An active capsule robot system and control method thereof

Abstract

The embodiments of this specification provide an active capsule robot control method, which collects the physical state of a sample user, a temporary physical management strategy, and the drift data of the cavity peristaltic characteristics after the implementation of the temporary physical management strategy. The drift data of the cavity peristaltic characteristics is used as a training label, and the physical state of the sample user and the temporary physical management strategy are input into a sample training peristaltic characteristic drift prediction model to obtain the physical state and temporary physical management strategy of the current case. The drift data of the cavity peristaltic characteristics of the current case is predicted using the model, and the cavity image collected by the capsule robot is three-dimensionally reconstructed to obtain the three-dimensional shape of the cavity. The drift data of the cavity peristaltic characteristics is used to evolve the three-dimensional shape of the cavity to obtain the dynamic change time sequence of the three-dimensional shape of the cavity in the future, and the dynamic change time sequence of the target position is calculated. Based on the result, an action strategy is generated to control the motion state of the capsule robot, thereby improving the accuracy and efficiency of controlling the movement of the capsule robot.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to an active capsule robot system and a control method thereof. Background Art

[0002] A capsule robot is an intelligent miniature tool that can enter the human gastrointestinal tract for medical exploration and treatment. It is a new breakthrough in in vivo interventional examination and treatment medical technology.

[0003] Capsule robots are categorized as either passive or active, depending on their movement. They can move to a target point for image acquisition, treatment, and medication administration. Current approaches to using capsule robots for treatment rely on planning a movement route based on the target's location and controlling the robot's movement within a cavity. However, cavities are often not static and often experience peristaltic motion. This peristaltic motion can cause the target's position to dynamically change, resulting in lower accuracy and efficiency in previously planned routes. Therefore, a new method is needed to improve the accuracy and efficiency of controlling the movement of capsule robots. Summary of the Invention

[0004] The embodiments of this specification provide an active capsule robot control method and system to improve the accuracy and efficiency of controlling the movement of the capsule robot.

[0005] The embodiments of this specification provide an active capsule robot control method, including:

[0006] Collecting the sample user's physical condition information, temporary physical management strategy information, and drift data of the cavity peristaltic characteristics after implementing the temporary physical management strategy; using the drift data of the cavity peristaltic characteristics as training labels; and using the sample user's physical condition information and temporary physical management strategy information as input samples to train a peristaltic characteristic drift prediction model; obtaining the physical condition information and temporary physical management strategy information of the current case; and using the peristaltic characteristic drift prediction model to predict the drift data of the cavity peristaltic characteristics of the current case;

[0007] Performing three-dimensional reconstruction on the cavity images collected by the capsule robot to obtain the three-dimensional shape of the cavity, and using the drift data of the peristaltic characteristics of the cavity to evolve the three-dimensional shape of the cavity to obtain the dynamic change time series of the three-dimensional shape of the cavity in the future;

[0008] The target position dynamic change sequence is calculated according to the predicted future dynamic change sequence of the three-dimensional shape of the cavity, and an action strategy is generated according to the dynamic change sequence of the target position to control the motion state of the capsule robot.

[0009] The embodiments of this specification also provide an active capsule robot control system, including:

[0010] a big data prediction module that collects sample users' physical condition information, temporary physical management strategy information, and drift data of cavity peristaltic characteristics after implementation of the temporary physical management strategy, uses the drift data of cavity peristaltic characteristics as training labels, and uses the sample users' physical condition information and temporary physical management strategy information as input samples to train a peristaltic characteristic drift prediction model, obtains the physical condition information and temporary physical management strategy information of the current case, and uses the peristaltic characteristic drift prediction model to predict the drift data of the cavity peristaltic characteristics of the current case;

[0011] The morphology evolution module performs three-dimensional reconstruction on the cavity images collected by the capsule robot to obtain the three-dimensional morphology of the cavity. The module uses the drift data of the peristaltic characteristics of the cavity to evolve the three-dimensional morphology of the cavity to obtain the dynamic change time series of the three-dimensional morphology of the cavity in the future.

[0012] The control strategy module calculates the dynamic change sequence of the target position according to the predicted dynamic change sequence of the three-dimensional shape of the cavity in the future, generates an action strategy according to the dynamic change sequence of the target position, and controls the motion state of the capsule robot.

[0013] An embodiment of this specification further provides an electronic device, wherein the electronic device includes:

[0014] processor; and,

[0015] A memory storing a computer executable program, wherein when the executable program is executed, the processor is caused to perform any one of the above methods.

[0016] An embodiment of this specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0017] The various technical solutions provided in the embodiments of this specification collect the physical state of the sample user, the temporary physical management strategy, and the drift data of the cavity peristaltic characteristics after the implementation of the temporary physical management strategy, use the drift data of the cavity peristaltic characteristics as training labels, and use the physical state of the sample user and the temporary physical management strategy as input to the sample training peristaltic characteristic drift prediction model to obtain the physical state and temporary physical management strategy of the current case, use the model to predict the drift data of the cavity peristaltic characteristics of the current case, perform three-dimensional reconstruction on the cavity image collected by the capsule robot to obtain the three-dimensional shape of the cavity, use the drift data of the cavity peristaltic characteristics to evolve the three-dimensional shape of the cavity, obtain the dynamic change time series of the three-dimensional shape of the cavity in the future, calculate the dynamic change time series of the target position, generate an action strategy based on it, control the motion state of the capsule robot, and improve the accuracy and efficiency of controlling the movement of the capsule robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A schematic diagram of the principle of an active capsule robot control method provided in an embodiment of this specification;

[0020] Figure 2 A schematic structural diagram of an active capsule robot control system provided in an embodiment of this specification;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0022] Figure 4 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of this specification. DETAILED DESCRIPTION

[0023] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, making it easier to fully convey the inventive concept to those skilled in the art. In the figures, the same reference numerals represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0024] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0025] In the description of specific embodiments, the features, structures, characteristics, or other details of the present invention are described to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from practicing the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0026] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0028] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0029] Figure 1 A schematic diagram of the principle of an active capsule robot control method provided in an embodiment of this specification may include:

[0030] S101: collecting physical condition information, temporary physical management strategy information, and drift data of cavity peristaltic characteristics after implementing the temporary physical management strategy of a sample user; using the drift data of the cavity peristaltic characteristics as training labels; and using the physical condition information and temporary physical management strategy information of the sample user as input samples to train a peristaltic characteristic drift prediction model; obtaining the physical condition information and temporary physical management strategy information of a current case; and using the peristaltic characteristic drift prediction model to predict the drift data of the cavity peristaltic characteristics of the current case;

[0031] S102: Performing three-dimensional reconstruction on the cavity image collected by the capsule robot to obtain the three-dimensional shape of the cavity, and evolving the three-dimensional shape of the cavity using the drift data of the peristaltic characteristics of the cavity to obtain a time sequence of dynamic changes of the three-dimensional shape of the cavity in the future;

[0032] S103: Calculate the target position dynamic change sequence based on the predicted future dynamic change sequence of the three-dimensional shape of the cavity, generate an action strategy based on the target position dynamic change sequence, and control the motion state of the capsule robot.

[0033] This embodiment collects the physical state of the sample user, the temporary physical management strategy, and the drift data of the cavity peristaltic characteristics after the implementation of the temporary physical management strategy, uses the drift data of the cavity peristaltic characteristics as training labels, and uses the physical state of the sample user and the temporary physical management strategy as input to a sample training peristaltic characteristic drift prediction model to obtain the physical state and temporary physical management strategy of the current case, uses the model to predict the drift data of the cavity peristaltic characteristics of the current case, performs three-dimensional reconstruction on the cavity image collected by the capsule robot to obtain the three-dimensional shape of the cavity, uses the drift data of the cavity peristaltic characteristics to evolve the three-dimensional shape of the cavity to obtain the dynamic change time series of the three-dimensional shape of the cavity in the future, calculates the dynamic change time series of the target position, generates an action strategy based on it, controls the motion state of the capsule robot, and improves the accuracy and efficiency of controlling the movement of the capsule robot.

[0034] In the embodiment of the present specification, the body state information includes: heartbeat waveform, pulse waveform, food digestion and absorption rate and digestion time, and the temporary body management strategy information includes: food intake within the preset period before treatment and the interval from the current time, exercise amount and the interval from the current time, and excretion amount and the interval from the current time.

[0035] Since the shape of the cavity changes, the position of the treatment target is actually also changing. If the dynamic position of the target can be taken into account when planning the movement path of the capsule robot, the control accuracy of the capsule robot can be improved.

[0036] Among them, existing technologies for three-dimensional reconstruction based on collected images have been applied. The finite element method can be used for three-dimensional reconstruction, which will not be elaborated here.

[0037] Wherein, the cavity is a peristaltic cavity.

[0038] In the embodiments of this specification, the peristaltic characteristics of the cavity include: the frequency, amplitude and duration of the peristalsis.

[0039] The drift data may be the change in the cavity peristaltic characteristics over time.

[0040] Since different body state information and temporary body management strategies will affect the peristaltic characteristics of the cavity during the treatment stage, the drift data of the cavity peristaltic characteristics is predicted by using the body state information and temporary body management strategies to improve the prediction ability of the dynamic peristaltic state of the cavity, thereby improving the accuracy.

[0041] In the embodiment of this specification, the evolving the three-dimensional shape of the cavity using the drift data of the cavity peristaltic characteristics includes:

[0042] A peristaltic simulation model is established using physical field software, and the three-dimensional shape of the cavity is imported. The drift data of the peristaltic characteristics of the cavity are configured for it, the peristaltic characteristics of the cavity after drift are calculated, and the three-dimensional shape of the cavity at each time point of peristalsis according to the peristaltic characteristics of the cavity after drift is simulated.

[0043] In the embodiment of this specification, the three-dimensional form of the cavity includes: shape and tilt angle.

[0044] The dynamic position of the target requires the capsule robot to not only move to the target's location, but also synchronize its arrival time with the target's dynamic characteristics. Therefore, this involves not only calculating the position but also the dimension of time, which can be solved by iterating according to time periods.

[0045] In the embodiment of this specification, the action strategy is generated according to the timing of the dynamic change of the target position, including:

[0046] Taking the relative position from the target to the capsule robot as the observation value, a dynamic environment space is constructed according to the dynamic change time sequence of the capsule robot's current position and the target position. An action space is constructed according to the capsule robot's moving direction, moving step length, and moving speed. Multiple particle swarms are created in the action space, and a reward function with the inverse of time and the inverse of distance as independent variables is constructed. The action strategy at each particle coordinate is determined, and the observation value after applying the action strategy to the environment space is calculated. The iteration is continued until the observation value is 0. Different particles are used as different iterative routes, and the sum of the reward values ​​is calculated for each iterative route. Multiple action strategies under the iterative route with the largest sum of reward values ​​are screened.

[0047] By screening multiple action strategies under the iterative route with the largest sum of reward values, the optimal movement path can be obtained. In the embodiment of this specification, the cavity is a peristaltic cavity.

[0048] An observation value of 0 indicates that the capsule robot has reached the target.

[0049] By constructing a dynamic environmental space, the reality that the cavity has rhythmic topographical deformation is taken into account.

[0050] The capsule robot's moving direction, moving step length, and moving speed reflect the control target of the capsule robot, so they are used to construct the action space.

[0051] By creating multiple particle swarms and taking each particle as a search iterative path, the optimal iterative path can be screened.

[0052] A reward function with the inverse of time and the inverse of distance as independent variables is constructed to facilitate screening out the movement path with the shortest movement time and distance, thereby improving treatment efficiency.

[0053] Constructing a reward function with the inverse of time and the inverse of distance as independent variables can be to simulate the movement process of the capsule robot in real time according to the action strategy and calculate its relative position with the target in real time.

[0054] The simulation process can take into account initial velocity, posture, movement direction, and step length. Formulas can be developed based on Newton's second law of motion, and resistance parameters can be set based on the viscosity of the fluid within the cavity to improve simulation realism and accuracy. The specific calculation formulas for simulating object motion can be set based on experience and are well documented in existing technologies, so we will not elaborate on them here.

[0055] In the embodiments of this specification, it also includes:

[0056] Obstacle avoidance is performed based on the future dynamic changes in the three-dimensional shape of the cavity.

[0057] In the embodiments of this specification, the obstacle avoidance according to the future dynamic change sequence of the cavity's three-dimensional shape includes:

[0058] Based on the displacement of multiple action strategies, it is determined whether the only process passes through the three-dimensional wall of the cavity. If so, the multiple action strategies under the next iterative route are screened in descending order according to the sum of the reward values ​​until their displacement does not pass through the three-dimensional wall of the cavity.

[0059] In this embodiment of the present specification, the method further includes:

[0060] Marking the capsule robot, developing the capsule robot after it enters the workspace to obtain a developed image, performing target recognition on the developed image to identify projection features of the mark, and calculating the development posture of the capsule robot based on the projection features of the mark;

[0061] Constructing a reinforcement learning model, using the reinforcement learning model to plan and generate magnetic control instructions, combining the development posture simulation to predict the position and posture of the capsule robot at the next moment after the magnetic control instruction is implemented, and determining whether the simulated predicted position and posture at the next moment are on a preset movement path. If so, implementing the magnetic control instruction, and, after implementation, continuing to develop the capsule robot, calculating the development posture of the capsule robot, using the development posture for the next iteration, and correcting the reinforcement learning model according to the deviation between the developed posture and the simulation prediction result;

[0062] The magnetic control command is implemented by a magnetic control system, wherein the magnetic control system has a magnetic field sensor array.

[0063] The method may further include: recording the positions of the marks and the relative positions between the marks.

[0064] The method may further include: determining a development time and executing a development instruction.

[0065] The target refers to the geometric shape features and color features of the mark (noun state).

[0066] In the embodiments of this specification, the construction of the reinforcement learning model includes:

[0067] The capsule robot's appearance information, the position information of the capsule robot's mass center of gravity, the position information of the internal permanent magnet, the spatial attribute information of the magnetic field sensor array in the magnetic control system, and the capsule robot's position and posture information at historical moments are collected from the database. These historical state information are input into the reinforcement learning model to be trained to obtain magnetic control decision information.

[0068] Inputting the historical state information and the magnetic control decision information into a pre-established posture and reward value prediction model to obtain reward value information and evolved state information, wherein the evolved state information includes evolved posture information;

[0069] The posture change amount is calculated, and the reinforcement learning model to be trained is updated according to each historical state information, the corresponding magnetic control decision information, the posture change amount and the reward value information, and the training is completed through multiple iterative updates.

[0070] By collecting the appearance information of the capsule robot, the position information of the capsule robot's mass center of gravity, and the position information of the internal permanent magnet, the influence of the uneven material distribution and the internal space material of the capsule robot are taken into account.

[0071] The appearance information of the capsule robot is the external shape of the capsule robot, which affects the motion state of the capsule robot. The appearance of each capsule robot can be three-dimensionally modeled to obtain the appearance information.

[0072] The position information of the mass center of gravity of the capsule robot can be obtained through actual measurement. By hanging the capsule robot at three different angles, the position coordinates of the intersection of the three perpendicular lines in the capsule robot are calculated, which is the mass center of gravity.

[0073] The position information of the internal permanent magnet can be obtained through design information or actual measurement.

[0074] The spatial attribute information of the magnetic field sensor array in the magnetic control system may refer to the length, width, sensor density and distance from the lesion of the magnetic field sensor array.

[0075] The position and posture information of the capsule robot at a historical moment can be obtained by multiple developments in historical treatment events.

[0076] The training is achieved by updating the reinforcement learning model to be trained so that the model has the decision-making ability to meet the reward requirements.

[0077] In the embodiment of this specification, the step of calculating the development posture of the capsule robot according to the projection features of the marker includes:

[0078] The length of the long side, the length of the short side, and the direction of the projected ellipse are determined, the inclination value is calculated according to the ratio of the short side to the long side as the cosine value of the inclination angle, the direction of the short side is used as the direction of the inclination angle, and the inclination value and direction of the inclination angle are used to record the development posture of the recording capsule robot.

[0079] The circular mark is projected into an ellipse after tilting. The short side of the ellipse is the tilt direction, and the short side / long side is the cosine value of the tilt angle. The tilt angle can be calculated based on this principle.

[0080] The selection of one of the first, second and third marks may be the selection of the one with the largest projection area, which can improve the calculation accuracy.

[0081] The long side is denoted as L1 and the short side is denoted as L2, then the inclination angle is arccos(L2 / L1), and the direction of the inclination angle is the direction of the short side.

[0082] The imaging posture of the capsule robot can be recorded as: (circular mark name, inclination degree away from the projection surface, pointing degree within the projection surface).

[0083] For example (circular marker name 1, 45 degrees inward away from the projection plane, 175 degrees in the projection plane).

[0084] Since development requires the mobilization of hardware devices, while iteration only requires software operations, in order to reduce the frequency of device calls, the development device can be called intermittently and development can be performed intermittently.

[0085] In the embodiment of this specification, continuing to develop the capsule robot, calculating the development posture of the capsule robot, and using the development posture for the next iteration includes:

[0086] The current iteration frequency is determined. If the iteration frequency reaches a multiple of a preset value, the capsule robot is developed, the development posture of the capsule robot is calculated, and the development posture and the position calculated in the previous iteration are used to perform the next iteration. If the iteration frequency does not reach a multiple of the preset value, the position and posture information calculated in the previous iteration are used for the next iteration.

[0087] In one application scenario, at the 5th, 10th, 15th... iterations, development is performed and the developed posture is used to iteratively calculate the position and posture at the next moment. For other iterations, only the posture calculated in the previous iteration is needed to calculate the position and posture at the next moment. Since the number of iterative uses of the posture is limited, the cumulative error is limited, the accuracy is improved, and the frequency of hardware adjustment is reduced.

[0088] In order to improve the magnetic control effect, reinforcement learning can be used to make decisions.

[0089] In the embodiment of this specification, the posture and reward value prediction model is a deep neural network model architecture.

[0090] The training process of the posture and reward value prediction model can be to construct training samples using the posture information of the previous moment and the implemented magnetic control decision, collect the posture of the next moment, calculate the reward value according to the implementation result of the magnetic control decision, set the training label with the reward value and the posture of the next moment, and train the deep neural network model architecture in a supervised learning manner to obtain the posture and reward value prediction model, which is used to predict the posture and reward value of the next moment for the existing iterative position, development posture and decided magnetic control strategy.

[0091] The reward value is calculated according to the result of the magnetic control decision implementation, which may be a reward function constructed with the inverse of time and the inverse of distance as independent variables to calculate the reward value.

[0092] The attitude change amount may be the direction and value of the tilt angle change.

[0093] The movement path of the capsule robot affects the treatment efficiency. Therefore, in order to improve the scientific nature of movement path planning, intracavitary images can be collected and used as a basis to plan the movement path and continuously adjust and optimize the movement path.

[0094] In the embodiment of this specification, the working space is the intersection of the working spaces of the magnetron system and the developing system.

[0095] In an embodiment of the present specification, it is characterized in that the reinforcement learning model to be trained has an action probability distribution function to be trained, and the probability distribution state of the action is adjusted through training.

[0096] The historical state information is input into the reinforcement learning model to be trained, and the magnetic control decision information is obtained according to its probability distribution state.

[0097] The specific probability distribution function refers to the functional relationship between the occurrence probability of an action and an action. The action refers to the magnetic control decision, which will not be elaborated here and can be set based on experience.

[0098] Figure 2 This is a schematic diagram of the structure of an active capsule robot control system provided in an embodiment of this specification. The system may include:

[0099] The big data prediction module 201 collects the sample user's physical condition information, temporary physical management strategy information, and the drift data of the cavity peristaltic characteristics after the implementation of the temporary physical management strategy, uses the drift data of the cavity peristaltic characteristics as training labels, and uses the sample user's physical condition information and temporary physical management strategy information as input samples to train a peristaltic characteristic drift prediction model, obtains the physical condition information and temporary physical management strategy information of the current case, and uses the peristaltic characteristic drift prediction model to predict the drift data of the cavity peristaltic characteristics of the current case;

[0100] The morphology evolution module 202 performs three-dimensional reconstruction on the cavity images collected by the capsule robot to obtain the three-dimensional morphology of the cavity, and evolves the three-dimensional morphology of the cavity using the drift data of the peristaltic characteristics of the cavity to obtain a time series of dynamic changes of the three-dimensional morphology of the cavity in the future;

[0101] The control strategy module 203 calculates the target position dynamic change sequence according to the predicted future dynamic change sequence of the cavity three-dimensional shape, generates an action strategy according to the target position dynamic change sequence, and controls the motion state of the capsule robot.

[0102] It should be noted that the above-mentioned method embodiment can be integrated into the system, for example, constructing a development processing module to execute the above-mentioned development control and development posture calculation related steps, and the big data prediction module 201 can be used to execute the model-related steps in the above-mentioned method embodiment.

[0103] The system collects the physical status, temporary body management strategies and drift data of cavity peristaltic characteristics after the implementation of temporary body management strategies of sample users, uses the drift data of cavity peristaltic characteristics as training labels, and inputs the physical status and temporary body management strategies of sample users into a sample training peristaltic characteristic drift prediction model to obtain the physical status and temporary body management strategies of the current case. The model is used to predict the drift data of the cavity peristaltic characteristics of the current case, and the cavity images collected by the capsule robot are reconstructed in three dimensions to obtain the three-dimensional shape of the cavity. The drift data of the cavity peristaltic characteristics is used to evolve the three-dimensional shape of the cavity to obtain the dynamic change time series of the three-dimensional shape of the cavity in the future, and the dynamic change time series of the target position is calculated. Based on this, an action strategy is generated to control the motion state of the capsule robot, thereby improving the accuracy and efficiency of controlling the movement of the capsule robot.

[0104] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0105] The following describes an electronic device embodiment of the present invention, which can be considered a specific physical implementation of the method and apparatus embodiments of the present invention described above. Details described in the electronic device embodiment of the present invention should be considered supplementary to the above-mentioned method or apparatus embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above-mentioned method or apparatus embodiments.

[0106] Figure 3 This is a schematic diagram of the structure of an electronic device provided in the embodiment of this specification. Figure 3 The electronic device 300 according to this embodiment of the present invention will be described. Figure 3 The electronic device 300 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0107] like Figure 3 As shown, electronic device 300 is implemented as a general-purpose computing device. Components of electronic device 300 may include, but are not limited to, at least one processing unit 310, at least one storage unit 320, a bus 330 connecting various system components (including storage unit 320 and processing unit 310), a display unit 340, and the like.

[0108] The storage unit stores program codes that can be executed by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 310 can perform the following steps: Figure 1 Steps shown.

[0109] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache memory unit 3202 , and may further include a read-only memory unit (ROM) 3203 .

[0110] The storage unit 320 may also include a program / utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0111] Bus 330 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0112] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 3Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0113] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium is enabled to implement the above method of the present invention, that is: Figure 1 The method shown.

[0114] Figure 4 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of this specification.

[0115] accomplish Figure 1 The computer program of the method shown can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0116] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0117] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0118] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that general data processing equipment such as a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0119] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

[0120] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0121] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An active capsule robot control system, characterized in that: include: a big data prediction module that collects sample users' physical condition information, temporary physical management strategy information, and drift data of cavity peristaltic characteristics after implementation of the temporary physical management strategy, uses the drift data of cavity peristaltic characteristics as training labels, and uses the sample users' physical condition information and temporary physical management strategy information as input samples to train a peristaltic characteristic drift prediction model, obtains the physical condition information and temporary physical management strategy information of the current case, and uses the peristaltic characteristic drift prediction model to predict the drift data of the cavity peristaltic characteristics of the current case; The body status information includes: heartbeat waveform, pulse waveform, food digestion and absorption rate and digestion time; the temporary body management strategy information includes: food intake and the interval from the current time, exercise amount and the interval from the current time, and excretion amount and the interval from the current time in the preset time period before treatment; The morphology evolution module performs three-dimensional reconstruction on the cavity images collected by the capsule robot to obtain the three-dimensional morphology of the cavity. The module uses the drift data of the peristaltic characteristics of the cavity to evolve the three-dimensional morphology of the cavity to obtain the dynamic change time series of the three-dimensional morphology of the cavity in the future. A control strategy module calculates the target position dynamic change sequence based on the predicted future dynamic change sequence of the cavity's three-dimensional shape, generates an action strategy based on the target position dynamic change sequence, and controls the motion state of the capsule robot; The action strategy is generated according to the timing of the dynamic change of the target position, including: Taking the relative position from the target to the capsule robot as the observation value, a dynamic environment space is constructed according to the dynamic change time sequence of the capsule robot's current position and the target position. An action space is constructed according to the capsule robot's moving direction, moving step length, and moving speed. Multiple particle swarms are created in the action space, and a reward function with the inverse of time and the inverse of distance as independent variables is constructed. The action strategy at each particle coordinate is determined, and the observation value after applying the action strategy to the environment space is calculated. The iteration is continued until the observation value is 0. Different particles are used as different iterative routes, and the sum of the reward values ​​is calculated for each iterative route. Multiple action strategies under the iterative route with the largest sum of reward values ​​are screened.

2. The active capsule robot control system according to claim 1, characterized in that: The evolving the three-dimensional shape of the cavity by utilizing the drift data of the cavity creep characteristics includes: A peristaltic simulation model is established using physical field software, and the three-dimensional shape of the cavity is imported. The drift data of the peristaltic characteristics of the cavity are configured for it, the peristaltic characteristics of the cavity after drift are calculated, and the three-dimensional shape of the cavity at each time point of peristalsis according to the peristaltic characteristics of the cavity after drift is simulated.

3. The active capsule robot control system according to claim 1, characterized in that: The cavity peristaltic characteristics include: peristaltic frequency, amplitude and peristaltic duration.

4. The active capsule robot control system according to claim 1, characterized in that: The three-dimensional form of the cavity includes: shape and tilt angle.

5. The active capsule robot control system according to claim 4, characterized in that: Also includes: Obstacle avoidance is performed based on the future dynamic changes in the three-dimensional shape of the cavity.

6. The active capsule robot control system according to claim 5, characterized in that: The obstacle avoidance according to the future dynamic change sequence of the cavity's three-dimensional shape includes: Based on the displacement of multiple action strategies, it is determined whether the only process passes through the three-dimensional wall of the cavity. If so, the multiple action strategies under the next iterative route are screened in descending order according to the sum of the reward values ​​until their displacement does not pass through the three-dimensional wall of the cavity.

Images