Mechanical arm motion control method and surgical robot

Abstract

The invention provides a mechanical arm motion control method and a surgical robot. The mechanical arm motion control method comprises the steps that force applied by a user is obtained through a force sensor arranged on a mechanical arm; determining a control purpose of the user according to the force applied by the user; according to the control purpose of the user, admittance control parameters of the mechanical arm are determined; and controlling the mechanical arm to move according to the admittance control parameters of the mechanical arm and the force applied by the user. According to the method, multiple control purpose types are preset, and the admittance control parameters of the mechanical arm are different under different control purpose types. In the actual using process, the force applied by the user is analyzed, the specific control purpose of the user is determined, and therefore the proper admittance control parameters are determined, and the mechanical arm is used more smoothly.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more particularly to a method for controlling the motion of a robotic arm and a surgical robot. Background Technology

[0002] Robots are being used more and more widely in neurosurgery and orthopedic surgery. Doctors use robots to assist in the execution of surgical plans. The robot's processing module controls the movement of the robotic arm and adjusts the surgical tools at the end of the robotic arm to a specific position, so as to achieve the support and guidance of the surgical tools.

[0003] Conventional robots control their robotic arms solely through processing modules. Some existing robots also offer force-controlled traction modes, allowing doctors to interact directly with the robotic arm. This means doctors can adjust the robotic arm's pose by dragging it, positioning the end effector tool as needed. Some robots also utilize "force-displacement" and "force-velocity" control algorithms to convert the force applied by the user into displacement and velocity at the end effector. These algorithms improve the robotic arm's maneuverability to some extent; however, the robotic arm still exhibits a specific response to user-input forces, making its movement seem rigid to the user.

[0004] In response, this invention provides a robotic arm motion control method and a surgical robot, which further improves the maneuverability of the robotic arm and makes its movement more in line with the user's control needs. Summary of the Invention

[0005] This invention provides a robotic arm motion control method and a surgical robot to address the shortcomings of poor maneuverability in existing robotic arms.

[0006] This invention provides a method for controlling the motion of a robotic arm, comprising:

[0007] The force applied by the user is obtained by using a force sensor installed on the robotic arm;

[0008] The user's control intention is determined based on the force applied by the user;

[0009] The admittance control parameters of the robotic arm are determined based on the user's control objectives;

[0010] The movement of the robotic arm is controlled based on the admittance control parameters of the robotic arm and the force applied by the user.

[0011] Optionally, the step of acquiring the force applied by the user using a force sensor installed on the robotic arm includes: acquiring the force detected by the force sensor and performing tool gravity compensation to obtain the force applied by the user.

[0012] Optionally, the force sensor acquires signals at a preset frequency to obtain the force applied by the user in sequence.

[0013] Optionally, determining the user's control intention based on the force applied by the user includes:

[0014] The force in the sequence form is input into a pre-trained first control purpose recognition model to obtain the user's control purpose.

[0015] Optionally, determining the user's control intention based on the force applied by the user includes:

[0016] Feature extraction is performed on the force applied by the user in the form of the sequence;

[0017] Based on the extracted features, analyze the user's control purpose.

[0018] Optionally, analyzing the user's control intent based on the extracted features includes:

[0019] The features are input into a pre-trained second control purpose recognition model to obtain the user's control purpose.

[0020] Optionally, the feature is calculated based on the data of each frame within a preset time window before the current moment, and the preset time window has at least two window widths to obtain features at different time scales.

[0021] Optionally, the features include at least two of the following indicators: average force, change in force, standard deviation of force, and variance of force.

[0022] Furthermore, the step of analyzing the user's control intent based on the extracted features includes:

[0023] If the average force is greater than the first average force threshold and less than the second average force threshold, the standard deviation of the force is greater than the first standard deviation threshold, and the change in force is less than the first change threshold, then the user's control purpose is determined to be a pre-adjustment.

[0024] If the average force is greater than the first average force threshold and less than the second average force threshold, the standard deviation of the force is greater than the first standard deviation threshold, and the change in force is greater than the first change threshold, or if the average force is greater than the second average force threshold, the standard deviation of the force is less than the second standard deviation threshold, and the change in force is less than the second change threshold, then the user's control purpose is determined to be a coarse adjustment.

[0025] If the direction of the force changes, the average force value is greater than the second average force threshold, and the standard deviation of the force is greater than the second standard deviation threshold; or, if the direction of the force changes, the average force value is greater than the second average force threshold, and the change in force is greater than the second change threshold, then the user's control objective is determined to be direction correction.

[0026] If the average force is greater than the first average force threshold, less than the second average force threshold, and the standard deviation of the force is less than the first standard deviation threshold, then the user's control objective is determined to be fine adjustment.

[0027] If the average force is less than the first average force threshold, then the user's control objective is determined to be the end of the adjustment.

[0028] Alternatively, different control objectives correspond to different robotic arm admittance control parameters, resulting in different maneuverability of the robotic arm.

[0029] Optionally, controlling the movement of the robotic arm based on the admittance control parameters of the robotic arm and the force applied by the user includes:

[0030] Based on the admittance control parameters and the force applied by the user, the expected motion speed of the robotic arm end effector at the next moment, as well as the expected position and orientation, are determined.

[0031] Control the robotic arm to move to the desired position and posture according to the movement speed.

[0032] The present invention also provides a surgical robot, including a processing module and a robotic arm. The robotic arm is equipped with a force sensor for detecting the force applied. The processing module includes a memory and a processor. When the processor executes a computer program stored in the memory, it implements the robotic arm motion control method described in any of the preceding claims.

[0033] The present invention also provides an endoscope robot, including a processing module, a robotic arm, and an endoscope;

[0034] The end of the robotic arm is connected to the endoscope, and a force sensor is installed on the robotic arm to detect the force applied.

[0035] The processing module includes a memory and a processor. When the processor executes the computer program stored in the memory, it implements any of the aforementioned robotic arm motion control methods to control the movement of the robotic arm in order to adjust the position and orientation of the endoscope.

[0036] The present invention also provides an external viewing mirror robot, including a processing module, a robotic arm, and an image acquisition module;

[0037] The image acquisition module is connected to the end of the robotic arm, and a force sensor is installed on the robotic arm to detect the force applied to it.

[0038] The processing module includes a memory and a processor. When the processor executes the computer program stored in the memory, it implements any of the aforementioned robotic arm motion control methods to control the movement of the robotic arm and adjust the position and orientation of the image acquisition module.

[0039] The robotic arm motion control method and surgical robot provided by this invention have at least the following beneficial effects:

[0040] 1. Multiple control objectives are preset, and the admittance control parameters of the robotic arm differ under different control objective types. In actual use, by analyzing the force applied by the user, the user's specific control objective is determined, thereby determining the appropriate admittance control parameters, making the robotic arm more "easy" to use, responding intelligently, and moving smoothly.

[0041] 2. By collecting the sequence of forces applied by the user and extracting the characteristics of the force sequence, the user's control purpose was analyzed more accurately based on the characteristics, and the admittance control parameters of the robotic arm were reasonably determined.

[0042] 3. By inputting the characteristics of the force sequence into a pre-trained control purpose recognition model, the user's control purpose is automatically and accurately determined.

[0043] 4. By supplementing the tool's gravity, the influence of the tool's gravity on "detecting the force applied by the user" is eliminated, which helps to analyze the user's control purpose more accurately and improves the maneuverability of the robotic arm. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating a robotic arm motion control method provided by the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of a surgical robot provided by the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] The following is combined Figures 1-2 The present invention describes the robotic arm motion control method and surgical robot. Figure 1 This is a flowchart illustrating a robotic arm motion control method provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0049] S1. The force applied by the user is obtained by using a force sensor installed on the robotic arm;

[0050] S2. Determine the user's control objective based on the force applied by the user;

[0051] S3. Determine the admittance control parameters of the robotic arm according to the user's control objectives;

[0052] S4. Control the movement of the robotic arm according to the admittance control parameters of the robotic arm and the force applied by the user.

[0053] Specifically, in this embodiment, the force sensor can be a force sensor installed at the end of the robotic arm. The user can change the posture of the robotic arm by applying force to the end of the robotic arm, thereby setting the tool connected to the end of the robotic arm to the desired position and posture. The force sensor can also include force sensors installed at each joint. The user can apply force to the robotic arm at any segment to change the posture of the robotic arm. Of course, both types of force sensors can be installed simultaneously to detect the force applied by the user. By using force sensors installed on the robotic arm to obtain the force applied by the user, we can analyze the user's control purpose. Different control purposes correspond to different robotic arm admittance control parameters. In other words, this embodiment can flexibly adjust the admittance control parameters of the robotic arm according to the identified "control purpose", making the response characteristics of the robotic arm more in line with the user's current usage needs, and making the robotic arm more convenient to use.

[0054] Based on the previous embodiment, in some embodiments, S1 includes: acquiring the force detected by the force sensor and performing tool gravity compensation to obtain the force applied by the user.

[0055] Specifically, the tool's weight can interfere with the force sensor's detection of the force applied by the user. Furthermore, due to the influence of the robotic arm's posture and the tool's center of gravity, the components of the tool's weight acting on the force sensor in each direction may not be constant. Therefore, after installing the end effector on the robotic arm, we positioned the robotic arm in at least three different postures and recorded the forces acting on the force sensor in each direction when the user did not apply any force. Based on this, we calculated the tool's weight and the position of its center of gravity.

[0056] During the subsequent control of the robotic arm's movement, the position of the center of gravity and the direction of gravity in the force sensor coordinate system can be determined based on the current posture of the robotic arm. Thus, the influence of the tool's gravity is subtracted from the force detected by the force sensor to determine the force applied by the user.

[0057] Additionally, the force sensor can be an end effector of the robotic arm capable of detecting forces in multiple directions, such as a 6-dimensional force sensor. When subtracting the influence of gravity, it can determine the components of the tool's weight in each dimension of the force sensor and subtract the tool's weight influence in each dimension. Alternatively, the forces detected by the force sensors in each direction can be synthesized, and the force applied by the user can be obtained after subtracting the influence of gravity, thereby analyzing the user's control intention. The force sensor can also include force sensors installed at each joint. When subtracting the influence of gravity, it calculates the effect of the tool's weight on the force sensors of each joint under the current posture of the robotic arm, subtracts the influence of the tool's weight, and determines the force applied by the user based on this.

[0058] This embodiment eliminates the influence of tool gravity without measurement, thus more accurately determining the force applied by the user.

[0059] Based on any embodiment, in some embodiments, the force sensor acquires signals according to a preset frequency, and in S1, it obtains the force applied by the user in a sequential form.

[0060] Specifically, the forces applied by the user are collected in sequence, which facilitates data processing by the computer. Moreover, this embodiment analyzes the user's control intention based on the sequence of forces, rather than the forces at a single moment, thus more accurately analyzing the user's control purpose.

[0061] Based on the previous embodiment, in some embodiments, S2 includes:

[0062] The user's control intention is obtained by inputting the force in the form of a sequence into a pre-trained first control intention recognition model.

[0063] Specifically, in this embodiment, the sequence of forces applied by the user is directly input into the first control purpose recognition model to identify the user's control purpose. The pre-trained model can improve the efficiency and accuracy of the recognition process. The aforementioned first control purpose recognition model can be a deep learning model, such as a Long Short-Term Memory Network (LSTM), a Recurrent Neural Network (RNN), a Recurrent Neural Network (GRU), or a Convolutional Neural Network (CNN) model with enhanced feature extraction capabilities. There are no restrictions here. The pre-trained deep learning model has the ability to automatically extract features and reason, and can directly analyze the user's control purpose based on the input force sequence.

[0064] Based on the foregoing embodiments, in some embodiments, S2 includes:

[0065] S21. Extract features from the forces applied by the user in sequence form;

[0066] S22. Analyze the user's control purpose based on the extracted features.

[0067] Specifically, the force sequence applied by the user can be preprocessed to improve data quality and enhance the accuracy of the analysis of the user's control intent. Preprocessing may include one or more of the following: outlier removal, missing data imputation, and moving average. The principle of moving average is to select a window of a certain size, calculate the arithmetic mean of the data within the window, and then use the calculated average as the data at the center point of the window. This averaging method is repeated by moving the window according to the point or line spacing until the entire graph has been processed. Moving average can smooth the data and reduce high-frequency noise. After preprocessing, feature extraction is performed. These features characterize the properties of the forces applied by the user over a certain period of time, reflecting the user's control intent.

[0068] Based on the previous embodiment, in some embodiments, S22 includes:

[0069] The features are input into a pre-trained second control purpose recognition model to obtain the user's control purpose.

[0070] Specifically, in this embodiment, the features extracted from the force sequence are input into the second control purpose recognition model to identify the user's control purpose. The pre-trained model can improve the efficiency and accuracy of the recognition process. Using the above features as training samples can accelerate the convergence speed of the model during training and improve the accuracy of the prediction results. The above-mentioned second control purpose recognition model can be a machine learning model, such as a support vector machine (SVM), a decision tree model, a random forest model, etc., and is not limited here.

[0071] Based on the foregoing embodiments, in some embodiments, the above features are calculated from the data of each frame within a preset time window before the current moment. The preset time window has at least two window widths to obtain features at different time scales.

[0072] Specifically, by setting multiple window widths, features at different time scales can be extracted, allowing for a more comprehensive analysis of the user's control intent. For example, by setting two time window widths, each covering the current frame and a certain amount of force data prior to it, the "short-term" and "long-term" features of the force applied by the user can be obtained through processing the data within each window width. These two types of features can then be combined to determine the user's control intent. Alternatively, by setting three time window widths, the "instantaneous," "short-term," and "long-term" features of the force applied by the user can be statistically analyzed, and these three types of features can be combined to determine the user's control intent.

[0073] It should also be noted that the time window in this embodiment is set independently from the sliding window used to implement the "moving average" in the previous embodiment. The two are not specifically related and can be set independently.

[0074] Based on any embodiment, in some embodiments, the above features include at least two of the following categories: average force, change in force, standard deviation of force, and variance of force.

[0075] Specifically, the average force is the absolute value of the arithmetic mean of the data in each frame within the time window; the change in force is the difference (including positive and negative) between the first and last data in the time window; and the standard deviation and variance of the force are the standard deviation and variance calculated for each frame within the window.

[0076] Based on any embodiment, in some embodiments, the control purpose includes: pre-adjustment, coarse adjustment, direction correction, fine adjustment, and end of adjustment.

[0077] Specifically, in the pre-adjustment phase, the user holds the robotic arm or the tool at its end, and the force sensor detects a small and continuously changing force, requiring control of the robotic arm's output speed. In the coarse adjustment phase, the user applies a larger force to pull the robotic arm, which accelerates and maintains a high speed. The force sensor initially detects a rapidly increasing force value and then stabilizes. The admittance control parameters need to be adjusted appropriately based on the magnitude of the force to control the robotic arm to move at a higher average speed by the corresponding offset. Sometimes, the user needs to apply a reverse force to the moving machine or the tool at its end to adjust its posture or change its current motion state, i.e., the direction adjustment phase. In this phase, the force sensor detects a large instantaneous reverse force, and correspondingly, the parameters need to be adjusted to make the robotic arm decelerate and move in the opposite direction in time. In the fine adjustment phase, the tool at the end of the robotic arm is already near the target position, and the user applies a small force to fine-tune the tool's position and posture. Force sensors can collect a sequence of forces that decrease and fluctuate around a small value. It is necessary to control the speed of the robotic arm to gradually decrease and stabilize at a small value. The robotic arm moves at a low speed and exhibits certain damping characteristics to avoid over-adjustment. At the end of the adjustment phase, the tool at the end of the robotic arm reaches the target position, the user's hand is removed from the robotic arm or the tool at the end of the robotic arm, and the contact force disappears. At this time, it is desirable for the robotic arm to maintain its position and posture.

[0078] This embodiment subdivides the control objectives into preparatory adjustment, coarse adjustment, direction correction, fine adjustment, and adjustment completion. Different control objectives correspond to different robotic arm admittance control parameters. By analyzing the force applied by the user, the user's specific control objective is determined from the above types, thus improving...

[0079] Based on any embodiment, in some embodiments, S22 includes:

[0080] If the average force is greater than the first average force threshold and less than the second average force threshold, the standard deviation of the force is greater than the first standard deviation threshold, and the change in force is less than the first change threshold, then the user's control purpose is determined to be a pre-adjustment.

[0081] If the average force is greater than the first average force threshold and less than the second average force threshold, the standard deviation of the force is greater than the first standard deviation threshold, and the change in force is greater than the first change threshold, or if the average force is greater than the second average force threshold, the standard deviation of the force is less than the second standard deviation threshold, and the change in force is less than the second change threshold, then the user's control purpose is determined to be a coarse adjustment.

[0082] If the direction of the force changes, the average force value is greater than the second average force threshold, and the standard deviation of the force is greater than the second standard deviation threshold; or, if the direction of the force changes, the average force value is greater than the second average force threshold, and the change in force is greater than the second change threshold, then the user's control objective is determined to be direction correction.

[0083] If the average force is greater than the first average force threshold, less than the second average force threshold, and the standard deviation of the force is less than the first standard deviation threshold, then the user's control objective is determined to be fine adjustment.

[0084] If the average force is less than the first average force threshold, then the user's control objective is determined to be the end of the adjustment.

[0085] The aforementioned thresholds can be set based on experience or user habits. For example, based on user habits, the first average force threshold can be set to 3N, and the second average force threshold can be set to 15N. This embodiment, by setting specific analysis strategies and combining experience-based thresholds that conform to user habits, accurately and comprehensively determines the user's control objectives, enabling the robotic arm to select appropriate admittance control parameters, and making the robotic arm's response characteristics more in line with the user's real-time usage needs.

[0086] In another embodiment, S22 includes:

[0087] If the standard deviation of the force is greater than the third standard deviation threshold and the change in force is less than the third change threshold, then the user's control purpose is determined to be a pre-adjustment.

[0088] If the average force is greater than the third average force threshold, the change in force is greater than the third change threshold, and the standard deviation of force is less than the fourth standard deviation threshold, then the user's control purpose is determined to be a coarse adjustment.

[0089] If the direction of the force changes and the standard deviation of the force exceeds the fifth standard deviation threshold, then the user's control objective is determined to be direction correction.

[0090] If the average force is less than the third average force threshold and the standard deviation of the force is less than the fourth standard deviation threshold, then the user's control objective is determined to be fine-tuning.

[0091] If the average force is less than the fourth average force threshold, then the user's control objective is determined to be the end of the adjustment.

[0092] Similarly, the above thresholds can be set based on experience or user habits. For example, based on user habits, the third average force threshold can be set to 10N and the third average force threshold can be set to 8N. This embodiment determines the user's control purpose more simply and efficiently.

[0093] Based on any embodiment, in some embodiments, different manipulation objectives in S3 correspond to different robotic arm admittance control parameters, resulting in different maneuverability of the robotic arm.

[0094] The admittance control parameters of the robotic arm include the mass parameter m and the damping parameter c. When the simulated mass m is set too large, the robotic arm has a large "inertia", its motion state is not easily changed, and it has a certain shielding effect on the noise in the applied force. The damping c affects the steady-state speed output by the robotic arm when the user inputs a certain force. The greater the damping, the greater the force that the user needs to input in order to make the robotic arm reach a certain steady-state speed.

[0095] Based on any embodiment, in some embodiments, S4 includes:

[0096] Based on the admittance control parameters and the force applied by the user, determine the expected motion speed of the robotic arm end effector at the next moment, as well as the expected position and orientation.

[0097] Control the robotic arm to move to the desired position and posture according to the movement speed.

[0098] Specifically, based on the identified "user control purpose," the admittance control parameters of the robotic arm can be determined. Correspondingly, the "force-velocity" functional relationship can be established. Combining this with the force applied by the user to obtain the velocity change, and then with the current velocity of the robotic arm's end effector, the desired motion velocity of the end effector can be determined. Similarly, the "force-displacement" functional relationship can be determined to obtain the displacement change. Combining this with the current pose of the robotic arm's end effector, the desired pose of the end effector can be determined. Based on this, the robotic arm can be controlled to move at the desired velocity to reach that desired pose.

[0099] The present invention also provides a surgical robot, the surgical robot described below and the robotic arm motion control method described above can be referred to each other.

[0100] The present invention provides a surgical robot including a processing module and a robotic arm.

[0101] The robotic arm is equipped with force sensors to detect the force it receives. The processing module includes a memory and a processor. When the processor executes the computer program stored in the memory, it implements any of the aforementioned robotic arm motion control methods.

[0102] Specifically, force sensors on the robotic arm detect the applied force and transmit it to the processing module. The processing module then executes the aforementioned robotic arm motion control method, enabling the robotic arm to move in accordance with the user's traction force and reach the user's desired target pose. The processing module can be set up independently or integrated with the robotic arm, for example, integrated into the robotic arm base.

[0103] The present invention also provides an endoscope robot, and the endoscope robot described below and the robotic arm motion control method described above can be referred to each other.

[0104] like Figure 2As shown, the endoscopic robot provided by the present invention includes a processing module 100, a robotic arm 200, and an endoscope 300.

[0105] The end of the robotic arm 200 is connected to the endoscope 300, and force sensors are provided at the end of the robotic arm and / or at the joints to detect the force applied.

[0106] The processing module 100 includes a memory and a processor. When the processor executes the computer program stored in the memory, it implements the robotic arm motion control method described above, and controls the movement of the robotic arm 200 to adjust the position and orientation of the endoscope 300.

[0107] Specifically, the robotic arm 200 can adjust the position and orientation of the endoscope 300. Force sensors on the robotic arm can detect the applied force and transmit it to the processing module 100. The processing module 100 can execute the aforementioned robotic arm motion control method, enabling the robotic arm 200 to move in accordance with the user's traction force, adjusting the endoscope 300 to the user's desired target position and orientation. The processing module 100 can be set independently or integrated with the robotic arm, for example, integrated into the robotic arm base.

[0108] The present invention also provides an external viewing mirror robot, and the external viewing mirror robot described below and the robotic arm motion control method described above can be referred to each other.

[0109] The present invention provides an external viewing mirror robot, comprising a processing module, a robotic arm, and an image acquisition module.

[0110] An image acquisition module is connected to the end effector of the robotic arm, and force sensors are installed at the end effector and / or joints of the robotic arm to detect the applied force.

[0111] The processing module includes a memory and a processor. When the processor executes the computer program stored in the memory, it implements the robotic arm motion control method described above, controls the movement of the robotic arm, and adjusts the position and orientation of the image acquisition module.

[0112] Specifically, the robotic arm can adjust the position and orientation of the image acquisition module. Force sensors on the robotic arm detect the applied force and transmit it to the processing module. The processing module executes the aforementioned robotic arm motion control method, enabling the robotic arm to move in accordance with the user's traction force, adjusting the image acquisition module to the user's desired target pose. The processing module can be set up independently or integrated with the robotic arm, for example, integrated into the robotic arm base.

[0113] The external endoscopic robot provided in this embodiment allows users to place the image acquisition module in a suitable position and angle by dragging the robotic arm, enabling high-resolution, magnified, and clear imaging of the surgical area, allowing doctors to observe the tissue in the surgical area more clearly.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of motion control of a robot arm, characterized by, The method comprises the following steps: acquiring the force exerted by the user by using a force sensor arranged on the mechanical arm; determining the control purpose of the user according to the force exerted by the user; determining the admittance control parameter of the mechanical arm according to the control purpose of the user; controlling the movement of the mechanical arm according to the admittance control parameter of the mechanical arm and the force exerted by the user.

2. The robot arm motion control method according to claim 1, wherein, The step of acquiring the force exerted by the user by using a force sensor arranged on the mechanical arm comprises the following steps:

3. The method of claim 1, wherein, acquiring the force detected by the force sensor, and performing tool gravity compensation to obtain the force exerted by the user.

4. The robot arm motion control method according to claim 3, wherein, The force sensor collects signals according to a preset frequency, so as to acquire the force exerted by the user in a sequence form. The step of determining the control purpose of the user according to the force exerted by the user comprises the following steps:

5. The method of claim 3, wherein, inputting the force in the sequence form into a first pre-trained control purpose recognition model to obtain the control purpose of the user. The step of determining the control purpose of the user according to the force exerted by the user comprises the following steps: performing feature extraction on the force exerted by the user in the sequence form; 6. The method of claim 5, wherein, analyzing the control purpose of the user according to the extracted features. The step of analyzing the control purpose of the user according to the extracted features comprises the following steps:

7. The method of claim 5, wherein, inputting the features into a second pre-trained control purpose recognition model to obtain the control purpose of the user.

8. The method of claim 5, wherein, The features are calculated for each frame of data within a preset time window before the current time, and the preset time window has at least two window widths to obtain features of different time scales.

9. The method of claim 8, wherein, The features comprise at least two of the following indicators: average force, force variation, force standard deviation, and force variance. The step of analyzing the control purpose of the user according to the extracted features comprises the following steps: if the average value of the force is greater than a first average force threshold, less than a second average force threshold, the standard deviation of the force is greater than a first standard deviation threshold, and the variation of the force is less than a first variation threshold, it is determined that the control purpose of the user is preliminary adjustment; if the average value of the force is greater than a first average force threshold, less than a second average force threshold, the standard deviation of the force is greater than a first standard deviation threshold, and the variation of the force is greater than a first variation threshold, or if the average value of the force is greater than a second average force threshold, the standard deviation of the force is less than a second standard deviation threshold, and the variation of the force is less than a second variation threshold, it is determined that the control purpose of the user is rough adjustment; if the direction of the force changes, the average value of the force is greater than a second average force threshold, the standard deviation of the force is greater than a second standard deviation threshold, or if the direction of the force changes, the average value of the force is greater than a second average force threshold, and the variation of the force is greater than a second variation threshold, it is determined that the control purpose of the user is direction correction; if the average value of the force is greater than a first average force threshold, less than a second average force threshold, and the standard deviation of the force is less than a first standard deviation threshold, it is determined that the control purpose of the user is fine adjustment; 10. The robot motion control method according to claim 1, wherein, if the average value of the force is less than a first average force threshold, it is determined that the control purpose of the user is adjustment end.

11. The method of claim 1, wherein, Different control purposes correspond to different admittance control parameters of the mechanical arm, so that the mechanical arm has different controllability. The step of controlling the movement of the mechanical arm according to the admittance control parameter of the mechanical arm and the force exerted by the user comprises the following steps: According to the admittance control parameter and the force applied by the user, a desired motion speed of the end of the robot arm at a next time is determined, and a desired position and posture to be reached is determined; The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed.

12. A surgical robot, characterized by The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed.

13. An endoscopic robot, characterized by The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed.

14. An exterior mirror robot, characterized by The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed. The robot arm is controlled to move to the desired position and posture to be reached according to the motion speed.

Images