Stable operation control method, device and equipment of capsule robot in cavity and medium

Abstract

This invention discloses a method, apparatus, device, and storage medium for stable operation control of a capsule robot inside a cavity. The method includes: responding to an operation command after the capsule robot enters a target cavity, performing a three-dimensional image scan of the target cavity to obtain spatial contour information of the target cavity; determining the desired position state of the capsule robot based on the spatial contour information of the target cavity; acquiring current motion parameter data of the capsule robot in the target cavity, and determining the current motion state vector of the capsule robot based on the current motion parameter data; generating a current feedforward control command based on the desired position state and the current motion state vector; generating a current feedback control command based on the current motion state vector; generating a target control command based on the current feedforward control command and the current feedback control command; and sending the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology, and in particular to a method, apparatus, equipment and medium for stable operation control of a capsule robot inside a cavity. Background Technology

[0002] In the field of capsule robot diagnostic and treatment technology, the precise motion control of capsule robots operating inside cavities is a key link to ensure the accuracy of digestive tract examinations and improve the safety and effectiveness of diagnosis and treatment. It is directly related to the comprehensiveness of lesion screening and the accuracy of targeted operation, and is of great significance for the early diagnosis, precise drug administration and minimally invasive biopsy of cavity diseases.

[0003] Current motion control methods for capsule robots in intracavitary diagnosis and treatment mostly employ single feedforward control, lacking collaborative analysis of the capsule robot's real-time motion state and the cavity's spatial contour. Furthermore, due to cavity peristalsis, issues such as motion deviation and posture disorder easily occur, failing to provide efficient and reliable technical support for precise diagnosis and treatment in complex cavities. Therefore, a technical solution is needed to achieve stable operation of capsule robots within cavities, addressing the poor stability of capsule robots in cavities under traditional control methods. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for stable operation control of a capsule robot inside a cavity, so as to improve the stability of the capsule robot in the process of performing tasks inside the cavity.

[0005] According to one aspect of the present invention, a method for stable operation control of a capsule robot inside a cavity is provided, the method comprising:

[0006] The current motion parameter data of the capsule robot in the target cavity is obtained, and the current motion state vector of the capsule robot is determined based on the current motion parameter data;

[0007] Based on the current motion state vector and the desired position state, generate the current feedforward control command.

[0008] Based on the current motion state vector, generate the current feedback control command;

[0009] Generate a target control command based on the current feedforward control command and the current feedback control command;

[0010] The target control command is sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

[0011] According to another aspect of the present invention, a stable operation control device for a capsule robot inside a cavity is provided, the device comprising:

[0012] The position state determination module is used to respond to the operation command after the capsule robot enters the target cavity, perform three-dimensional image scanning of the target cavity to obtain the spatial contour information of the target cavity, and determine the desired position state of the capsule robot based on the spatial contour information of the target cavity.

[0013] The motion state vector determination module is used to acquire the current motion parameter data of the capsule robot in the target cavity, and determine the current motion state vector of the capsule robot based on the current motion parameter data;

[0014] The feedforward control command generation module is used to generate the current feedforward control command based on the current motion state vector and the desired position state.

[0015] The feedback control command generation module is used to generate the current feedback control command based on the current motion state vector.

[0016] The target control instruction generation module is used to generate target control instructions based on the current feedforward control instructions and the current feedback control instructions;

[0017] The target control command sending module is used to send the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform a stable operation control method for the capsule robot inside the cavity according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement a stable operation control method for a capsule robot inside a cavity according to any embodiment of the present invention.

[0023] The technical solution of this invention responds to the operational instructions after the capsule robot enters the target cavity by performing a three-dimensional image scan of the target cavity to obtain the spatial contour information of the target cavity. Based on the spatial contour information of the target cavity, the desired position state of the capsule robot is determined. The current motion parameter data of the capsule robot in the target cavity is acquired, and the current motion state vector of the capsule robot is determined based on the current motion parameter data. Based on the current motion state vector and the desired position state, a current feedforward control instruction is generated. Based on the current motion state vector, a current feedback control instruction is generated. Based on the current feedforward control instruction and the current feedback control instruction, a target control instruction is generated. The target control instruction is sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control instruction. It can collaboratively generate feedforward control instructions and feedback control instructions based on the cavity spatial contour and the real-time motion state vector of the capsule robot, achieving precise control of the capsule robot's motion posture and position state. This effectively solves the problems of control lag, trajectory deviation, and inaccurate target positioning in traditional capsule robots, improving the stability and accuracy of scanning and diagnostic operations inside the target cavity.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a stable operation control method for a capsule robot inside a cavity, according to Embodiment 1 of the present invention;

[0027] Figure 2 This is a flowchart of a method for stable operation control of a capsule robot inside a cavity, according to Embodiment 2 of the present invention;

[0028] Figure 3 This is a flowchart of a method for stable operation control of a capsule robot inside a cavity according to Embodiment 3 of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of a stable operation control device for a capsule robot inside a cavity, according to Embodiment 4 of the present invention.

[0030] Figure 5This is a schematic diagram of the structure of an electronic device for implementing a stable operation control method for a capsule robot inside a cavity, according to an embodiment of the present invention. Detailed Implementation

[0031] 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.

[0032] 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.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a method for stable operation control of a capsule robot inside a cavity, provided in Embodiment 1 of the present invention. This embodiment is applicable to cavity detection scenarios in the field of cavity diagnostic and treatment technology. It can be implemented by a device system for diagnosing and treating digestive tract cavities. The system control terminal acquires real-time motion state data of the capsule robot and spatial contour information of the target cavity, thereby achieving precise motion control and stable intracavitary operation of the capsule robot. This method can be executed by a stable operation control device for the capsule robot inside the cavity. This stable operation control device can be implemented in hardware and / or software and can be configured in a server used for cavity detection scenarios with a capsule robot. Figure 1 As shown, the method includes:

[0035] S101. In response to the operation command after the capsule robot enters the target cavity, perform a three-dimensional image scan of the target cavity to obtain the spatial contour information of the target cavity, and determine the desired position state of the capsule robot based on the spatial contour information of the target cavity.

[0036] S102. Obtain the current motion parameter data of the capsule robot in the target cavity, and determine the current motion state vector of the capsule robot based on the current motion parameter data.

[0037] S103. Based on the current motion state vector and the desired position state, generate the current feedforward control command.

[0038] S104. Generate the current feedback control command based on the current motion state vector.

[0039] S105. Generate the target control command based on the current feedforward control command and the current feedback control command.

[0040] S106. Send the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

[0041] The capsule robot can be used for gastrointestinal diagnosis and treatment. The work instructions can be commands issued by relevant technicians to instruct the capsule robot to perform tasks. The target cavity can be the cavity where the capsule robot needs to perform operations, such as the colon or gastrointestinal tract. The target cavity spatial contour information can be three-dimensional spatial contour data of the target cavity obtained through three-dimensional image scanning. The desired position state can be the desired position determined by relevant technicians based on the target cavity spatial contour information, adapted to different work scenarios.

[0042] For example, the capsule robot can perform a three-dimensional scan of the target cavity using its own image acquisition unit to obtain the spatial contour information of the target cavity. Then, relevant technicians can plan the desired position state according to actual needs and the operation scenario. For example, when the capsule robot enters the colon cavity to perform an axial scan, the relevant technicians can select the center point of the lumen as the desired position state.

[0043] The current motion parameter data can be real-time motion sensing data of the capsule robot during its movement inside the target cavity, including the capsule robot's three-axis linear acceleration, three-axis angular velocity, and three-dimensional position coordinates. The current motion state vector can be a multi-dimensional state vector containing the capsule robot's current motion parameter data and the corresponding roll angle, pitch angle, and yaw angle. The inertial measurement unit can be a miniature inertial sensing unit carried by the capsule robot itself, used to collect the capsule robot's motion data.

[0044] For example, motion data can be collected by the inertial measurement unit carried by the capsule robot itself. The inertial measurement unit can combine the positioning information to calculate the attitude and position, and finally obtain the current motion state vector of the capsule robot.

[0045] Furthermore, to achieve accurate calculation of the capsule robot's motion state and improve the accuracy of the current motion state vector calculation, in one optional embodiment, the current motion parameter data of the capsule robot in the target cavity is acquired, and the current motion state vector of the capsule robot is determined based on the current motion parameter data, including:

[0046] Step a1: Obtain the triaxial linear acceleration and triaxial angular velocity of the capsule robot through the inertial measurement unit of the capsule robot.

[0047] Step a2: Determine the attitude angle of the capsule robot based on the three-axis linear acceleration and three-axis angular velocity.

[0048] Step a3: Determine the current motion state vector based on the current position and attitude angle of the capsule robot relative to the target cavity.

[0049] Among them, the three-axis linear acceleration can be the axial acceleration data of the capsule robot in three-dimensional space, and the three-axis angular velocity can be the rotational angular velocity data of the capsule robot around the three-dimensional axes.

[0050] For example, the inertial measurement unit can use the measurement chip built into the capsule robot to collect motion data at a frequency set by relevant technicians according to actual needs. For example, the inertial measurement unit can collect three-axis linear acceleration of [0.05, 0.02, 9.8] m / s² and three-axis angular velocity of [0.1, 0.05, 0] rad / s.

[0051] Among them, the attitude angles of the capsule robot can be the roll angle, pitch angle, and yaw angle of the capsule robot, which are used to characterize the spatial orientation of the capsule robot.

[0052] For example, motion data of the capsule robot is collected by an inertial measurement unit and then calculated by a filtering algorithm to obtain the current attitude angles of the capsule robot as roll angle 5°, pitch angle 2°, and yaw angle 0°.

[0053] For example, within a target cavity, a capsule robot can acquire acceleration and angular velocity data via an inertial measurement unit (IMU) to calculate roll, pitch, and yaw angles, and obtain the capsule robot's three-dimensional coordinates in real time, forming a current motion state vector. This current motion state vector can be expressed as S(t) = [x,y,z,γ,θ,ψ,v_x,v_y,v_z], for instance, as S(t) = [0.15,0.02,0.03,5°,2°,0°,0.002,0,0], where x, y, and z are the three-dimensional position coordinates, γ is the roll angle, θ is the pitch angle, ψ is the yaw angle, and v_x, v_y, and v_z are the three-dimensional linear velocities.

[0054] The above technical solution uses an inertial measurement unit to collect acceleration and angular velocity data to calculate the attitude angle, and combines it with the three-dimensional information coordinates of the capsule robot's current position to construct a complete motion state vector. This can characterize the capsule robot's real-time spatial motion information in a multi-dimensional and high-precision manner, effectively improving the accuracy of control command calculation and anti-creep capability, and ensuring the capsule robot moves smoothly in complex cavity environments.

[0055] Specifically, the current feedforward control command can be a control command generated based on the predicted deviation between the desired position and the actual position of the capsule robot, used to control the capsule robot to perform advance compensation control force and torque. The feedforward control command can include a vector formed by the combination of three-dimensional control force and three-dimensional control torque to control the movement of the capsule robot, for example...

[0056]

[0057] in, It can be used as the current feedforward control command. These represent the three-dimensional control forces along the x, y, and z axes, respectively. These represent the three-dimensional control torques along the x, y, and z axes, respectively.

[0058] For example, a current feedforward control command can be generated based on the three-dimensional coordinate position of the capsule robot in the current motion state vector and the three-dimensional coordinate position of the capsule robot in the desired position state. The current feedforward control command is a command to control the capsule robot to move from the current position to the desired position state.

[0059] Among them, the current feedback control command can be a command used to control the capsule robot to adjust its three-dimensional coordinate position in real time.

[0060] Furthermore, to enhance real-time error correction capabilities and improve the positioning and tracking accuracy of the capsule robot, in one optional embodiment, a current feedback control command is generated based on the current motion state vector, including:

[0061] Step b1: Based on the current motion state vector, determine the target deviation between the current position state of the capsule robot relative to the target cavity and the desired position state.

[0062] Step b2: Generate the current feedback control command based on the target deviation.

[0063] Here, the current position state can be the vector representing the three-dimensional position coordinates of the capsule robot in the current motion state vector. The target deviation can be the calculated position difference and attitude difference between the current position state and the desired state of the capsule robot.

[0064] For example, the real-time three-dimensional position coordinates (0.15m, 0.02m, 0.03m) and roll angle of 5°, pitch angle of 2°, and yaw angle of 0° are extracted from the current motion state vector. The difference between these coordinates and the desired position coordinates (0.15m, 0.02m, 0.028m) and desired attitude angles of 0°, 0°, and 0° is calculated. The axial position deviation is 0.002m, and the attitude angle deviations are 5°, 2°, and 0°, respectively. This set of position and attitude deviations is the target deviation.

[0065] For example, the position, attitude, and velocity in the current motion state vector are calculated by subtracting them from the desired position and attitude to obtain the target deviation. For instance, if the current position of the capsule robot in the current motion state vector is (0.15, 0.02, 0.03) m, the desired position is (0.15, 0.02, 0.028) m, the current roll angle is 5°, the pitch angle is 2°, the yaw angle is 0°, and the desired attitude angles are all 0°, the calculated position deviation is 0.0002 m, and the attitude angle deviations are 5°, 2°, and 0°, respectively. Based on this deviation, the advance compensation control quantity is solved, and the feedforward control command can be [0.02, 0, 0, 0.001, 0, 0], which is used to control the capsule robot to compensate for the difference between the desired position and attitude.

[0066] The above technical solution calculates the target deviation between the current state and the desired state of the capsule robot in real time, and generates current feedback control commands based on the target deviation. This can quickly correct positioning errors and attitude deviations generated during movement, effectively suppress state fluctuations caused by the peristalsis of the cavity environment, improve the motion stability of the capsule robot, and ensure the accuracy of the capsule robot in performing operations inside the target cavity.

[0067] The target control command can be a command for controlling the movement of the capsule robot generated by fusing the current feedforward control command and the current feedback control command.

[0068] Furthermore, in order to achieve dynamic coordinated control between the current feedforward control command and the current feedback control command, thereby improving control capabilities in complex creeping environments, in one optional embodiment, a target control command is generated based on the current feedforward control command and the current feedback control command, including:

[0069] Step c1: Determine the cavity peristalsis intensity based on the current position of the capsule robot relative to the target cavity.

[0070] Step c2: Determine the weights of the feedforward control command and the feedback control command based on the cavity peristalsis intensity.

[0071] Step c3: Based on the current feedforward control command and the current feedback control command, generate the target control command according to the weights of the feedforward control command and the feedback control command.

[0072] Among them, the cavity peristalsis intensity can be a disturbance intensity level classified according to the amplitude and frequency of intestinal peristalsis, which is collected in real time by the capsule robot.

[0073] For example, the capsule robot can carry a cavity peristalsis intensity monitoring unit to collect and obtain the cavity peristalsis intensity of the capsule robot in real time according to the current position of the capsule robot relative to the target cavity.

[0074] The weights of the feedforward control commands can be the weighting coefficients of the current feedforward vector. The weights of the feedback control commands can be the weighting coefficients of the current feedback vector.

[0075] For example, the weights of the feedforward control command and the feedback control command can be matched according to the intensity of the cavity peristalsis. For instance, if the intensity of the cavity peristalsis is high, the weight of the feedforward control command is 0.6 and the weight of the feedback control command is 0.4.

[0076] For example, if the weight of the feedforward control instruction is 0.6 and the weight of the feedback control instruction is 0.4, the current feedforward control instruction is [0.02,0,0,0.001,0,0] and the current feedback control instruction is [0.01,0,0,0.0005,0,0]. After weighted calculation, the target control instruction is generated as [0.016,0,0,0.0008,0,0].

[0077] The above technical solution determines the peristaltic intensity of the cavity by combining the current position of the capsule robot relative to the target cavity, and adaptively determines the weight of the feedforward control command and the weight of the feedback control command. It can enhance the advance suppression effect of the feedforward when there is strong peristaltic disturbance, and improve the accurate correction effect of the feedback when there is weak disturbance, thus effectively improving the motion stability of the capsule robot in the complex digestive tract environment.

[0078] For example, target control commands can be sent to a capsule robot, which then moves according to the three-dimensional control forces and three-dimensional control torques in the target control commands.

[0079] The technical solution of this invention responds to the operational instructions after the capsule robot enters the target cavity by performing a three-dimensional image scan of the target cavity to obtain the spatial contour information of the target cavity. Based on the spatial contour information of the target cavity, the desired position state of the capsule robot is determined. The current motion parameter data of the capsule robot in the target cavity is acquired, and the current motion state vector of the capsule robot is determined based on the current motion parameter data. Based on the current motion state vector and the desired position state, a current feedforward control instruction is generated. Based on the current motion state vector, a current feedback control instruction is generated. Based on the current feedforward control instruction and the current feedback control instruction, a target control instruction is generated. The target control instruction is sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control instruction. It can collaboratively generate feedforward control instructions and feedback control instructions based on the cavity spatial contour and the real-time motion state vector of the capsule robot, achieving precise control of the capsule robot's motion posture and position state. This effectively solves the problems of control lag, trajectory deviation, and inaccurate target positioning in traditional capsule robots, improving the stability and accuracy of scanning and diagnostic operations inside the target cavity.

[0080] Example 2

[0081] Figure 2 This is a flowchart of a method for stable operation control of a capsule robot inside a cavity, provided in Embodiment 2 of the present invention. This embodiment optimizes and improves upon the above-mentioned technical solutions. The step "generate current feedforward control command based on the current motion state vector and the desired position state" is refined to "obtain historical motion state vectors under historical time periods that satisfy a preset time period, generate a time-series state sequence based on the historical motion state vectors and the current motion state vectors, determine a future state prediction sequence based on the time-series state sequence, and determine the current feedforward control command based on the desired position state according to the future state prediction sequence." This improves the method for generating target control commands.

[0082] It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments. For example... Figure 2 As shown, the method includes the following specific steps:

[0083] S201. In response to the operation command after the capsule robot enters the target cavity, perform a three-dimensional image scan of the target cavity to obtain the spatial contour information of the target cavity, and determine the desired position state of the capsule robot based on the spatial contour information of the target cavity.

[0084] S202. Obtain the current motion parameter data of the capsule robot in the target cavity, and determine the current motion state vector of the capsule robot based on the current motion parameter data.

[0085] S203. Obtain the historical motion state vector under the historical time period that meets the preset time period, generate a time-series state sequence based on the historical motion state vector and the current motion state vector, and determine the future state prediction sequence based on the time-series state sequence.

[0086] S204. Based on the future state prediction sequence and the expected position state, determine the current feedforward control command.

[0087] S205. Generate the current feedback control command based on the current motion state vector.

[0088] S206. Generate the target control command based on the current feedforward control command and the current feedback control command.

[0089] S207. Send the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

[0090] The preset time period can be a time period pre-set by relevant technicians for collecting historical motion state vectors. The historical time period can be multiple consecutive control cycles preceding the current time period. The historical motion state vectors can be historical motion state vectors collected during the historical time period. The time-series state sequence can be a set of historical motion state vectors arranged in chronological order that meet the quantity thresholds pre-set by relevant technicians. The future state prediction sequence can be the motion state prediction results of the capsule robot for multiple future time periods based on the output of the time-series state sequence.

[0091] For example, the preset time period is set to 0.01s (i.e., the control period is 0.01s). The historical time period is selected from the 50 consecutive control periods before the current moment. The corresponding historical motion state vector is collected and stored for each historical time period. These 50 historical motion state vectors and the current motion state vector are arranged in chronological order to form a temporal state sequence Seq(t)=[S(t-49),S(t-48),…,S(t)] that meets the quantity threshold, where S(t) is the current motion state vector, and S(t-49) to S(t-1) are the historical motion state vectors corresponding to each historical time period. The temporal state sequence is input into a pre-trained Long Short-Term Memory (LSTM) network model. The LSTM network model learns and predicts the motion law and cavity peristalsis of the capsule robot, and outputs the prediction results of the capsule robot's motion state for the next 5 time periods, which is the future state prediction sequence.

[0092] In one optional embodiment, the training process of the LSTM model for predicting the motion state of the capsule robot is as follows: Motion state data from different cavity environments are acquired as training samples. Parameter information, including position coordinates, attitude angles, and motion speed, is extracted from each sample. This motion state information is preprocessed, and the preprocessed motion state information is used as sample data. Corresponding labels are generated for the sample data. The sample data and their corresponding labels are input into a pre-set LSTM model. Based on the actual motion state labels of the sample data and the model prediction results, the model loss value is calculated. The network parameters of the LSTM model are iteratively updated based on the loss value until a pre-set model training termination condition is met, resulting in a pre-trained LSTM model for predicting the motion state of the capsule robot. The model training termination condition can be pre-set by relevant technical personnel, such as the loss value reaching a preset threshold or the number of iterations reaching a certain number.

[0093] Furthermore, to achieve advanced prediction of peristaltic disturbances in the capsule robot and improve its control accuracy, in one optional embodiment, the current feedforward control command is determined based on the expected position state according to the future state prediction sequence, including:

[0094] Step d1: Based on the predicted sequence of future states, construct the objective optimization function based on the desired position state.

[0095] Step d2: Determine the feedforward control instruction sequence based on the objective optimization function, and generate the current feedforward control instruction based on the feedforward control instruction sequence.

[0096] The objective optimization function can be a multi-constraint optimization objective that minimizes the deviation between the predicted future state and the desired state while simultaneously constraining the magnitude of the control quantity.

[0097] For example, a Model Predictive Control Optimizer (MPC optimizer) can be used, where relevant technical personnel pre-set the objective optimization function. The objective optimization function can be set to minimize the sum of squared deviations between the future predicted state and the desired position state.

[0098] Among them, the feedforward control instruction sequence can be a sequence of feedforward control instructions for multiple future control cycles output by the model predictive control optimizer based on the objective optimization function.

[0099] For example, a model predictive control optimizer can be used periodically to solve for the objective optimization function to obtain future multi-step feedforward control instructions. Each time, the first step is taken as the current feedforward control instruction. For example, if a sequence of feedforward control instructions for the next five time periods is obtained, the feedforward control instruction corresponding to the first time period can be taken as the current feedforward control instruction.

[0100] The above technical solution constructs a target optimization function based on the future state prediction sequence, uses a model predictive control optimizer to solve the feedforward control command sequence and generate the current feedforward control command, which can suppress the creep disturbance of the target cavity in advance, reduce the tracking deviation of the future state while constraining the amplitude of the control quantity, and effectively improve the control accuracy and operational stability of the capsule robot.

[0101] Furthermore, in order to achieve precise execution and stable output of target control commands, thereby improving the operational reliability and motion stability of the capsule robot, in an optional embodiment, the target control commands are sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control commands, including:

[0102] Step e1: Send the target control command to the magnetic navigation system so that the magnetic navigation system can determine the drive current according to the target control command.

[0103] Step e2: Apply magnetic force and torque to the capsule robot according to the driving current to enable the capsule robot to achieve stable movement.

[0104] The magnetic navigation system can be a system consisting of an external electromagnetic coil array drive and control system for the capsule robot. The drive current can be the drive current value of each electromagnetic coil calculated by the magnetic navigation system of the capsule robot according to the target control command.

[0105] For example, the magnetic navigation system calculates and outputs the driving current of each electromagnetic coil based on the received target control command.

[0106] Among them, the magnetic force can be the three-dimensional control force generated by the driving current of the capsule robot, and the torque can be the magnetic torque generated by the driving current of the capsule robot for attitude adjustment.

[0107] For example, the magnetic navigation system generates a magnetic field by driving an electric current, and outputs corresponding magnetic force and torque to drive the capsule robot to move. For example, the output magnetic force can range from 0 to 0.5 N, and the torque can range from 0 to 5 × 10 N. - ³N・m.

[0108] The above technical solution converts the target control command into the driving current of the magnetic navigation system and uses magnetic force and torque to drive the capsule robot, thereby achieving non-contact stable driving and improving the reliability and safety of the capsule robot's motion control.

[0109] This embodiment's technical solution, through the construction of time-series state sequences, LSTM deep learning for advanced prediction of peristaltic patterns, MPC model predictive control for rolling optimization, feedforward active compensation and feedback real-time correction fusion control, and magnetic navigation for high-precision drive execution, enables stable control of the capsule robot's position, attitude, and speed in the complex and highly disturbed peristaltic environment of the gastrointestinal tract. It effectively solves the problems of traditional capsule robots such as control lag, weak anti-interference ability, and inaccurate positioning, improving the accuracy and safety of clinical operations such as intracavitary scanning, lesion hovering, and precise biopsy.

[0110] Example 3

[0111] Figure 3 This is a flowchart illustrating a method for stable operation control of a capsule robot within a cavity, as provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment provides a preferred example. The method includes:

[0112] S301, responding to the operation start command after the capsule robot enters the target cavity.

[0113] S302. The capsule robot uses its built-in inertial measurement unit to collect raw motion data such as acceleration and angular velocity at a fixed frequency.

[0114] S303. Solve the collected raw motion data to obtain the current position and posture information of the capsule robot, and form the current motion state vector.

[0115] S304. Obtain the historical motion state vectors of the most recent consecutive time steps, and combine the historical motion state vectors with the current motion state vectors in chronological order to construct a time-series state sequence.

[0116] S305. Input the completed time-series state sequence into the pre-trained LSTM model to output the motion state prediction sequence for multiple future time periods.

[0117] S306. Construct the MPC objective optimization function based on the future state prediction sequence and the system's preset desired position state, and generate the current feedforward control command.

[0118] S307. Calculate the target deviation based on the current actual motion state vector of the capsule robot and the desired position state, and generate the current feedback control command based on the target deviation.

[0119] S308. The current feedforward control instruction and the current feedback control instruction are weighted and fused to obtain the final target control instruction used for drive execution.

[0120] S309. The target control command is sent to the external magnetic navigation drive control system, and the magnetic navigation system calculates the drive current corresponding to each electromagnetic coil according to the target control command.

[0121] S310: By driving the current, a magnetic field gradient is generated, forming a magnetic force and torque acting on the capsule robot, controlling the capsule robot to achieve stable movement and posture adjustment.

[0122] The information collected in the above embodiments of the present invention is all information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0123] Example 4

[0124] Figure 4 This is a schematic diagram of a stable operation control device for a capsule robot inside a cavity, provided in Embodiment 4 of the present invention. The stable operation control device for a capsule robot inside a cavity provided in this embodiment of the invention is applicable to cavity internal detection scenarios in the field of cavity diagnostic and therapeutic technology. This stable operation control device for a capsule robot inside a cavity can be implemented in hardware and / or software. It can be applied to a stable operation control method for a capsule robot inside a cavity, and can be specifically configured in a server using a capsule robot for cavity internal detection scenarios. For example... Figure 4 As shown, the device includes: a position state determination module 401, a motion state vector determination module 402, a feedforward control command generation module 403, a feedback control command generation module 404, a target control command generation module 405, and a target control command sending module 406. Wherein:

[0125] The position state determination module 401 is used to respond to the operation command after the capsule robot enters the target cavity, perform three-dimensional image scanning on the target cavity to obtain the spatial contour information of the target cavity, and determine the desired position state of the capsule robot based on the spatial contour information of the target cavity.

[0126] The motion state vector determination module 402 is used to acquire the current motion parameter data of the capsule robot in the target cavity, and determine the current motion state vector of the capsule robot based on the current motion parameter data;

[0127] The feedforward control command generation module 403 is used to generate a current feedforward control command based on the current motion state vector and the desired position state.

[0128] The feedback control command generation module 404 is used to generate a current feedback control command based on the current motion state vector.

[0129] The target control instruction generation module 405 is used to generate a target control instruction based on the current feedforward control instruction and the current feedback control instruction;

[0130] The target control command sending module 406 is used to send the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

[0131] The technical solution of this invention responds to the operational instructions after the capsule robot enters the target cavity by performing a three-dimensional image scan of the target cavity to obtain the spatial contour information of the target cavity. Based on the spatial contour information of the target cavity, the desired position state of the capsule robot is determined. The current motion parameter data of the capsule robot in the target cavity is acquired, and the current motion state vector of the capsule robot is determined based on the current motion parameter data. Based on the current motion state vector and the desired position state, a current feedforward control instruction is generated. Based on the current motion state vector, a current feedback control instruction is generated. Based on the current feedforward control instruction and the current feedback control instruction, a target control instruction is generated. The target control instruction is sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control instruction. It can collaboratively generate feedforward control instructions and feedback control instructions based on the cavity spatial contour and the real-time motion state vector of the capsule robot, achieving precise control of the capsule robot's motion posture and position state. This effectively solves the problems of control lag, trajectory deviation, and inaccurate target positioning in traditional capsule robots, improving the stability and accuracy of scanning and diagnostic operations inside the target cavity.

[0132] Optionally, the feedforward control command generation module 403 includes:

[0133] The future state prediction sequence determination unit is used to obtain historical motion state vectors under historical time periods that satisfy a preset time period, generate a time-series state sequence based on the historical motion state vectors and the current motion state vectors, and determine a future state prediction sequence based on the time-series state sequence.

[0134] The feedforward control command determination unit is used to determine the current feedforward control command based on the expected position state and the future state prediction sequence.

[0135] Optionally, the feedforward control command determination unit is specifically used for:

[0136] Based on the predicted future state sequence, and the desired position state, a target optimization function is constructed.

[0137] The feedforward control instruction sequence is determined based on the objective optimization function, and the current feedforward control instruction is generated based on the feedforward control instruction sequence.

[0138] Optionally, the feedback control instruction generation module 404 is specifically used for:

[0139] Based on the current motion state vector, determine the target deviation between the current position state of the capsule robot relative to the target cavity and the desired position state;

[0140] The current feedback control command is generated based on the target deviation.

[0141] Optionally, the target control instruction generation module 405 is specifically used for:

[0142] The cavity peristalsis intensity is determined based on the current position of the capsule robot relative to the target cavity;

[0143] The weights of the feedforward control command and the feedback control command are determined based on the cavity peristalsis intensity.

[0144] Based on the current feedforward control command and the current feedback control command, a target control command is generated according to the weights of the feedforward control command and the feedback control command.

[0145] Optionally, the motion state vector determination module 402 is specifically used for:

[0146] The triaxial linear acceleration and triaxial angular velocity of the capsule robot are obtained through the inertial measurement unit of the capsule robot;

[0147] The attitude angle of the capsule robot is determined based on the three-axis linear acceleration and three-axis angular velocity.

[0148] The current motion state vector is determined based on the current position and attitude angle of the capsule robot relative to the target cavity.

[0149] Optionally, the target control command sending module 406 is specifically used for:

[0150] The target control command is sent to the magnetic navigation system so that the magnetic navigation system can determine the drive current according to the target control command;

[0151] The capsule robot is subjected to magnetic force and torque according to the driving current so that the capsule robot can achieve stable movement.

[0152] The stable operation control device for a capsule robot inside a cavity provided in this embodiment of the invention can execute a stable operation control method for a capsule robot inside a cavity provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0153] Example 5

[0154] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0155] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded from storage unit 58 into the RAM 53. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0156] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0157] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as the stable operation control method for a capsule robot inside a cavity.

[0158] In some embodiments, the method for stable operation control of a capsule robot within a cavity can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the method for stable operation control of a capsule robot within a cavity described above can be performed. Alternatively, in other embodiments, processor 51 can be configured for the method for stable operation control of a capsule robot within a cavity by any other suitable means (e.g., by means of firmware).

[0159] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0161] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0163] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0164] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0165] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0166] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for stable operation control of a capsule robot inside a cavity, characterized in that, include: In response to the operation command after the capsule robot enters the target cavity, a three-dimensional image scan of the target cavity is performed to obtain the spatial contour information of the target cavity, and the desired position state of the capsule robot is determined based on the spatial contour information of the target cavity. The current motion parameter data of the capsule robot in the target cavity is obtained, and the current motion state vector of the capsule robot is determined based on the current motion parameter data; Based on the current motion state vector and the desired position state, generate the current feedforward control command. Based on the current motion state vector, generate the current feedback control command; Generate a target control command based on the current feedforward control command and the current feedback control command; The target control command is sent to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

2. The method according to claim 1, characterized in that, Based on the current motion state vector and the desired position state, a current feedforward control command is generated, including: Obtain historical motion state vectors under historical time periods that satisfy a preset time period, generate a time-series state sequence based on the historical motion state vectors and the current motion state vectors, and determine a future state prediction sequence based on the time-series state sequence. Based on the predicted future state sequence, the current feedforward control command is determined according to the expected position state.

3. The method according to claim 2, characterized in that, The step of determining the current feedforward control command based on the expected position state according to the predicted future state sequence includes: Based on the predicted future state sequence, and the desired position state, a target optimization function is constructed. The feedforward control instruction sequence is determined based on the objective optimization function, and the current feedforward control instruction is generated based on the feedforward control instruction sequence.

4. The method according to claim 1, characterized in that, The step of generating the current feedback control command based on the current motion state vector includes: Based on the current motion state vector, determine the target deviation between the current position state of the capsule robot relative to the target cavity and the desired position state; The current feedback control command is generated based on the target deviation.

5. The method according to claim 1, characterized in that, The step of generating a target control command based on the current feedforward control command and the current feedback control command includes: The cavity peristalsis intensity is determined based on the current position of the capsule robot relative to the target cavity; The weights of the feedforward control command and the feedback control command are determined based on the cavity peristalsis intensity. Based on the current feedforward control command and the current feedback control command, a target control command is generated according to the weights of the feedforward control command and the feedback control command.

6. The method according to claim 1, characterized in that, The step of acquiring the current motion parameter data of the capsule robot in the target cavity and determining the current motion state vector of the capsule robot based on the current motion parameter data includes: The triaxial linear acceleration and triaxial angular velocity of the capsule robot are obtained through the inertial measurement unit of the capsule robot; The attitude angle of the capsule robot is determined based on the three-axis linear acceleration and three-axis angular velocity. The current motion state vector is determined based on the current position and attitude angle of the capsule robot relative to the target cavity.

7. The method according to claim 1, characterized in that, Sending the target control command to the capsule robot, so that the capsule robot can operate stably inside the target cavity based on the target control command, includes: The target control command is sent to the magnetic navigation system so that the magnetic navigation system can determine the drive current according to the target control command; The capsule robot is subjected to magnetic force and torque according to the driving current so that the capsule robot can achieve stable movement.

8. A stable operation control device for a capsule robot inside a cavity, characterized in that, include: The position state determination module is used to respond to the operation command after the capsule robot enters the target cavity, perform three-dimensional image scanning of the target cavity to obtain the spatial contour information of the target cavity, and determine the desired position state of the capsule robot based on the spatial contour information of the target cavity. The motion state vector determination module is used to acquire the current motion parameter data of the capsule robot in the target cavity, and determine the current motion state vector of the capsule robot based on the current motion parameter data; The feedforward control command generation module is used to generate the current feedforward control command based on the current motion state vector and the desired position state. The feedback control command generation module is used to generate the current feedback control command based on the current motion state vector. The target control instruction generation module is used to generate target control instructions based on the current feedforward control instructions and the current feedback control instructions; The target control command sending module is used to send the target control command to the capsule robot so that the capsule robot can operate stably inside the target cavity based on the target control command.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the stable operation control method for the capsule robot inside the cavity as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the stable operation control method for the capsule robot inside the cavity as described in any one of claims 1-7.

Images