are connected via a joint 321. At least one drive motor 33 is connected to at least one joint 321 and is configured to drive the joint 321 to move. The controller 4 is in communication connection with the drive motor 33 and is configured to control the rotation of the drive motor 33 using the dexterous hand control method of the above embodiment.

[0137] Since the controller 4 of the dexterous hand 3 uses the dexterous hand control method of the above embodiment to control the rotation of the driving motor 33, the dexterous hand 3 has all the technical features and technical effects of the dexterous hand control method, which will not be repeated here.

[0138] Fig.12 FIG. 1 is a schematic diagram of the structure of a robot provided by an embodiment of the present application. Fig.12 As shown, the robot 1 includes: a main body 2 and at least one dexterous hand 3.

[0139] The dexterous hand 3 is connected to the main body 2. The main body 2 can be the structure of the body part of a humanoid robot, or the structure of the arm part of an industrial robot, which is not specifically limited in this application.

[0140] Since the robot 1 includes the dexterous hand 3 mentioned in the above embodiment, the robot 1 has all the technical features and technical effects of the dexterous hand 3, which will not be described in detail here.

[0141] In the embodiments of the present application, if the connection form is not clearly defined, the connection form may be a detachable connection form such as bolts and nuts, screws, buckles, magnets, etc. If there is no special requirement for a non-detachable connection form in some connections, a non-detachable connection may be made by welding, bonding, etc.

[0142] Below, reference Fig.13 An electronic device according to an embodiment of the present disclosure is described. Fig.13 Shown is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0143] like Fig.13 As shown, the electronic device 1300 includes one or more processors 1310 and a memory 1320 .

[0144] The processor 1310 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 1300 to perform desired functions.

[0145] The memory 1320 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 1310 may run the program instructions to implement the image evaluation methods of the various embodiments of the present disclosure mentioned above and / or other desired functions. Various contents such as target fundus images may also be stored in the computer-readable storage medium.

[0146] In one example, the electronic device 1300 may further include: an input device 1330 and an output device 1340 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0147] The input device 1330 may include, for example, a keyboard, a mouse, etc. The output device 1340 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0148] Of course, to simplify, Fig.13 Only some of the components related to the present disclosure in the electronic device 1300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 1300 may also include any other appropriate components.

[0149] In addition to the above methods and devices, embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the image evaluation method according to various embodiments of the present disclosure described above in this specification.

[0150] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0151] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the image evaluation method according to various embodiments of the present disclosure described above in this specification.

[0152] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0153] The phrases "one embodiment", "an embodiment", etc. mentioned in the specification indicate that the embodiment described may include a specific feature, structure or characteristic, but not every embodiment may include the specific feature, structure or characteristic. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it is within the knowledge of those skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments, whether explicitly or not explicitly described.

[0154] It should be understood that “on,” “above,” and “over” in this disclosure should be interpreted in the broadest manner, so that “on” not only means “directly on something,” but also includes the meaning of “on something” with intervening features or layers therebetween, and “above” or “over” not only includes the meaning of “above” or “over,” but also may include the meaning of “above” or “over something” with no intervening features or layers therebetween (i.e., directly on something).

[0155] Additionally, spatially relative terms, such as "below," "below," "beneath," "above," "above," etc., may be used herein for ease of description to describe the relationship of one component or feature to other components or features as shown in the figures. The spatially relative terms are intended to encompass different orientations of the component in use or operation in addition to the orientation depicted in the figures. The device may be otherwise oriented (rotated 90 degrees or at other orientations), and the spatially relative descriptors used herein may likewise be interpreted accordingly.

[0156] 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.

[0157] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A dexterous hand control method, characterized in that: Applied to a dexterous hand, the dexterous hand comprises a palm, at least one finger and at least one driving motor, the finger comprises a plurality of joints and a plurality of knuckles, one knuckle of one finger is connected to the palm via one of the joints, and an adjacent knuckle of one finger is connected via one of the joints, the driving motor is connected to at least one of the joints and is configured to drive the joint to move, so as to realize the movement of the dexterous hand; Wherein, the dexterous hand control method comprises: receiving teleoperation data, the teleoperation data comprising target position data and / or target angle data, the target position data being used to represent data of a target position of the finger input by a teleoperation device, and the target angle data being used to represent data of a target angle of the joint input by the teleoperation device; Determining a target angle of the drive motor based on a first mapping relationship and the teleoperation data, wherein the first mapping relationship is determined based on the structure of the dexterous hand; The target angle of the driving motor is sent to the driving motor, so that the driving motor rotates to the target angle.

2. The dexterous hand control method according to claim 1, characterized in that: The first mapping relationship includes: a mapping relationship between the target position data and the target angle data and a mapping relationship between the target angle of the drive motor and the target angle of the joint; Wherein, determining the target angle of the drive motor based on the first mapping relationship and the teleoperation data includes: In the case where the teleoperation data includes the target position data, based on the mapping relationship between the target position data and the target angle data and the target position data, solving the target angle of the joint and determining a solution result; When the solution result is that there is no solution, controlling the state of the driving motor to remain unchanged; When the solution result is that there is a solution, the target angle of the drive motor is determined based on a mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

3. The dexterous hand control method according to claim 2, characterized in that: The step of solving the target angle of the joint based on the mapping relationship between the target position data and the target angle data and the target position data, and determining the solution result includes: Based on the scaling factor, scaling the target position data to obtain scaled target position data; Based on the mapping relationship between the target position data and the target angle data and the scaled target position data, the target angle of the joint is solved and the solution result is determined.

4. The dexterous hand control method according to claim 3, characterized in that: The remote operation device includes an operation glove; Before scaling the target position data based on the scaling factor to obtain the scaled target position data, the method further includes: Based on the geometric relationship between the joints and the knuckles and the coupling relationship between the joints, determining first motion space data of the dexterous hand, wherein the first motion space data of the dexterous hand is used to characterize the motion range of the dexterous hand; The scaling factor is determined based on the first motion space data of the dexterous hand and the second motion space data of the operating glove.

5. The dexterous hand control method according to claim 2, characterized in that: The number of the fingers is multiple; When the solution result is that there is a solution, determining the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint includes: Perform collision detection based on a collision detection algorithm and the target angles of each of the plurality of joints, and determine a collision detection result; When the collision detection result is that there is a collision, controlling the state of the driving motor to remain unchanged; When the solution result is that there is a solution and the collision detection result is that there is no collision, the target angle of the drive motor is determined based on a mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

6. The dexterous hand control method according to claim 5, characterized in that: The dexterous hand further comprises a tactile sensor, which is arranged on the finger and configured to detect the force applied to the finger and generate a sensing value; Wherein, when the solution result is that there is a solution and the collision detection result is that there is no collision, determining the target angle of the drive motor based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint includes: Receiving the sensing value sent by the tactile sensor; When the sensing value is greater than a preset value, the state of the driving motor is controlled to remain unchanged; When the solution result is a solution, the collision detection result is no collision and the sensor value is less than or equal to the preset value, the target angle of the drive motor is determined based on the mapping relationship between the target angle of the drive motor and the target angle of the joint and the target angle of the joint.

7. The dexterous hand control method according to any one of claims 1 to 6, characterized in that: The step of determining the target angle of the drive motor based on the first mapping relationship and the teleoperation data includes: In the case where the teleoperation data includes the target angle data, based on a second mapping relationship, normalizing and denormalizing the target angle data to determine an actual target angle of the joint, wherein the second mapping relationship is determined based on a motion range of the teleoperation device and a motion range of the dexterous hand; Based on the first mapping relationship and the actual target angle of the joint, a target angle of the drive motor is determined.

8. The dexterous hand control method according to claim 7, characterized in that: The dexterous hand further comprises at least one position sensor, at least one of the position sensors is connected to at least one of the joints, and the position sensor is configured to detect a current angle of the corresponding joint, wherein the dexterous hand control method further comprises: receiving a current angle of the joint; Determining a current angle of the drive motor based on a third mapping relationship and a current angle of the joint, wherein the third mapping relationship is determined based on a connection relationship between the drive motor and the joint; The current angle of the drive motor is sent to the drive motor.

9. A dexterous hand control device, characterized in that: Applied to a dexterous hand, the dexterous hand comprises a palm, at least one finger and at least one driving motor, the finger comprises a plurality of joints and a plurality of knuckles, one knuckle of one finger is connected to the palm via one of the joints, and an adjacent knuckle of one finger is connected via one of the joints, the driving motor is connected to at least one of the joints and is configured to drive the joint to move, so as to realize the movement of the dexterous hand; Wherein, the dexterous hand control device comprises: a receiving module configured to receive teleoperation data, wherein the teleoperation data includes target position data and / or target angle data, wherein the target position data is used to represent data of a target position of the finger input by a teleoperation device, and the target angle data is used to represent data of a target angle of the joint input by the teleoperation device; a calculation module configured to determine a target angle of the drive motor based on a first mapping relationship and the teleoperation data, wherein the first mapping relationship is determined based on a structure of the dexterous hand; The sending module is configured to send the target angle of the driving motor to the driving motor, so that the driving motor rotates to the target angle.

10. A dexterous hand, characterized in that: include: palm; At least one finger, the finger comprising a plurality of joints and a plurality of knuckles, one knuckle of the finger being connected to the palm via one of the joints, and adjacent knuckles of the finger being connected via one of the joints; at least one driving motor connected to at least one of the joints and configured to drive the joint to move; A controller is communicatively connected to the drive motor and is configured to control the rotation of the drive motor using the dexterous hand control method according to any one of claims 1 to 8.

11. A robot, characterized in that: include: main body; At least one dexterous hand according to claim 10, connected to the body.

Images