Hand-leaving detection method, controller and robot

Abstract

The embodiment of the invention provides a hand leaving detection method, a controller and a robot. The method comprises the steps that a controller of the robot obtains a sampling signal of a robot main hand tail end operation unit; and the controller of the robot judges whether the robot is in a hand-off state or an operation state according to whether the signal change in the preset duration meets the hand-off condition or not. The method is used for achieving the effect of improving the accuracy and real-time performance of robot hand separation judgment.

Description

Technical Field

[0001] This application relates to the field of robot control, and more particularly to a method for detecting off-hand movement, a controller, and a robot. Background Art

[0002] Minimally invasive laparoscopic surgical robot systems achieve remote operation through master-slave control, and their safety highly depends on real-time awareness of the surgeon's operational status. If the surgeon accidentally leaves the master control platform (i.e., loses their hand) and the system fails to promptly interrupt the master-slave mapping, the slave robotic arm may continue to perform unintended actions, increasing surgical risks. Therefore, hand-loss detection is a core technology for ensuring the safe operation of the system.

[0003] Existing hand-removal detection solutions mostly rely on external sensors. For example, a pressure sensor can be integrated into the master end effector to determine the hand-removal state based on a grip strength threshold. Alternatively, a capacitive touch sensor can be integrated into the master end effector to detect hand removal based on changes in skin capacitance. Or, a visual monitoring device can be used, employing a camera to capture the hand's position to assist in the determination.

[0004] However, methods that rely on external sensors for off-hand detection are susceptible to environmental interference, suffer from poor detection stability, and are prone to false detections, resulting in low detection accuracy. Summary of the Invention

[0005] This application provides a method, controller, and robot for off-hand detection, which aims to improve detection accuracy.

[0006] In a first aspect, embodiments of this application provide a method for detecting hand-off detection, applied to the main hand of a robot, comprising:

[0007] Acquire sampling signals from at least one end effector unit of the robot's main hand;

[0008] If the change of the sampled signal within a preset time period meets the preset hand-free condition, then the working state of the robot is determined to be the hand-free state; otherwise, the working state of the robot is determined to be the operating state.

[0009] In one example, acquiring a sampling signal from at least one end effector unit of the robot's master hand includes:

[0010] The encoder value of the encoder of the end operation unit is obtained according to the preset sampling frequency;

[0011] The sampling signal is generated based on the encoder value.

[0012] In one example, the end effector unit is an end joint and / or an end effector.

[0013] In one example, the end effector unit is an end joint, and the preset duration includes a first duration; the change of the sampled signal within the preset duration conforms to a preset release condition, including:

[0014] Within the first time period, the signal difference between two adjacent sampled signals is acquired;

[0015] If the signal difference is less than the first threshold within the first time period, then it is determined that the change of the sampled signal within the preset time period meets the preset release condition.

[0016] In one example, the end effector is an end effector, and the preset duration includes a second duration; the change of the sampled signal within the preset duration conforms to a preset release condition, including:

[0017] The number of sampled signals that are less than the second threshold within the second time period is counted;

[0018] If the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0019] In one example, the end effector unit includes an end effector and at least one end joint, and the preset duration includes a first duration corresponding to the end joint and a second duration corresponding to the end effector; the change of the sampled signal within the preset duration conforms to a preset release condition, including:

[0020] Acquire the sampled signals of the end joints within a first time period prior to the current time; and calculate the signal difference between two adjacent sampled signals of each end joint within the first time period;

[0021] Acquire the sampled signal of the end effector within a second time period prior to the current moment; and count the number of signals whose sampled signal is less than a second threshold.

[0022] If the signal differences are all less than the first threshold and the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0023] In one example, the method further includes:

[0024] Based on the working status, update the robot's status flag to enable the robot to switch operating modes according to the status flag.

[0025] In one example, the method further includes:

[0026] If the robot's working state is off-hand state, then the robot's current master-slave synchronization mode will be switched to joint impedance mode.

[0027] In one example, before switching the robot from its current master-slave synchronization mode to a joint impedance mode, the method further includes:

[0028] The redundant joint obstacle avoidance strategy is suspended, and the friction compensation of the force-controlled joints is reduced.

[0029] Secondly, embodiments of this application provide a hand-off detection device, including: a main hand applied to a robot, comprising:

[0030] An acquisition module is used to acquire sampling signals from at least one end effector unit of the robot's main hand;

[0031] The judgment module is used to determine that the working state of the robot is the off-hand state if the change of the sampled signal within a preset time period meets the preset off-hand condition; otherwise, it determines that the working state of the robot is the operating state.

[0032] In one example, the module is used for:

[0033] The encoder value of the encoder of the end operation unit is obtained according to the preset sampling frequency;

[0034] The sampling signal is generated based on the encoder value.

[0035] In one example, the end effector unit is an end joint and / or an end effector.

[0036] In one example, the end effector unit is an end joint, and the preset duration includes a first duration; the judgment module is used for:

[0037] Within the first time period, the signal difference between two adjacent sampled signals is acquired;

[0038] If the signal difference is less than the first threshold within the first time period, then it is determined that the change of the sampled signal within the preset time period meets the preset release condition.

[0039] In one example, the end effector is an end effector, and the preset duration includes a second duration; the judgment module is used for:

[0040] The number of sampled signals that are less than the second threshold within the second time period is counted;

[0041] If the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0042] In one example, the end effector unit includes an end effector and at least one end joint, and the preset duration includes a first duration corresponding to the end joint and a second duration corresponding to the end effector; the judgment module is used for:

[0043] Acquire the sampled signals of the end joints within a first time period prior to the current time; and calculate the signal difference between two adjacent sampled signals of each end joint within the first time period;

[0044] Acquire the sampled signal of the end effector within a second time period prior to the current moment; and count the number of signals whose sampled signal is less than a second threshold.

[0045] If the signal differences are all less than the first threshold and the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0046] In one example, the device further includes:

[0047] The control module is used to update the status flag of the robot according to the working state, so that the robot switches the operating mode according to the status flag.

[0048] In one example, the control module is used for:

[0049] If the robot's working state is off-hand state, then the robot's current master-slave synchronization mode will be switched to joint impedance mode.

[0050] In one example, the control module is used for:

[0051] The redundant joint obstacle avoidance strategy is suspended, and the friction compensation of the force-controlled joints is reduced.

[0052] Thirdly, embodiments of this application provide a controller, including: a memory and a processor;

[0053] The memory stores computer-executable instructions;

[0054] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0055] Fourthly, embodiments of this application provide a robot, the robot's main hand including at least one end effector unit and the controllers described in the third aspect above and / or various possible controllers described in the third aspect above;

[0056] The end effector unit is a user-operated contactor and / or at least one end joint fixedly connected to the end effector.

[0057] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0058] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0059] The off-hand detection method, controller, and robot provided in this application obtain sampling signals from the robot's end effector and determine whether the robot is in an off-hand state or an operating state based on whether the signal changes within a preset time period meet the off-hand conditions. This achieves off-hand state determination based on the robot arm's own data, thereby reducing the hardware requirements of external sensors, lowering the robot's hardware cost, and simplifying the robot's assembly and design. Furthermore, determining the off-hand state based on the robot arm's own data ensures synchronization between the determination and the robot arm's own data, thus improving the accuracy and real-time performance of the robot's off-hand determination. Additionally, the robot arm's own data is inherently present during robot arm use; determining the off-hand state based on this data avoids the need for external sensor data, improving the versatility of the off-hand determination method. Attached Figure Description

[0060] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0061] Figure 1 Flowchart of the off-hand detection method provided in this application Figure 1 ;

[0062] Figure 2 Flowchart of the off-hand detection method provided in this application Figure 2 ;

[0063] Figure 3 This is a schematic diagram of the off-hand detection device provided in this application;

[0064] Figure 4 A schematic diagram of the controller provided in this application.

[0065] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. Detailed Implementation

[0066] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0067] With the rapid development of minimally invasive surgical techniques, laparoscopic-assisted minimally invasive surgery has gradually become an important means of modern clinical surgical treatment. To further improve surgical precision, reduce trauma, and expand surgeons' operational capabilities, laparoscopic minimally invasive surgical robot systems have emerged. Among them, master-slave control robot systems, represented by the da Vinci Surgical System, have been widely used in various surgical scenarios such as urology, gynecology, and general surgery, significantly improving the operability and stability of surgeries.

[0068] In these types of surgical robot systems, surgeons perform precise manipulations using a master hand. The master and slave hands are precisely mapped through a structure. To ensure the safety of the surgeon's operation and the accuracy of the system's response, the system must quickly detect and interrupt the master-slave mapping relationship when the surgeon removes their hand from the operating platform, preventing the slave robotic arm from performing unnecessary or unintended actions. This process is called "hand-off detection," and its accuracy and real-time performance directly impact the safety and robustness of the entire surgical system.

[0069] Currently, most off-hand detection solutions rely on external sensor technology. For example, pressure sensors, capacitive touch sensors, visual monitoring devices, or photoelectric and infrared sensors are integrated into the end effector controlled by the master controller to determine in real time whether the doctor is holding the end effector. While these methods can effectively detect off-hand states, their complex structure, high cost, complex wiring, and excessive dependence on the external environment and sensor performance significantly limit the system's integration capabilities, stability, and potential for industrial applications. For instance, in the da Vinci surgical robot and its derivatives, once the system detects that the doctor has released the end effector (i.e., the "off-hand" state), it immediately interrupts the master-slave mapping relationship or initiates a safety mode to avoid misoperation. However, such solutions are limited in their scope and versatility due to high hardware complexity, high maintenance costs, and poor environmental adaptability.

[0070] Furthermore, no publicly available literature or product proposes a sensorless detection method for determining whether a robot is off-hand based on the motion characteristics of the end joints and the changes in encoder characteristics of the robot's main control platform. While existing sensor-based off-hand detection methods can identify the doctor's control state, they still have many significant drawbacks and shortcomings.

[0071] For example, strong hardware dependence leads to complex system integration, which is not conducive to the standardization and modular design of products; additional sensors increase manufacturing costs and maintenance difficulty, and may fail due to wear and tear, environmental interference, calibration deviation, etc., affecting system stability and safety; some sensors are susceptible to factors such as hand humidity, wearing gloves, changes in lighting, or electromagnetic interference, which reduces the accuracy of off-hand detection and poses a risk of misjudgment or missed detection; high-sensitivity detection may misjudge minor operations as off-hand, reducing system response stability, while excessively low sensitivity may delay response, causing operational safety hazards, making it difficult to balance real-time performance and reliability; current sensor-dependent solutions often require significant modifications to the main control platform, limiting the adaptability and portability of different surgical robot systems, which is not conducive to technology promotion and large-scale deployment.

[0072] Therefore, developing a novel off-hand detection method that relies on existing motion data and requires no additional hardware is of great significance for improving the practicality, reliability, and integration of surgical robot systems. Based on this, there is an urgent need to develop an off-hand detection method that requires no additional sensors, has a simple structure, high reproducibility, and superior detection accuracy.

[0073] Therefore, this application proposes a method for detecting hand-off state based on existing end-effector manipulation units. This application achieves accurate sensorless judgment of the hand-off state by analyzing the positional changes of the two distal joints of the doctor's controlled hand and the operational information of the end effector. This application achieves highly robust and real-time doctor hand-off detection using only the kinematic and encoder information of the existing system, without changing the existing operating platform structure or increasing any additional hardware costs. It has good adaptability, real-time performance, and engineering implementation value.

[0074] The off-hand detection method proposed in this application first acquires sampling signals from the end effector unit of the main control platform at a fixed frequency. This end effector unit can be two end effector joints and an end effector actuator. The controller can use the encoder values ​​of the encoders of the end effector joints and the end effector actuator as the sampling signals. The sampling period can be 2ms. The two end effector joints can be denoted as Joint6 and Joint7, respectively. The end effector actuator can be denoted as Gripper.

[0075] Subsequently, the controller can utilize a sliding time window technique to construct an incremental sequence for the values ​​of Joint6 and Joint7 within a first duration. The controller can extract the signal difference between two adjacent sampled signals to obtain an incremental sequence composed of signal differences within the sliding time window of the first duration. If any signal difference in the incremental sequence is greater than or equal to a first threshold, it can be determined that the main hand is in a user-operated state. If all signal differences in the incremental sequence are less than the first threshold, it can be determined that the main hand is in a hands-free state.

[0076] The first duration can be 200ms. The first threshold can be 1.2 pulses.

[0077] Simultaneously, the controller can utilize a sliding time window technique to analyze the Griper value within the second time period. The controller can count the number of sampled signals below a second threshold within this second time period, thereby determining the opening / closing state of the end effector and counting the number of opening / closing operations. If the number of signals is greater than or equal to a third threshold, it can be determined that the master hand is in a user-operated state. If the number of signals is less than the third threshold, it can be determined that the master hand is in a hands-free state.

[0078] The second duration can be 100ms. The second threshold can be 3000 pulses. This pulse value can be determined based on the pulse value when the end effector of different master actuators opens. The third threshold can be 2 times.

[0079] Subsequently, the controller can modify the flag bit of the master hand based on this operating state. This flag bit can be denoted as "flag". This operating state can include operating state and hands-free state. Flag=0 corresponds to operating state, and Flag=1 corresponds to hands-free state.

[0080] The controller can execute the corresponding response based on this flag. If Flag=1, the redundant joint obstacle avoidance strategy is paused, friction compensation of the force-controlled joints is reduced, and preparation is made for switching to impedance mode. If Flag=0, master-slave synchronous execution is maintained.

[0081] Furthermore, this method features highly adjustable parameters; the threshold and time window can be dynamically configured according to actual needs, facilitating adaptation to different control mechanisms and surgical practices. Additionally, a differential filter or standard deviation judgment mechanism can be further introduced to enhance the robustness of off-hand detection.

[0082] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0083] Figure 1 Flowchart of the off-hand detection method provided in this application Figure 1 ,like Figure 1 As shown, this method is applied to the master hand of a robot. The controller of the robot is the execution entity of this method. The robot may also include a slave hand. When the user controls the master hand through the end effector of the master hand, the slave hand of the robot follows the movement of the master hand. The method includes:

[0084] S101. Acquire the sampling signal of at least one end effector unit of the robot's master hand.

[0085] For example, the user's end effector is typically located at the end of the robot's master arm. Therefore, the controller can determine whether the user is currently in an operating state by acquiring sampled signals from at least one end effector unit of the robot's master arm.

[0086] In one example, the end effector unit is an end joint and / or an end effector.

[0087] For example, when the end effector is the end joint of the robotic arm, the controller can acquire sampling signals of at least one end joint of the robotic arm. For instance, for a 7-joint robotic arm, the controller can acquire the sampling signals of the sixth and seventh joints.

[0088] For example, when the end effector is an end effector at the end of the robotic arm, the controller can acquire the sampled signal of the end effector operated by the user. For example, the end effector can correspond to a group gripper, joystick, trackball, etc.

[0089] In one example, the sampled signal can be a control signal for the end-effector.

[0090] For example, when a user applies force to the end effector unit, the end effector unit generates a corresponding control signal in response to the user's control, thereby controlling the corresponding end effector unit in the user's hand to perform the corresponding operation. During this process, the controller can read the control signal and generate corresponding sampling information based on the control signal.

[0091] In another example, the sampled signal can be the position signal of the end effector unit.

[0092] For example, the end effector unit may be equipped with a position sensor. The controller sends read commands to the position sensor at regular time intervals to obtain the position coordinate data of the end effector unit.

[0093] For example, the position sensor can be an encoder or a laser displacement sensor.

[0094] For example, an encoder is mounted at a joint to indirectly calculate the position of the end effector unit by measuring the joint's rotation angle. For instance, the encoder can convert rotational displacement into a digital pulse signal.

[0095] For example, a laser displacement sensor can directly measure the distance and position information between the end effector and the target object. This position coordinate data can be, for example, the X, Y, and Z coordinates in three-dimensional space.

[0096] In another example, the sampled signal can also be a signal obtained by multi-sensor fusion.

[0097] S102. If the change of the sampled signal within a preset time period meets the preset hand-off condition, then the robot's working state is determined to be the hand-off state. Otherwise, the robot's working state is determined to be the operating state.

[0098] For example, the controller can collect and record sampled signals within a preset time period and analyze their changes to determine the robot's working state. The working state can include a hands-free state and an operational state.

[0099] In one example, the preset duration can be set according to the analysis conditions. Alternatively, the preset duration can be set according to the type of end effector unit.

[0100] For example, when the end effector is an end joint, the preset duration can be 200ms. Or, when the end effector is an end effector actuator, the preset duration can be 100ms.

[0101] In one example, when the robot's master hand is off-hand, the sampling signal of the end effector unit typically remains stable in the inactive state. Therefore, the controller can set a corresponding threshold based on the stable value of the end effector unit in the inactive state. By comparing the sampling signal with the threshold, the operating state can be determined.

[0102] For example, if the sampled signal matches the threshold, it is determined that the main hand is in a hands-free state. If the sampled signal does not match the threshold, it is determined that the main hand is in an operating state.

[0103] Optionally, this threshold can correspond to a small threshold range. Setting this threshold range can avoid misjudgments caused by excessive precision.

[0104] In another example, when the robot's master hand is in a hands-free state, the sampling signal of the end effector unit is usually stable. Therefore, the controller can analyze the working state of the robot's master hand based on the sampling signal curve or the sampling signal change value of the end effector unit within a preset time period.

[0105] For example, if the sampled signal curve matches a preset curve within a preset time period, it is determined that the main hand is in a hands-free state. If the sampled signal curve has abnormal points or abnormal curvature, it is determined that the main hand is in an operating state.

[0106] For example, if the changes in the sampled signal are all less than a threshold value within a preset time period, it is determined that the main hand is in a hands-free state. If the changes in the sampled signal are greater than the threshold value, it is determined that the main hand is in an operating state.

[0107] In another example, the sampled signal within the preset time period can be input into the algorithm model to predict and output the working state of the robot's main arm.

[0108] Optionally, the algorithm model can be a deep learning model, a neural network model, a big data model, etc. The algorithm model is a pre-trained model.

[0109] In this example, by acquiring the sampling signal of the robot's end effector unit and determining whether the robot is in a hands-free or operational state based on whether the signal change within a preset time period meets the hands-free condition, this method achieves hands-free state determination based on the robot arm's own data. This reduces the hardware requirements of external sensors, lowers the robot's hardware cost, and simplifies the robot's assembly and design. Furthermore, determining the hands-free state based on the robot arm's own data ensures synchronization between the determination and the robot arm's own data, thereby improving the accuracy and real-time performance of the hands-free determination. Finally, the robot arm's own data is inherently present during robot arm use; determining the hands-free state based on this data avoids the need for external sensor data, thus improving the versatility of this hands-free determination method.

[0110] Furthermore, off-hand detection based on external sensors typically relies on data such as pressure, capacitance, photoelectricity, or images detected by external sensors. The acquisition of these data is easily affected by factors such as hand humidity, glove wearing status, lighting changes, or electromagnetic interference. However, using the robotic arm's own data to determine the off-hand status avoids the influence of external interference on data acquisition and further improves the accuracy of the off-hand status determination.

[0111] In one example, S101, acquiring a sampled signal from at least one end effector unit of the robot's master hand includes:

[0112] S1011. Obtain the encoder value of the encoder of the end operation unit according to the preset sampling frequency.

[0113] For example, the controller first periodically acquires the encoder value of the encoder of the end effector unit according to a preset sampling frequency.

[0114] In one example, the preset sampling frequency can be determined based on the encoder's signal frequency. For example, the sampling frequency could be once every 1 ms, or once every 2 ms, etc.

[0115] In one example, the controller can be configured with an internal hardware timer that triggers an interrupt based on the sampling frequency. When an interrupt occurs, the controller immediately sends a data read command to the encoder of the end effector unit via a preset communication protocol. Upon receiving the command, the encoder sends its encoder value to the controller.

[0116] For example, the encoder and controller can communicate via signals such as SPI, I2C, or SSI.

[0117] Optionally, the encoder value can be a pulse signal generated when the grating disk or magnetic disk inside the encoder rotates. Alternatively, the encoder value can be a digitally encoded value converted from the pulse signal.

[0118] For example, the digital encoding value can be a 16-bit binary number.

[0119] In one example, after the controller reads the encoder value, it performs data verification to confirm data integrity. If the verification fails, a data retransmission mechanism is automatically triggered.

[0120] For example, the check can be a cyclic redundancy check (CRC).

[0121] S1012. Generate a sampling signal based on the encoder value.

[0122] For example, after the controller obtains the encoder value, it can convert it into a sampled signal with a uniform format.

[0123] In one example, when only one end effector unit is included, the controller can directly use the encoder value of the end effector unit's encoder as the sampled signal.

[0124] When multiple end effector units are included, if the encoders of the multiple end effector units are the same encoder, the controller can directly use the encoder value of the encoder of the end effector unit as the sampled signal.

[0125] In another example, the controller can scale the encoder value to the actual physical range of the robotic arm joint, and then use that physical range as the sampled signal.

[0126] For example, encoder values ​​in the range of 0 to 65535 can be scaled to -180 degrees to 180 degrees.

[0127] In one example, the controller can also smooth multiple consecutively acquired encoder values ​​to suppress noise interference.

[0128] For example, the moving average method can be used to take the average of the most recent 5 sampled values, or the Kalman filter algorithm can be used in combination with the system model to predict the true value.

[0129] In this example, by triggering data acquisition at a preset sampling frequency and reading the encoder value of the end effector unit, combined with the conversion processing method of encoder value to standardized digital signal, the effect of real-time perception of the motion state of the robotic arm end effector and accurate signal generation is achieved.

[0130] In one example, when the end effector is an end joint, the preset duration can be a first duration. For example, the first duration can be 200ms.

[0131] In one example, when the end effector is an end joint, when the user is in contact with the master hand, due to the user's own characteristics, even if the user is holding the handle of the master hand and remains stationary, slight shaking of the user's arm will still cause changes in the sampling signal of the end joint. Therefore, it can be considered that the sampling signal of the end joint changes continuously during operation.

[0132] When the user releases their hand, the primary hand needs to maintain the user's position at that moment to prevent accidental movement of the secondary hand. Therefore, it can be assumed that the sampling signal of the end effector joint will remain unchanged in the current pose of the joint when the user releases their hand.

[0133] Taking an end joint as an example, step S102 above, which determines whether the change of the sampled signal in the end joint within a preset time period meets a preset release condition, includes:

[0134] S10211. Obtain the signal difference between two adjacent sampled signals.

[0135] S10212. If the signal difference is less than the first threshold within the first time period, then it is determined that the change of the sampled signal within the preset time period meets the preset release condition.

[0136] For example, the controller can accurately determine whether the end effector of the robotic arm is in a hands-free state by dynamically monitoring the continuous change characteristics of the sampled signal and combining it with a multi-level time window difference analysis mechanism.

[0137] In one example, the controller can sequentially calculate the difference between two adjacent sampled signals based on the sampled signal sequence acquired within a first time period, thus obtaining a signal difference sequence. If all signal differences in this signal difference sequence are less than a first threshold, the controller can determine that the change in the sampled signal within a preset time period meets a preset release condition.

[0138] In one example, the first duration can be a sliding window. That is, the controller can acquire the sampled signal of the first duration prior to the current time at the current time and process the sampled signal.

[0139] In another example, the controller can calculate the difference between the sampled signal from the previous moment and the sampled signal from the current moment in real time during the acquisition of the sampled signal, thus obtaining the signal difference. The controller can then use the detection that the signal difference is less than a first threshold as the start time of the first duration.

[0140] If the signal difference is less than the first threshold after the first time period, the controller can determine that the change of the sampled signal within the preset time period meets the preset release condition.

[0141] Otherwise, if a signal difference is greater than or equal to the first threshold within the first time period, the controller can restart the timing when the next signal difference is less than the first threshold.

[0142] In one example, the first threshold can be a small pulse value. For example, the first threshold can be 1.2 pulses, 1.3 pulses, 2 pulses, etc.

[0143] In this example, by monitoring whether the signal difference between adjacent sampled signals within the first time period is less than a first threshold, the sampled signals within the first time period are analyzed and verified, thereby achieving the effect of accurately determining whether the robot's master hand is in a hands-free state.

[0144] In one example, when the end effector is an end joint, the controller can simultaneously acquire sampled data from at least one end joint. When at least one end joint indicates that the master hand is in an operating state, the controller can determine that the master hand is in an operating state. When all end joints indicate that the master hand is in a hands-free state, the controller can determine that the master hand is in a hands-free state.

[0145] In one example, when the end effector is an end effector, the preset duration can be a second duration. For example, the second duration can be 100ms.

[0146] In one example, when the end effector is an end effector unit, similar to an end joint, the sampled signal of the end effector changes with the user's operation when the master hand is in the operating state. When the master hand is off-hand, the sampled signal of the end effector remains at a stable value.

[0147] Unlike end effectors, when the user hand is off-hand, the stable value of the sampled signal from an end effector is typically the value when the end effector is not in use. This value is usually a fixed value determined based on the end effector. The stable value of an end effector, however, is the sampled signal corresponding to the pose of the end effector when the user releases their hand.

[0148] Specifically, step S102 above, which determines that the change in the sampling signal of the end effector within a preset time period meets the preset release condition, includes:

[0149] S10221. Count the number of sampled signals that are less than the second threshold within the second time period.

[0150] S10222. If the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0151] For example, the controller can determine whether the user operated the controller at the time corresponding to each sampled signal by comparing each sampled signal with a second threshold. If the sampled signal is less than the second threshold, the sampled signal can be determined to be a valid value. Further, the controller determines whether the robotic arm end effector is in a detached state based on the number of valid signals within the window.

[0152] In one example, the controller can determine whether each sampled signal is less than a second threshold based on the sampled signals collected within a second time period, thereby accumulating the number of sampled signals less than the second threshold. If the number of signals is less than a third threshold, it is determined that the change of the sampled signal within a preset time period meets a preset release condition.

[0153] In one example, the second duration can be a sliding window. That is, the controller can acquire the sampled signal of the second duration preceding the current time at the current time and process the sampled signal.

[0154] In another example, the controller can use the moment when it detects a sampled signal greater than or equal to a second threshold during the acquisition of the sampled signal as the start time of the second time period. Subsequently, the controller can accumulate the number of sampled signals greater than or equal to the second threshold. If, within the second time period, this number of signals reaches a third threshold, the controller can determine that the master hand is in an operational state.

[0155] The controller can restart accumulating the number of signals greater than or equal to the second threshold sampling signal within the second time period when it detects a sampling signal greater than or equal to the second threshold sampling signal for the next time.

[0156] If the number of signals does not reach the third threshold when the second time point is reached, the controller can determine that the change of the sampled signal within the preset time period meets the preset release condition.

[0157] In one example, the third threshold can be a small natural number. For example, the third threshold could be 2, 3, etc.

[0158] In one example, since different end effectors have different pulse values ​​for their inactive state, the second threshold can be a threshold determined based on the pulse value of the inactive state of the end effector.

[0159] For example, when the end effector is a gripper, its clamps are in an open state when not in use. In this case, the encoder value of the gripper can be 3000 pulses. Therefore, the second threshold can be 3000 pulses.

[0160] In this example, by counting the number of signals whose sampled signals are below the second threshold within the second time period, the sampled signals within the second time period are analyzed and verified, thus achieving the effect of accurately determining whether the robot's master hand is in a hands-free state.

[0161] In one example, when the end effector unit includes an end effector and at least one end joint, the preset duration includes a first duration corresponding to the end joint and a second duration corresponding to the end effector.

[0162] In step S102 above, the change of the sampled signal within a preset time period meets the preset release condition, including:

[0163] S10231. Obtain the sampled signals of the end joints within the first time period before the current time. And calculate the signal difference between two adjacent sampled signals of each end joint within the first time period.

[0164] For example, for an end-effector joint, the controller can acquire sampled signals from a first time period prior to the current time at the current moment, obtaining a sampled signal sequence. The controller can then calculate the signal difference between two adjacent sampled signals in this sampled signal sequence, obtaining a signal difference sequence.

[0165] S10232. Obtain the sampled signals of the end effector within the second time period before the current time. And count the number of signals whose sampled signals are less than the second threshold.

[0166] For example, for an end effector, the controller can acquire sampled signals from a second time period prior to the current time at the current moment. The controller can then count the number of sampled signals within this second time period that are less than a second threshold.

[0167] S10233. If the signal difference is less than the first threshold and the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0168] For example, the controller can compare the signal difference obtained in step S10231. If the signal difference of the at least one end joint is less than the first threshold, it indicates that the at least one end joint remains stationary.

[0169] The controller can compare the number of signals obtained in step S10232. If the number of signals is less than the third threshold, it indicates that the end effector is in a stationary state.

[0170] If both the at least one end joint and the end effector are stationary, it can be determined that the change of the sampled signal within a preset time period meets the preset release condition.

[0171] Otherwise, if the signal difference at the end effector joint is greater than the first threshold, it can be determined that the master hand is in an operating state. In this case, if the end effector is in a stationary state, the user operates the handle to move the master hand, but no control is exercised over the end effector.

[0172] Alternatively, if the number of signals is greater than or equal to the third threshold, it indicates that the end effector is being operated. In this case, if the end joint is stationary, it indicates that the user is operating on a fixed position.

[0173] In one example, when including an end joint and an end effector, based on the 7-joint robotic arm used in this application, the end joint can be the 7th joint, and the end effector can be a gripper.

[0174] In one example, when multiple distal joints are included, the number of distal joints can be 2, 3, 4, etc.

[0175] Specifically, when the robotic arm includes two end-effectors, based on the 7-joint robotic arm used in this application, the end-effectors can be the 7th and 6th joints, and the end effector can be a gripper. When the robotic arm includes three end-effectors, based on the 7-joint robotic arm used in this application, the end-effectors can be the 7th to 5th joints, and the end effector can be a gripper. And so on.

[0176] Preferably, the accuracy of the release judgment of this application can be maximized when the 7th joint, the 6th joint, and the gripper are included.

[0177] In this example, by integrating multi-point continuous monitoring of end-joint motion differences with statistical threshold analysis of end-effector signal amplitude, and combining dynamic feature extraction with dual time windows and multi-condition joint verification, high-precision identification and anti-interference safety judgment of the robotic arm's off-hand state are achieved, thus improving the accuracy of off-hand detection.

[0178] In one example, the robot may also have a status flag set.

[0179] S103. Update the robot's status flags according to the working status so that the robot can switch operating modes according to the status flags.

[0180] For example, the controller achieves decoupling mapping between working state and control mode through a dynamic update mechanism of status flag bits, providing a basis for state decision-making for adaptive switching of robot operating mode.

[0181] In one example, the controller can first obtain the robot's current working state according to the steps described above. Then, the controller can update its internal status flag register according to predefined status coding rules.

[0182] In one example, the register typically uses a bit-field design, with different bit fields representing the operating mode, security level, and exception type, respectively.

[0183] For example, this status flag can be denoted as flag. When flag=1, it indicates that the robot's master hand is in a hands-free state. When flag=0, it indicates that the robot's master hand is in an operating state.

[0184] In this example, the real-time update of the status flag is ensured to guarantee the real-time nature and consistency of the status update, so that other controllers of the robot can obtain the robot's status in a timely manner and thus quickly adjust the control strategy according to the real-time status.

[0185] In one example, when the controller determines that the robot is in a hands-free state, it can perform the following operations:

[0186] S104. Suspend the redundant joint obstacle avoidance strategy and reduce the friction compensation of the force-controlled joint.

[0187] For example, the controller optimizes the allocation of computing resources and improves control stability under specific working conditions through a dynamic reconfiguration mechanism of the control strategy.

[0188] In one example, when a status flag indicates that the robot has entered a hands-free state, the controller first sends a pause command to the obstacle avoidance module. This command reduces CPU utilization by disabling collision detection threads on redundant joints or disabling relevant sensor data input.

[0189] In one example, the controller dynamically adjusts the compensation parameters based on the friction model of the force-controlled joint, reducing the friction compensation coefficient to decrease joint vibration caused by over-compensation when the hand is off.

[0190] For example, the friction compensation coefficient can be linearly reduced from 1.0 during normal operation to 0.6-0.8.

[0191] In one example, the controller can implement policy suspension based on task scheduling of the real-time operating system by suspending the priority of obstacle avoidance tasks or setting them to a sleep state.

[0192] In another example, the controller can use a parameter table lookup method to read the corresponding value from the pre-stored compensation parameter table based on the current status flag, thereby improving the efficiency of parameter adjustment.

[0193] Among them, the redundant joint obstacle avoidance strategy refers to the multiple collision detection and avoidance mechanism configured to improve the reliability of the system. Its pause can avoid false triggering caused by environmental disturbances when the hand is off.

[0194] Friction compensation is a nonlinear control term used in the force control system to counteract the mechanical friction of the joints. Reducing it can lower the force feedback noise when there is no operation.

[0195] In this example, collision detection calculation tasks of redundant joints are dynamically disabled to reduce system resource consumption, and friction compensation parameters of force-controlled joints are simultaneously optimized to suppress mechanical vibration in the inactive state, thereby achieving a synergistic improvement in control accuracy and computational efficiency of the robot in low-priority working mode.

[0196] In one example, when the controller determines that the robot is in a hands-free state, it can perform the following operations:

[0197] S105. If the robot is in a hands-free working state, switch the robot from the current master-slave synchronization mode to the joint impedance mode.

[0198] For example, the controller achieves a flexible control transition from master-slave synchronization to joint impedance in the off-hand state through a seamless switching mechanism of control modes.

[0199] In one example, when the status flag detects a release state, the controller first sends a stop command to the master-slave synchronization module, terminating position / force tracking between the master and slave hands. Simultaneously, the controller can activate the joint impedance control module.

[0200] In one example, the joint impedance control module adjusts the joint stiffness (K) and damping (D) parameters to make the robot end effector exhibit passive compliance characteristics similar to a spring-damped system.

[0201] In one example, the controller can switch modes based on the state transition of the control mode manager by switching control algorithm pointers or calling different dynamic link libraries.

[0202] In another example, the controller can use a gradient parameter transition method, gradually attenuating the master-slave synchronization gain and increasing the impedance parameter during the transition period to avoid the impact caused by mode switching.

[0203] For example, the transition period can be 100-200ms.

[0204] Among them, the master-slave synchronization mode means that the robot end strictly follows the motion / force commands input by the master end, which is suitable for precision operation scenarios.

[0205] Among them, the joint impedance mode achieves environmental adaptation by simulating the physical impedance characteristics, and is suitable for safe interaction when the hands are off.

[0206] In this example, the switching mechanism ensures control continuity and environmental adaptability through the preloading of dual-mode parameters and dynamic calibration of the switching threshold.

[0207] Figure 2 Flowchart of the off-hand detection method provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the method includes:

[0208] S201, System Initialization.

[0209] For example, the robot's control system is initialized.

[0210] S202. Periodically collect encoder values ​​from the two end joints and the gripper.

[0211] For example, when the end effector includes two end joints and a gripper, the controller can continuously acquire encoder values ​​of the two end joints and the gripper during robot operation.

[0212] In one example, the encoder value is the sampling information mentioned above.

[0213] S203. Calculate the angle change within the sliding window.

[0214] For example, the controller can set sliding windows for the end joint and the gripper respectively.

[0215] For example, the sliding window of the end joint can be 200ms, and the sliding window of the gripper can be 100ms.

[0216] In one example, the last moment of the sliding window could be the current moment.

[0217] S204. Whether the change determined by the encoder value of the end joint is less than the first threshold, and whether the number of encoder values ​​of the gripper that are less than the second threshold is less than the third threshold.

[0218] For example, the controller can acquire the encoder value of the end-effector within the sliding window. Within the sliding window, the controller can calculate the change in the encoder value of the end-effector and determine whether the change is less than a first threshold.

[0219] Furthermore, the controller can acquire the encoder value of the gripper within the sliding window. Within this sliding window, the controller can count the number of times the gripper's encoder value is less than a second threshold. Then, the controller can determine whether this number is less than a third threshold.

[0220] In one example, this change can be determined based on the difference between two adjacent encoder values.

[0221] If the controller's judgments on the end effector and gripper both meet the conditions, then step S206 is executed. Otherwise, step S205 is executed.

[0222] S205, determined to be in operation state.

[0223] S206, determined to be in a hands-free state.

[0224] Figure 3 This is a schematic diagram of the off-hand detection device provided in this application, as shown below. Figure 3 As shown, the off-hand detection device 300 provided in this embodiment includes:

[0225] The acquisition module 301 is used to acquire the sampling signal of at least one end effector unit of the robot's master hand.

[0226] The judgment module 302 is used to determine the robot's working state as an unattended state if the change of the sampled signal within a preset time period meets the preset unattended condition. Otherwise, it determines the robot's working state as an operating state.

[0227] In one example, module 301 is used for:

[0228] The encoder value of the encoder of the end effector unit is obtained according to the preset sampling frequency.

[0229] The sampling signal is generated based on the encoder value.

[0230] In one example, the end effector unit is an end joint and / or an end effector.

[0231] In one example, the end effector is an end joint, and the preset duration includes a first duration. The judgment module 302 is used for:

[0232] Within the first time period, the signal difference between two adjacent sampled signals is obtained.

[0233] If the signal difference is less than the first threshold within the first time period, then the change of the sampled signal within the preset time period is determined to meet the preset release condition.

[0234] In one example, the end effector is a terminal actuator, and the preset duration includes a second duration. The judgment module 302 is used for:

[0235] The number of sampled signals that are less than the second threshold within the second time period is counted.

[0236] If the number of signals is less than the third threshold, then the change of the sampled signal within the preset time period is determined to meet the preset release condition.

[0237] In one example, the end effector unit includes an end effector and at least one end joint, and the preset duration includes a first duration corresponding to the end joint and a second duration corresponding to the end effector. The determination module 302 is used for:

[0238] Acquire the sampled signals of the end joints within a first time period prior to the current time; and calculate the signal difference between two adjacent sampled signals of each end joint within the first time period;

[0239] Acquire the sampled signal of the end effector within a second time period prior to the current moment; and count the number of signals whose sampled signal is less than a second threshold.

[0240] If the signal differences are all less than the first threshold and the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

[0241] In one example, the device further includes:

[0242] The control module 303 is used to update the robot's status flags according to the working status, so that the robot can switch the operating mode according to the status flags.

[0243] In one example, control module 303 is used for:

[0244] If the robot is in an off-hand state, then switch the robot from the current master-slave synchronization mode to the joint impedance mode.

[0245] In one example, control module 303 is used for:

[0246] The redundant joint obstacle avoidance strategy is suspended, and the friction compensation of the force-controlled joints is reduced.

[0247] The off-hand detection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0248] Figure 4 This is a schematic diagram of the controller provided in this application. Figure 4 As shown, the controller 400 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the controller 400 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0249] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0250] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0251] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0252] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0253] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0254] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0255] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0256] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0257] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0258] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0259] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0260] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0261] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0262] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0263] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting hand-off detection, characterized in that, The main hand used in robots includes: Acquire sampling signals from at least one end effector unit of the robot's main hand; If the change of the sampled signal within a preset time period meets the preset hand-free condition, then the working state of the robot is determined to be the hand-free state; otherwise, the working state of the robot is determined to be the operating state.

2. The method according to claim 1, characterized in that, Acquiring a sampling signal from at least one end effector unit of the robot's master hand includes: The encoder value of the encoder of the end operation unit is obtained according to the preset sampling frequency; The sampling signal is generated based on the encoder value.

3. The method according to claim 1, characterized in that, The end effector unit is an end joint and / or an end effector.

4. The method according to claim 3, characterized in that, The end effector is an end joint, and the preset duration includes a first duration. The change of the sampled signal within a preset time period conforms to a preset release condition, including: Obtain the signal difference between two adjacent sampled signals; If the signal difference is less than the first threshold within the first time period, then it is determined that the change of the sampled signal within the preset time period meets the preset release condition.

5. The method according to claim 3, characterized in that, The end-efficiency unit is an end effector, and the preset duration includes a second duration; The change of the sampled signal within a preset time period conforms to a preset release condition, including: The number of sampled signals that are less than the second threshold within the second time period is counted; If the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

6. The method according to claim 3, characterized in that, The end effector unit includes an end effector and at least one end joint, and the preset duration includes a first duration corresponding to the end joint and a second duration corresponding to the end effector. The change of the sampled signal within a preset time period conforms to a preset release condition, including: Acquire the sampled signals of the end joints within a first time period prior to the current time; and calculate the signal difference between two adjacent sampled signals of each end joint within the first time period; Acquire the sampled signal of the end effector within a second time period prior to the current moment; and count the number of signals whose sampled signal is less than a second threshold. If the signal differences are all less than the first threshold and the number of signals is less than the third threshold, then it is determined that the change of the sampled signal within the preset time period meets the preset hand-off condition.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Based on the working status, update the robot's status flag to enable the robot to switch operating modes according to the status flag.

8. The method according to any one of claims 1-6, characterized in that, The method further includes: If the robot's working state is off-hand state, then the robot's current master-slave synchronization mode will be switched to joint impedance mode.

9. The method according to claim 8, characterized in that, Before switching the robot from the current master-slave synchronization mode to the joint impedance mode, the following steps are also included: The redundant joint obstacle avoidance strategy is suspended, and the friction compensation of the force-controlled joints is reduced.

10. A hand-free detection device, characterized in that, The main hand used in robots includes: An acquisition module is used to acquire sampling signals from at least one end effector unit of the robot's main hand; The judgment module is used to determine that the working state of the robot is the off-hand state if the change of the sampled signal within a preset time period meets the preset off-hand condition; otherwise, it determines that the working state of the robot is the operating state.

11. A controller, characterized in that, include: Memory, processor; The memory stores computer-executable instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

12. A robot, characterized in that, The robot's main hand includes at least one end effector unit and a controller as described in claim 11; The end effector unit is a user-operated contactor and / or at least one end joint fixedly connected to the end effector.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images