Robot finger control methods, systems, devices, and non-volatile storage media

Abstract

This invention discloses a method, system, device, and non-volatile storage medium for controlling a robot finger. The method includes: receiving control commands input from a target account via an EtherCAT bus; identifying control parameters based on the control commands, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determining a finger control signal and a finger to be controlled in the target robot based on the control parameters; and sending the finger control signal to a driver board corresponding to the finger to be controlled via an SPI interface, wherein the driver board controls the movement of the corresponding finger based on the finger control signal. This invention solves the technical problem of achieving modular distributed control of high-degree-of-freedom joints in humanoid robot dexterous hands within a limited space.

Description

Technical Field

[0001] This invention relates to the field of robot control technology, and more specifically, to a robot finger control method, system, device, and non-volatile storage medium. Background Technology

[0002] Current humanoid robot dexterous hand systems mostly employ a centralized control architecture, where a single main control unit directly drives all joint motors, controlling the speed and position of each motor separately through multiple PWM, analog, or pulse signals. Such systems typically require independent drive circuits and signal lines for each joint, resulting in complex wiring, numerous interfaces, and a large space footprint, making it difficult to arrange high-density joints with seven or more degrees of freedom within the limited space of the hand structure. Furthermore, there is a general lack of system-level integration of tactile perception; fingertip sensor data is usually uploaded through independent channels, failing to form a closed-loop feedback with joint movements, leading to low precision in grasping force control and weak environmental adaptability.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a robot finger control method, system, device, and non-volatile storage medium to at least solve the technical problem that it is difficult to achieve modular distributed control of high-degree-of-freedom joints in a limited space for the dexterous hand of a humanoid robot.

[0005] According to one aspect of the present invention, a robot finger control method is provided, comprising: receiving control instructions based on target account input via an EtherCAT bus; identifying control parameters based on the control instructions, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determining a finger control signal and a finger to be controlled in a target robot based on the control parameters; and sending the finger control signal to a drive board corresponding to the finger to be controlled via an SPI interface, wherein the drive board controls the movement of the corresponding finger to be controlled based on the finger control signal.

[0006] Optionally, configuration parameters are sent to multiple finger tactile sensors in the target robot via a UART interface. The configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format. Confirmation indications are received from each of the multiple finger tactile sensors, wherein the confirmation indication indicates that the corresponding finger tactile sensor has been successfully configured.

[0007] Optionally, when the control parameters include a motion mode, the finger control signal is determined based on the control parameters, including: when the motion mode is a multi-finger linkage mode, determining the motion trajectory corresponding to each of the multiple fingers to be controlled based on the control command; mapping the motion trajectory corresponding to each of the multiple fingers to be controlled to the movement parameters corresponding to each of the multiple fingers to be controlled; and generating the finger control signal corresponding to each of the multiple fingers to be controlled based on the movement parameters corresponding to each of the multiple fingers to be controlled.

[0008] Optionally, when the control parameters include a motion mode, sending the finger control signal to the driver board corresponding to the finger to be controlled includes: when the motion mode is a single-finger independent motion mode, allocating a chip select signal line to the driver board corresponding to the finger to be controlled based on the SPI interface; and sending the finger control signal to the driver board corresponding to the finger to be controlled based on the chip select signal line.

[0009] According to another aspect of the present invention, a robot finger control system is also provided, comprising: a control board connected to a plurality of drive boards for implementing the robot finger control method of any one of claims 1 to 4; the plurality of drive boards are respectively connected to their respective corresponding finger motors for receiving control signals based on an SPI interface and controlling the corresponding finger movements based on the finger control signals.

[0010] Optionally, the control panel is connected to the finger tactile sensors corresponding to each of the multiple fingers.

[0011] According to another aspect of the present invention, a robot finger control device is also provided, comprising: a receiving module for receiving control commands input based on a target account via an EtherCAT bus; an identification module for identifying control parameters based on the control commands, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; a determining module for determining a finger control signal and a finger to be controlled in a target robot based on the control parameters; and a sending module for sending the finger control signal to a drive board corresponding to the finger to be controlled via an SPI interface, wherein the drive board controls the movement of the corresponding finger to be controlled based on the finger control signal.

[0012] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described robot finger control methods.

[0013] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor for running a program, wherein the program executes any of the above-described robot finger control methods during runtime.

[0014] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described robot finger control methods.

[0015] In this embodiment of the invention, a robot finger control method is adopted. Control commands based on target account input are received via an EtherCAT bus. Based on the control commands, control parameters are identified, including at least one of the following: motion mode, motion speed, and torque parameters. Based on the control parameters, finger control signals and the fingers to be controlled in the target robot are determined. The finger control signals are sent to the corresponding drive board of the finger to be controlled via an SPI interface. The drive board controls the movement of the corresponding finger based on the finger control signals, achieving the separation of the control module from the drive board corresponding to each finger. This improves the flexibility of finger control and solves the technical problem of achieving modular distributed control of high-degree-of-freedom joints in a limited space in current humanoid robot dexterous hands. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a computer terminal for implementing a robot finger control method is shown.

[0018] Figure 2 This is a flowchart illustrating a robot finger control method according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of a robot finger control system provided according to an embodiment of the present invention;

[0020] Figure 4 This is a structural block diagram of a robot finger control device provided according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of the present invention, a method embodiment for controlling a robot finger is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a robot finger control method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0025] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the robot finger control method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the robot finger control method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0027] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0028] Figure 2 This is a flowchart illustrating a robot finger control method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0029] Step S202: Receive control commands based on the target account input via the EtherCAT bus.

[0030] In this step, instruction information initiated by the target account can be obtained from an external source through the EtherCAT communication protocol. The instruction content contains explicit requirements for the dexterous hand to perform actions, such as motion parameters or operating modes. This receiving behavior relies entirely on the EtherCAT bus as the sole communication channel and does not involve other network or protocol forms, ensuring that control instructions are reliably imported into the system in a standard industrial bus manner.

[0031] As an EtherCAT slave device, the control board initializes the physical layer link upon power-up, establishes a physical connection with the master device (such as the humanoid robot's main control unit), and performs network topology scanning and device address allocation via the EtherCAT protocol to ensure its unique identifier and normal communication channel in the bus network. Subsequently, the control board continuously listens for periodic Process Data Objects (PDOs) broadcast by the EtherCAT master station. These PDOs are generated and sent by the target account through the host computer system or the robot motion planning module and contain target motion parameters, such as the target speed of each joint, target position, motion mode number (such as "grasp", "pinch", "translation", etc.), and enable signals.

[0032] Step S204: Based on the control command, identify control parameters, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters.

[0033] In this step, based on control commands, the control board extracts and identifies several key control parameters from the received EtherCAT process data. These parameters directly determine the dexterous hand's motion behavior and output characteristics. The motion mode is a core command specifying the type of action being performed, such as predefined modes like "full-finger grasp," "fingertip pinch," "palm support," or "independent single-finger fine-tuning." Each mode corresponds to a set of pre-calibrated multi-joint collaborative trajectories or position-force coupling relationships. The control board calls the corresponding control strategy based on the mode number, without needing to calculate the path of each joint in real time. The motion speed parameter sets the speed of movement for each joint or the entire finger, typically expressed as the change in angle per unit time (e.g., ° / s) or the linear velocity of the end effector. The control board uses this value to plan the speed of joint movement, ensuring smooth motion and avoiding impact. In multi-finger linkage scenarios, this speed can be uniformly applied to all participating joints or proportionally distributed to different finger joints to maintain morphological consistency.

[0034] Torque parameters are used to directly or indirectly control the magnitude of the torque output by the motor. They can be expressed as a target current value, torque compensation coefficient, or adaptive force control threshold based on tactile feedback. When the system enters force control mode, the control board will dynamically adjust the PWM output according to this parameter and the real-time feedback phase current data, so that the motor output is consistent with the target torque, thereby achieving smooth gripping or fine operation of objects and avoiding crushing or slipping.

[0035] When recognizing the above parameters, the control board performs validity checks, such as whether the speed exceeds hardware limits, whether the torque exceeds safety boundaries, and whether the motion mode exists in the preset library, ensuring that any input command is executed within the system's safe range. After recognition, the parameters are distributed to the corresponding drive boards, driving the joint motors to respond in a coordinated manner, achieving precise closed-loop control from command input to physical action.

[0036] Step S206: Based on the control parameters, determine the finger control signal and the finger to be controlled in the target robot.

[0037] In this step, after identifying the control parameters—including motion mode, motion speed, and torque parameters—the control board dynamically determines the fingers to be controlled and their corresponding control signals based on the current dexterous hand's structural configuration and the physical mapping relationship between each finger. First, the control board analyzes the set of participating joints associated with the motion mode. For example, if the motion mode is "full-finger grasp," the system automatically identifies all active joints of the thumb, index finger, middle finger, ring finger, and little finger as the objects to be controlled; if it is "finger-tip pinch," only the distal phalangeal joints of the thumb and index finger are activated, while the other fingers remain stationary or enter a safe holding state. Based on this mapping relationship, the control board filters the required finger number and its corresponding physical address from the system's joint list. Subsequently, the control board combines the motion speed and torque parameters to calculate precise control signals for each joint of each finger to be controlled. These control signals include: target position or target speed commands, the current reference value corresponding to the desired output torque, and necessary acceleration limits and smoothing curve parameters. For joints using speed control mode, the control board generates drive commands based on angular velocity; for force control mode, it dynamically generates reference values ​​for the current closed loop based on torque parameters and current load feedback to achieve compliant contact.

[0038] After generating control signals, the control board sends customized instruction packets to the corresponding driver boards via the SPI bus. Each driver board only receives instructions related to the finger it is connected to; other unrelated driver boards remain in standby mode to avoid wasting resources. The control board also records the instruction issuance timestamp and the target finger number for matching subsequent status feedback and tracing anomalies.

[0039] The entire process achieves precise "command-finger" mapping, ensuring that whether it is single-finger fine-tuning or complex multi-finger coordination, the system can accurately translate control intentions into specific physical actions with minimal delay, thereby realizing the intelligent, directional, and reproducible control capabilities of a highly dexterous hand in complex operation scenarios.

[0040] Step S208: Based on the SPI interface, the finger control signal is sent to the driver board corresponding to the finger to be controlled, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signal.

[0041] In this step, the control board sends the finger control signals, independently generated for each finger to be controlled, to the corresponding driver board one by one in a compact data frame format via the SPI interface. Each data frame contains the target joint position or speed command, the current reference value corresponding to the desired output torque, the motion mode flag, and the enable control command. All parameters are packaged according to a predefined communication protocol to ensure that the driver board can accurately parse and execute them. After receiving the data, the driver board first verifies the data integrity and address matching. If the verification passes, it immediately updates the internal control register and starts the closed-loop control algorithm. Based on the built-in integrated driver chip (such as Infineon 6EDL7141), the driver board converts the received speed or torque command into a PWM duty cycle signal, precisely controls the switching timing of the H-bridge MOSFET, and drives the motor to run along the target trajectory. At the same time, the driver board collects the phase current of the motor and encoder feedback in real time, and combines it with the external contact force data transmitted by the tactile sensor to dynamically adjust the output, realizing high-response closed-loop control of the target torque and motion accuracy. During operation, the drive board continuously transmits feedback data, including the actual position of each joint, current value, temperature status, and abnormal indicators, back to the control board via the SPI channel, forming a complete bidirectional control loop. If overcurrent, stall, or communication abnormality is detected, the drive board will immediately trigger a safety protection mechanism, stop the motor output, and report fault information to ensure system safety.

[0042] The entire process is centrally scheduled by the control board, with each driver board executing independently. No real-time computation by the main controller is required, significantly reducing system latency and improving the synchronization and response speed of multi-finger coordination. High-bandwidth, low-latency communication via the SPI interface enables millisecond-level precision in controlling the movement of each finger, ultimately achieving stable, compliant, and high-precision grasping and manipulation of target objects by a dexterous hand in complex tasks.

[0043] Through the above steps, the control module can be separated from the drive board corresponding to each finger, thereby improving the flexibility of finger control and solving the technical problem that humanoid robot dexterous hands are currently unable to achieve modular distributed control of high-degree-of-freedom joints in a limited space.

[0044] As an optional embodiment, configuration parameters are sent to multiple finger tactile sensors in the target robot based on the UART interface. The configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format. Confirmation indications are received from each of the multiple finger tactile sensors, wherein the confirmation indication indicates that the corresponding finger tactile sensor has been successfully configured.

[0045] Optionally, the control board sends a sequence of independent configuration commands to each fingertip tactile sensor in the target robot via a UART interface to initialize parameters. Configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format. The sampling frequency sets the time interval for the sensor to collect pressure or strain data, such as 100Hz, 500Hz, or 1kHz, to adapt to the dynamic response requirements of different operating scenarios. The sensitivity threshold defines the minimum pressure value required to trigger a valid tactile signal, avoiding environmental noise interference; for example, it is set to 0.1N or 0.5N. The data output format specifies the encoding structure of the sensor's returned data, such as ASCII strings, binary packets, or a structure containing timestamps, ensuring the control board can correctly parse the raw data. Each configuration command consists of a specific protocol frame, containing the target sensor's unique address identifier, parameter command code, and verification field. The control board sends these commands sequentially in a preset order to ensure no data conflicts occur. After receiving a valid configuration command, each tactile sensor's internal microprocessor parses and writes it to non-volatile memory, then performs a self-test and parameter activation process. If the configuration is successful, the sensor will return an acknowledgment message containing an "ACK" identifier and its own ID to the control board via UART. The message will also include the effective parameter values ​​for verification. If the configuration fails (e.g., due to a verification error, address mismatch, or hardware malfunction), it will return "NACK" along with an error code.

[0046] After sending each configuration command, the control board can set a fixed timeout window to receive confirmation responses from the corresponding sensor. If an "ACK" is received within the timeout period, the sensor configuration is marked as complete, and the system status table is updated. If no response is received or a "NACK" is received, the system will retry up to three times. If the retry still fails, the sensor will be recorded as offline or faulty, and an anomaly will be reported to the main control system. At the same time, the subsequent data reading process for that sensor will be skipped to ensure that the overall system can continue to operate based on the other normal sensors.

[0047] After all tactile sensors have completed configuration and returned confirmation instructions, the control board enters normal perception mode and begins periodically polling the data streams of each sensor. This provides realistic environmental interaction feedback for subsequent force control algorithms, enabling the dexterous hand to truly perceive contact states, object shapes, and grasping stability. This UART-based independent configuration mechanism ensures the flexibility, scalability, and high reliability of the multi-finger tactile system.

[0048] The system sends configuration parameters, including sampling frequency, sensitivity threshold, and data output format, to multiple finger tactile sensors in the target robot via the UART interface and receives confirmation indications from each sensor. These confirmation indications clearly indicate that the corresponding sensor has completed parameter configuration and is in a ready state. This ensures that the sensing capabilities of all tactile sensing units have been initialized and successfully verified as needed before the dexterous hand executes finger movement control based on the SPI interface. This effectively solves the problem of unreliable environmental perception data and unstable system response caused by the lack of a tactile sensor configuration status feedback mechanism in existing technologies. It realizes centralized configuration and reliable verification of multi-finger tactile systems, improving the perception accuracy and control coordination of humanoid robots in complex environments under a distributed architecture.

[0049] As an optional embodiment, when the control parameters include a motion mode, determining the finger control signal based on the control parameters includes: when the motion mode is a multi-finger linkage mode, determining the motion trajectory corresponding to each of the multiple fingers to be controlled based on the control command; mapping the motion trajectory corresponding to each of the multiple fingers to be controlled to the movement parameters corresponding to each of the multiple fingers to be controlled; and generating the finger control signal corresponding to each of the multiple fingers to be controlled based on the movement parameters corresponding to each of the multiple fingers to be controlled.

[0050] Optionally, when the motion mode included in the control parameters is a multi-finger linkage mode, the control board first extracts the mode identifier from the EtherCAT instruction and matches it to a multi-finger cooperative motion library pre-stored in local Flash or RAM. This motion library pre-stores joint cooperative trajectories for various typical operating scenarios, such as "full-finger grasping," "finger pinching," "palm lifting," or "dynamic gripping." Each mode is associated with a set of standardized motion trajectories generated based on robotic modeling or teaching learning, including the position, velocity, and acceleration change curves of each finger and joint in the time dimension. Based on the current motion mode, the control board retrieves the matching trajectory set from the motion library and parses the motion trajectory data of all active joints corresponding to each finger to be controlled. For example, in the "full-finger grasping" mode, the system identifies the adduction-flexion joint of the thumb, the proximal and distal phalanges of the index finger, the three phalanges of the middle and ring fingers, and the two phalanges of the little finger as the joints involved in the linkage, and extracts their trajectory functions from the initial pose to the target pose.

[0051] Subsequently, the control board maps each joint trajectory to executable movement parameters, including the target angle value, target angular velocity, maximum permissible acceleration, trajectory interpolation step size, and motion duration. These parameters are normalized and limited based on the mechanical structure's degree-of-freedom constraints, motor dynamic response characteristics, and safety boundaries to ensure the trajectory is smooth and feasible within the hardware's capabilities. For example, if a trajectory requires a joint to move from 0° to 65° within 200ms, the control board breaks it down into 100 time steps, each corresponding to an increment of 0.65° and a constant speed command.

[0052] Based on the mapped movement parameters, the control board independently generates a unique finger control signal for each joint of each finger to be controlled. These signals include the target position (or target velocity), the current reference value corresponding to the desired torque, and the movement direction flag, all encapsulated into SPI data frames according to the driver board's communication protocol. The control board sends these signals sequentially according to the physical address of each driver board, based on priority or timing order, ensuring high synchronization of multi-finger movements in time and avoiding motion distortion or loss of coordination due to communication delays.

[0053] The generated finger control signals not only drive each joint to move along a preset trajectory, but also simultaneously activate force control enable positions, enabling the system to achieve trajectory-force dual closed-loop control during movement by combining tactile feedback. For example, when grasping fragile objects, the system dynamically reduces the torque reference value while following the trajectory to prevent overload. The entire process is uniformly scheduled and globally coordinated by the control board, ensuring that in multi-finger linkage mode, the dexterous hand can achieve natural, smooth, and adaptive collaborative operations like a human hand, significantly improving the humanoid robot's operational capabilities and task generalization in unstructured environments.

[0054] After receiving control commands containing motion patterns via the EtherCAT bus, when the motion pattern is identified as a multi-finger linkage mode, the system no longer generates a general control signal based solely on a single control parameter. Instead, it further analyzes the individual motion trajectories of multiple fingers to be controlled and precisely maps these trajectories to movement parameters corresponding to the independent motion characteristics of each finger. Based on these movement parameters, it generates targeted finger control signals and finally sends these independent control signals synchronously to the corresponding driver board via the SPI interface. This achieves precise execution of multi-finger coordinated motion, effectively solving the problem of collaborative control failure caused by the lack of trajectory decomposition and parameter conversion mechanisms for multi-finger linkage intentions in a distributed architecture. This enables humanoid robot dexterous hands to achieve synchronous, coordinated, and high-precision motion control of multiple fingers in complex tasks.

[0055] As an optional embodiment, when the control parameters include a motion mode, sending a finger control signal to the driver board corresponding to the finger to be controlled includes: when the motion mode is a single-finger independent motion mode, allocating a chip select signal line to the driver board corresponding to the finger to be controlled based on the SPI interface; and sending the finger control signal to the driver board corresponding to the finger to be controlled based on the chip select signal line.

[0056] Optionally, after receiving control commands and identifying the motion modes based on the EtherCAT bus, when the motion mode is detected as a single-finger independent motion mode, a dedicated chip select signal line is dynamically allocated to the driver board corresponding to the finger to be controlled through the SPI interface. This ensures that the control signal is transmitted to the target driver board only through this chip select signal line, while other driver boards connected in parallel to the same SPI bus are in a high-impedance state because they are not selected. This effectively isolates the non-target driver boards from receiving signals incorrectly, thereby avoiding false triggering or control disorder caused by signal conflicts or parallel responses when multiple driver boards share the SPI bus. This achieves accurate selection and signal isolation of the target finger driver board in the single-finger independent motion mode, significantly improving the control accuracy and system stability of the dexterous hand in a distributed architecture.

[0057] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the robot finger control method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0059] According to an embodiment of the present invention, a robot finger control system is also provided. Figure 3 This is a schematic diagram of a robot finger control system provided according to an embodiment of the present invention, such as... Figure 3As shown, it includes: a control board connected to multiple drive boards for implementing any of the above-mentioned robot finger control methods; multiple drive boards are respectively connected to their respective finger motors for receiving control signals based on the SPI interface and controlling the corresponding finger movements based on the finger control signals.

[0060] Optionally, the control panel is connected to the finger tactile sensors corresponding to each of the multiple fingers.

[0061] This system adopts a separate drive and control architecture, with the control board and joint drive board separated. The control board uses TI's TMS320F28P650DK9 and implements EtherCAT communication via DP83826ERHB, facilitating integration into mainstream humanoid robot EtherCAT communication topologies. Each drive board interacts with the control board via SPI, meeting control speed requirements. The drive board includes motor drive circuitry, with an integrated drive chip at its core, such as the Infineon 6EDL7141, which integrates phase current detection and internal six-step commutation. Receiving the motor Hall signal requires only one PWM channel to control the motor, saving control board resources. External MOSFETs can be used to adapt to different motor drive requirements. External tactile sensors on the robot's fingertips are configured via UART and receive data feedback, enhancing the dexterous hand's environmental perception.

[0062] According to embodiments of the present invention, a robot finger control device for implementing the above-described robot finger control method is also provided. Figure 4 This is a structural block diagram of a robot finger control device provided according to an embodiment of the present invention, such as... Figure 4 As shown, the robot finger control device includes: a receiving module 402, an identification module 404, a determining module 406, and a sending module 408. The robot finger control device will be described below.

[0063] The receiving module 402 is used to receive control commands based on target account input via the EtherCAT bus.

[0064] The identification module 404, connected to the receiving module 402, is used to identify control parameters based on control commands, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters.

[0065] The determination module 406, connected to the recognition module 404, is used to determine the finger control signal and the finger to be controlled in the target robot based on the control parameters.

[0066] The transmitting module 408 and the determining module 406 are used to transmit finger control signals to the driver board corresponding to the finger to be controlled based on the SPI interface, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signals.

[0067] It should be noted that the receiving module 402, the identification module 404, the determining module 406, and the sending module 408 mentioned above correspond to steps S202 to S208 in the embodiments. Multiple modules implement the same instances and application scenarios as their corresponding steps, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run in the computer terminal 10 provided in the embodiments.

[0068] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0069] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the robot finger control method and device in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned robot finger control method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0070] The processor can access information and application programs stored in memory via a transmission device to perform the following steps: receiving control commands based on target account input via an EtherCAT bus; identifying control parameters based on the control commands, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determining finger control signals and the finger to be controlled in the target robot based on the control parameters; and sending the finger control signals to the corresponding driver board of the finger to be controlled via an SPI interface, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signals.

[0071] Optionally, the processor may also execute program code that performs the following steps: sending configuration parameters to multiple finger tactile sensors in the target robot via a UART interface, wherein the configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format; receiving confirmation indications returned by each of the multiple finger tactile sensors, wherein the confirmation indications indicate that the corresponding finger tactile sensor has been successfully configured.

[0072] Optionally, the processor may also execute program code that performs the following steps: when the control parameters include a motion mode, determining finger control signals based on the control parameters, including: when the motion mode is a multi-finger linkage mode, determining the motion trajectory corresponding to each of the multiple fingers to be controlled based on the control command; mapping the motion trajectory corresponding to each of the multiple fingers to be controlled to the movement parameters corresponding to each of the multiple fingers to be controlled; and generating finger control signals corresponding to each of the multiple fingers to be controlled based on the movement parameters corresponding to each of the multiple fingers to be controlled.

[0073] Optionally, the processor may also execute program code that performs the following steps: when the control parameters include a motion mode, sending a finger control signal to the driver board corresponding to the finger to be controlled, including: when the motion mode is a single-finger independent motion mode, allocating a chip select signal line to the driver board corresponding to the finger to be controlled based on the SPI interface; and sending the finger control signal to the driver board corresponding to the finger to be controlled based on the chip select signal line.

[0074] This invention provides a method for controlling robot fingers. The method involves receiving control commands input from a target account via an EtherCAT bus; identifying control parameters based on the control commands, whereby the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determining finger control signals and the fingers to be controlled in the target robot based on the control parameters; and sending the finger control signals to the corresponding drive board of the finger to be controlled via an SPI interface. The drive board controls the movement of the corresponding finger based on the finger control signals, achieving separation of the control module from the drive board corresponding to each finger. This improves the flexibility of finger control and solves the technical problem of achieving modular distributed control of high-degree-of-freedom joints in a limited space in current humanoid robot dexterous hands.

[0075] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0076] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the robot finger control method provided in the above embodiments.

[0077] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0078] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: receiving control instructions based on target account input via an EtherCAT bus; identifying control parameters based on the control instructions, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determining a finger control signal and a finger to be controlled in the target robot based on the control parameters; and sending the finger control signal to the driver board corresponding to the finger to be controlled via an SPI interface, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signal.

[0079] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: sending configuration parameters to multiple finger tactile sensors in the target robot via a UART interface, wherein the configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format; receiving confirmation indications returned by each of the multiple finger tactile sensors, wherein the confirmation indication indicates that the corresponding finger tactile sensor has been successfully configured.

[0080] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when the control parameters include a motion mode, determining finger control signals based on the control parameters, including: when the motion mode is a multi-finger linkage mode, determining the motion trajectory corresponding to each of the multiple fingers to be controlled based on the control command; mapping the motion trajectory corresponding to each of the multiple fingers to be controlled to the movement parameters corresponding to each of the multiple fingers to be controlled; and generating finger control signals corresponding to each of the multiple fingers to be controlled based on the movement parameters corresponding to each of the multiple fingers to be controlled.

[0081] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when the control parameters include a motion mode, sending a finger control signal to the driver board corresponding to the finger to be controlled, including: when the motion mode is a single-finger independent motion mode, allocating a chip select signal line to the driver board corresponding to the finger to be controlled based on the SPI interface; and sending the finger control signal to the driver board corresponding to the finger to be controlled based on the chip select signal line.

[0082] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can: receive control instructions based on target account input via an EtherCAT bus; identify control parameters based on the control instructions, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; determine a finger control signal and a finger to be controlled in a target robot based on the control parameters; and send the finger control signal to the driver board corresponding to the finger to be controlled via an SPI interface, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signal.

[0083] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0084] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0086] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] Furthermore, 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0088] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or 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 described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0089] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for controlling a robot's finger, characterized in that, include: Receives control commands based on target account input via EtherCAT bus; Based on the control command, control parameters are identified, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; Based on the control parameters, the finger control signal and the finger to be controlled in the target robot are determined; Based on the SPI interface, the finger control signal is sent to the driver board corresponding to the finger to be controlled, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signal.

2. The method according to claim 1, characterized in that, Also includes: Based on the UART interface, configuration parameters are sent to multiple finger tactile sensors in the target robot, wherein the configuration parameters include at least one of the following: sampling frequency, sensitivity threshold, and data output format; The system receives confirmation indications from each of the plurality of finger tactile sensors, wherein the confirmation indications indicate that the corresponding finger tactile sensor has been successfully configured.

3. The method according to claim 1, characterized in that, When the control parameters include a motion mode, determining the finger control signal based on the control parameters includes: When the movement mode is a multi-finger linkage mode, the movement trajectory of each of the multiple fingers to be controlled is determined based on the control command. Map the motion trajectory of each of the multiple fingers to be controlled to the movement parameters corresponding to each of the multiple fingers to be controlled. Based on the movement parameters corresponding to each of the plurality of fingers to be controlled, a finger control signal corresponding to each of the plurality of fingers to be controlled is generated.

4. The method according to any one of claims 1 to 3, characterized in that, When the control parameters include a motion mode, sending the finger control signal to the drive board corresponding to the finger to be controlled includes: When the movement mode is a single-finger independent movement mode, a chip select signal line is allocated to the driver board corresponding to the finger to be controlled based on the SPI interface; Based on the chip select signal line, the finger control signal is sent to the driver board corresponding to the finger to be controlled.

5. A robot finger control system, characterized in that, Includes a control board and multiple driver boards, among which, The control board is connected to the plurality of drive boards and is used to implement any one of the robot finger control methods of claims 1 to 4 above. The plurality of drive boards are respectively connected to their respective finger motors, and are used to receive the control signals based on the SPI interface and control the corresponding finger movements based on the finger control signals.

6. The system according to claim 5, characterized in that, Also includes: The control board is connected to the finger tactile sensors corresponding to each of the multiple fingers.

7. A robot finger control device, characterized in that, include: The receiving module is used to receive control commands input from the target account via the EtherCAT bus. The identification module is used to identify control parameters based on the control command, wherein the control parameters include at least one of the following: motion mode, motion speed, and torque parameters; The determination module is used to determine the finger control signal and the finger to be controlled in the target robot based on the control parameters. The transmitting module is used to send the finger control signal to the driver board corresponding to the finger to be controlled via the SPI interface, wherein the driver board controls the movement of the corresponding finger to be controlled based on the finger control signal.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, the device containing the non-volatile storage medium is controlled to perform the robot finger control method according to any one of claims 1 to 4.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the robot finger control method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the robot finger control method according to any one of claims 1 to 4.

Images