Micro-detonation surgical robot out-of-control braking system and method based on energy step

Abstract

The invention discloses an out-of-control braking system and method for a micro-detonation surgical robot based on energy step. The system comprises a multi-modal data acquisition module, a risk monitoring and braking control module and a micro-detonation physical braking module. The multi-modal data acquisition module comprises a hardware state data acquisition module, a motion state data acquisition module, a physiological state data acquisition module and a data storage-fusion-transmission chip; the risk monitoring and braking control module comprises a communication module, a data fusion module and a control circuit; the braking method comprises the steps that robot mechanical arm current, output shaft torque, magnetic field intensity, translation speed, acceleration component, point cloud density, depth, and patient blood oxygen saturation, heart rate variability and blood pressure variability are collected; and risk levels are divided according to the comprehensive risk quantized value, the hardware risk quantized value, the exercise risk quantized value and the physiological risk quantized value for braking. According to the invention, out-of-control risk monitoring, graded response and hardware-level physical damage brake control of the robot are realized.

Description

Technical Field

[0001] This invention relates to the field of safety control technology for intelligent surgical robots, and in particular to a micro-detonation-based braking system and method for surgical robots to address the risk of runaway. Background Technology

[0002] Intelligent surgical robots have played a significant role in improving surgical precision, reducing trauma, and enabling telemedicine. However, their system complexity also introduces potential risks of loss of control. Loss of control typically refers to a robot deviating from preset commands and performing unexpected actions due to hardware malfunctions (such as motor overload or sensor failure), software anomalies (algorithm crashes or network attacks), or external interference (electromagnetic pulses or tissue adhesions). Examples include high-speed tremors of the robotic arm, continuous pressure from the end effector, or accidental severing of blood vessels. Such loss of control can lead to catastrophic consequences: in cardiac interventional surgery, catheter malfunction can cause vascular perforation and massive hemorrhage; in deep brain stimulation, millimeter-level electrode misalignment can damage critical neural nuclei, causing permanent functional impairment or even death. Therefore, the loss-of-control perception module and emergency braking mechanism of intelligent surgical robots must terminate dangerous actions within an extremely short time window, serving as the last line of defense for patient safety.

[0003] Current braking technology for intelligent surgical robots faces multiple bottlenecks, primarily manifested in insufficient multi-dimensional perception capabilities and untimely braking mechanism responses. Current intelligent surgical robots rely heavily on single sensors (such as current or angle) for anomaly detection, lacking deep integration of visual data, physiological signals (ECG, intracranial pressure), and environmental parameters (electromagnetic field strength, temperature, and humidity), leading to misjudgments or missed detections. For example, the da Vinci Si system only judges anomalies based on force feedback thresholds, failing to identify instrument displacement risks caused by visual occlusion. Secondly, risk monitoring models are rudimentary, with mainstream solutions employing a "safe / dangerous" binary classification without establishing a refined grading system, resulting in false triggering of low-risk scenarios or missed detection of high-risk scenarios. More seriously, traditional braking relies on software shutdown or mechanical brakes, with an average response time exceeding 200ms, far exceeding the latency limits of delicate surgery. Furthermore, the residual kinetic energy of the surgical robot's arm after emergency braking often remains at a high level, potentially causing further injury to the patient.

[0004] As surgical robots evolve towards higher complexity (vascular intervention, single-port endoscopy) and higher autonomy (AI decision-making), the risk of loss of control exhibits multi-factor coupling and nonlinear burst characteristics. The industry's demand for innovative braking technology is imminent. Therefore, it is urgent to develop a braking system method that integrates multimodal data and supports hardware self-destruction and dynamic disaster recovery to achieve accurate perception, hierarchical decision-making, and rapid braking response in the case of loss of control of surgical robots, so as to meet the safety and reliability requirements of intelligent surgical robots. Summary of the Invention

[0005] Purpose of the Invention: To address the shortcomings of existing technologies, traditional solutions rely on single sensors such as current or force feedback for anomaly detection, which are insufficient to cover runaway scenarios involving multiple coupled factors such as hardware failures, software anomalies, and environmental interference. Furthermore, the "safe / dangerous" binary classification model cannot match differentiated braking strategies, leading to false triggering of low-risk scenarios or missed detection of high-risk scenarios. Additionally, braking methods relying on software shutdown or mechanical brakes suffer from long response delays, failing to meet the high time-accuracy safety requirements of minimally invasive surgery. This invention proposes a runaway braking system and method for surgical robots based on energy level jumps. By integrating a multimodal data acquisition module, a risk monitoring and braking control module, and a micro-detonation physical braking module, it achieves real-time monitoring of runaway risks in surgical robots, graded response to runaway risks, and hardware-level physical damage braking control. This solves the problems of insufficient multimodal data fusion for runaway monitoring, coarse-grained risk level monitoring, and passive braking delays in the field of runaway safety protection for intelligent surgical robots, making it difficult to accurately predict and intervene in runaway situations, leading to irreversible human injury or even death.

[0006] Technical solution: The present invention is a micro-detonation surgical robot runaway braking system based on energy level jump, including a multi-modal data acquisition module, a risk monitoring and braking control module, and a micro-detonation physical braking module;

[0007] The multimodal data acquisition module includes a hardware status data acquisition module, a motion status data acquisition module, a physiological status data acquisition module, and a data storage-fusion-transmission chip. The hardware status data acquisition module includes current acquisition, torque acquisition, temperature acquisition, and magnetic field acquisition modules. The motion status data acquisition module includes velocity acquisition, acceleration acquisition, point cloud acquisition, and depth acquisition modules. The physiological status data acquisition module includes blood oxygen acquisition, heart rate acquisition, and blood pressure acquisition modules. The risk monitoring and braking control module includes a communication module, a data fusion module, and braking module control circuitry.

[0008] The micro-detonation physical braking module includes a semiconductor bridge transducer, an energetic charge, a charge ring, a flyer plate, a flyer plate acceleration chamber, and a detonation energy output port.

[0009] This invention relates to a runaway braking method for a micro-detonation surgical robot based on energy level jumps, comprising the following steps:

[0010] (1) The hardware status data acquisition module collects the robot's manipulator motor current, manipulator joint reducer output shaft torque, manipulator motor temperature, and magnetic field strength at the manipulator motor; the motion status data acquisition module collects the robot's end effector's three-dimensional translational velocity components and three-dimensional translational acceleration components in the coordinate system, as well as the point cloud density of the end effector's operating area and the depth of the operating area from the body surface entrance; the physiological status data acquisition module collects the patient's blood oxygen saturation, heart rate variability, and blood pressure variability.

[0011] (2) Transmit the data collected in step (1) to the data storage-fusion-transmission chip, and convert the robot hardware risk quantification value R generated according to the risk monitoring function. mech Robot motion risk quantification value R motion and the robot physiological risk quantification value R bio The data is transmitted to the communication module and data fusion module, where a comprehensive risk quantification value R is obtained through a comprehensive risk monitoring function. mix ;

[0012]

[0013] α k (t) is the time function of risk weights for different modules, α mech For the risk weight of the hardware module, α motion For the risk weight of the motion module, α bio Risk weights for the physiological module; R k The hardware risk quantification value R mech Quantitative value of sports risk R motion and physiological risk quantification value R bio β is the cross-coupling factor;

[0014] (3) In the data fusion module, based on the comprehensive risk quantification value R mix Hardware risk quantification value R mech Quantitative value of sports risk R motion and physiological risk quantification value R bio The risk of robots going out of control is classified into low risk, medium risk, high risk, and ultra-high risk levels; among them,

[0015]

[0016] ω1 is the current risk weight; I is the robot arm motor current; μ1 is the current baseline mean; σ1 is the current standard deviation; ω2 is the torque risk weight; τ is the output shaft torque of the robot arm joint reducer; τ MAX ω3 represents the maximum safe torque; ω3 is the temperature weight; T is the surface temperature of the robotic arm motor; T safe ω4 represents the safe temperature threshold; ω4 represents the magnetic field weight; B xLet B be the component of the magnetic field strength vector along the X-axis at the robot arm motor. y B is the component along the Y-axis. z B represents the component along the Z-axis; MAX The threshold for magnetic field interference;

[0017]

[0018] Among them, R motion ω5 represents the quantification value of robot motion risk; v represents the motion risk weight. x v y v z For the speed of the robot's end effector; a x a y a z ω6 represents the acceleration of the robot's end effector; ω6 represents the risk weight of the surgical area; ρ represents the point cloud density of the robot's end effector's operating area. normal z is the baseline value for point cloud density. depth The depth of the robot's end effector operating area from the body surface inlet;

[0019]

[0020] Among them, R bio ω6 represents the physiological risk quantification value for the robot; ω6 represents the blood oxygen risk weight; SpO2 represents the patient's blood oxygen saturation; ω7 represents the risk weight for heart rate and blood pressure variability; HRV represents the patient's heart rate variability; BPV represents the patient's blood pressure variability; BPV norml These are normal values ​​for blood pressure variability;

[0021] (4) When the high-risk threshold R mix-3 ≤R mix or R mech R motion R bio When the safety threshold is exceeded, the robot is in an extremely high-risk state. The data fusion module sends a physical braking signal to the braking module control circuit. The braking module control circuit supplies power to the semiconductor bridge transducer in the micro-detonation physical braking module. The semiconductor bridge transducer releases high-temperature plasma under the electrothermal effect to drive the energetic charge to produce an electro-explosion effect. The energetic charge detonates and shears the edge of the flying blade, and drives the detonation energy output hole of the sheared flying blade, physically damaging the robot's power module to brake.

[0022] In step (1), heart rate variability

[0023] In step (1), blood pressure variability

[0024] In step (3), when R mix <Rmix-1 And R mech <R mech-safe And R motion <R motion-safe And R bio-safe At that time, the robot is in a low-risk situation, and the data fusion module records the robot's work in real time;

[0025] Among them, R mech-safe Hardware risk security threshold; R motion-safe R represents the safety threshold for sports risks. bio-safe The physiological risk safety threshold; R mix-1 The low-risk threshold is a comprehensive quantitative value.

[0026] In step (3), when R mix-1 ≤R mix <R mix-2 or R mech R motion R bio If any of the following exceeds the safety threshold, the robot is at medium risk, and the robotic arm motors slow down.

[0027] Among them, R mix-1 As a comprehensive quantitative value, the low-risk threshold, R mix-2 R is the risk threshold in the comprehensive quantitative value. mix-3 The high-risk threshold is a comprehensive quantitative value.

[0028] In step (3), when R mix-2 ≤R mix <R mix-3 or R mech R motion R bio If either of the following two conditions exceeds the safety threshold, the robot is at high risk and the robotic arm motors will stop; among them, R mix-2 R is the risk threshold in the comprehensive quantitative value. mix-3 The high-risk threshold is a comprehensive quantitative value.

[0029] In step (3), when B x >B MAX Or B y >B MAX Or B z >B MAX At that time, the ambient magnetic field can affect the operation of the hardware.

[0030] In step (3), when T>T safe At that time, the temperature risk is amplified through an exponential function.

[0031] Beneficial effects: Compared with the prior art, the present invention has the following advantages:

[0032] (1) This invention addresses the multimodal data fusion and risk level monitoring response, dynamic disaster recovery, and physical damage braking of surgical robot runaway risk. The process is as follows: First, a multimodal data-driven closed-loop risk monitoring system is constructed. By fusing heterogeneous data of hardware status (current, torque, temperature, magnetic field), motion status (velocity, acceleration, surgical area point cloud, surgical area depth), and physiological status (blood oxygen, heart rate, blood pressure), a dynamic weighted fusion algorithm is adopted to form a multimodal data fusion monitoring method of hardware risk quantification value, motion risk quantification value, physiological risk quantification value, and comprehensive risk quantification value. This achieves a leap from "single threshold judgment" to "multi-dimensional collaborative analysis" and improves the accuracy of surgical robot runaway identification.

[0033] (2) This invention establishes a graded response mechanism for the risk of loss of control of surgical robots. By integrating the monitoring of hardware status risk, motion status risk, physiological status risk and comprehensive monitoring risk, a graded response mechanism of L1 (low risk) to L4 (ultra-high risk) is established. This avoids the "one-size-fits-all" binary classification model of "safety / danger", reduces the probability of low-risk false triggering and high-risk missed judgment of loss of control of surgical robots, and improves the adaptability of the system to real surgical scenarios.

[0034] (3) The present invention forms a hardware-level rapid braking method based on micro-detonation. By integrating a micro-detonation physical braking module, it realizes rapid braking by driving the flying piece to move at high speed through micro-detonation of energetic agents to achieve energy level jump. The high-speed flying piece achieves rapid response and safe and reliable physical destruction braking by destroying the power module of the surgical robot. Attached Figure Description

[0035] Figure 1 This is a schematic diagram illustrating the composition and workflow of the runaway braking system for the micro-detonation surgical robot based on energy level jump of the present invention;

[0036] Figure 2 This is a schematic diagram of the packaging shell of the present invention;

[0037] Figure 3 This is an assembly diagram of the present invention;

[0038] Figure 4 This is a schematic diagram of the risk monitoring and braking control module of the present invention;

[0039] Figure 5 This is a schematic diagram of the micro-detonation physical braking module of the present invention. Detailed Implementation

[0040] like Figures 1 to 5As shown, the micro-detonation surgical robot runaway braking system based on energy level jump of the present invention consists of a multimodal data acquisition module 4, a risk monitoring and braking control module 2, a micro-detonation physical braking module 3, and an encapsulation shell 1.

[0041] The multimodal data acquisition module 4 consists of a hardware status data acquisition module 4-1, a motion status data acquisition module 4-2, a physiological status data acquisition module 4-3, and a data storage-fusion-transmission chip 4-4. Specifically, the hardware status data acquisition module 4-1 comprises a current acquisition module 4-1-1, a torque acquisition module 4-1-2, a temperature acquisition module 4-1-3, and a magnetic field acquisition module 4-1-4. The motion status data acquisition module 4-2 comprises a velocity acquisition module 4-2-1, an acceleration acquisition module 4-2-2, a point cloud acquisition module 4-2-3, and a depth acquisition module 4-2-4. The physiological status data acquisition module 4-3 comprises a blood oxygen acquisition module 4-3-1, a heart rate acquisition module 4-3-2, and a blood pressure acquisition module 4-3-3.

[0042] The risk monitoring and braking control module 2 consists of a communication module 2-1, a data fusion module 2-2, and a braking module control circuit 2-3. The micro-detonation physical braking module 3 consists of a semiconductor bridge transducer 3-1, an energetic charge 3-2, a charge ring 3-3, a flyer plate 3-4, a flyer plate acceleration chamber 3-5, and a detonation energy output port 3-6.

[0043] The present invention provides a runaway braking method for a micro-detonation surgical robot based on energy level jumps, which is implemented by a multimodal data acquisition module, a risk monitoring and braking control module, and a micro-detonation physical braking module. The braking method includes the following steps:

[0044] (1) The hardware status data acquisition module, motion status data acquisition module and physiological status data acquisition module in the multimodal data acquisition module are respectively installed on the relevant positions of the surgical robot to perform real-time data acquisition.

[0045] (1.1) The current acquisition module in the hardware status data acquisition module is installed at the motor of the surgical robot's robotic arm to acquire the motor current I in real time. The motor current signal I reflects the motor's power load, and a sudden increase in current indicates motor overload or mechanical jamming. The torque acquisition module is installed at the joint harmonic reducer of the surgical robot's robotic arm to acquire the output shaft torque τ of the joint harmonic reducer in real time. The torque τ reflects the stress state of the mechanical transmission chain. When the contact force between the robotic arm and human tissue is too large, it will cause the torque to exceed the limit. The temperature acquisition module is installed at the motor of the surgical robot's robotic arm to acquire the surface temperature T of the robotic arm motor in real time. The temperature T of the motor driver reflects its heat generation. Excessive temperature will cause material expansion or electronic component failure. The magnetic field acquisition module is installed at the motor of the surgical robot's robotic arm to acquire the x-axis magnetic field strength B at the robotic arm motor in real time. x y-axis magnetic field strength B y z-axis magnetic field strength B z Magnetic field strength B along the x-axis x y-axis magnetic field strength B y z-axis magnetic field strength B z The electromagnetic interference in the reaction environment can affect the robot's control signals when the magnetic field strength is high.

[0046] (1.2) The velocity acquisition module in the motion state data acquisition module is installed at the end effector of the surgical robot's robotic arm to acquire the three-dimensional translational velocity components of the end effector of the surgical robot in the selected coordinate system in real time: the velocity component v along the x-axis. x The velocity component v along the y-axis y and the velocity component v along the z-axis z， The end effector's velocity reflects the robotic arm's motion state. High speeds or sudden increases in velocity can cause tissue tearing in the surgical area. An acceleration acquisition module is mounted on the end effector of the surgical robot's arm to collect real-time three-dimensional translational acceleration components in a selected coordinate system: the acceleration component a along the x-axis. x The acceleration component a along the y-axis y and the acceleration component a along the z-axis zThe end effector's acceleration reflects its dynamic changes in motion. Changes in acceleration caused by abnormal control commands or external impacts can lead to accidental injury. A point cloud acquisition module is mounted on the end effector of the surgical robot's arm to collect the point cloud density ρ of the operating area in real time. The point cloud density ρ of the surgical area reflects the complexity of the tissue structure; a larger ρ indicates a dense area of ​​blood vessels or nerve bundles, making the surgical operation more difficult. A depth acquisition module is mounted on the end effector of the surgical robot's arm to collect the depth z of the operating area from the body surface entrance in real time. depth The depth z of the operating area of ​​the end effector from the body surface inlet depth The larger the value, the deeper the surgical robot's end effector penetrates into the human body, and the higher the operational risk.

[0047] (1.3) The blood oxygen acquisition module in the physiological state data acquisition module is worn by the patient to collect the patient's blood oxygen saturation (SpO2) in real time, reflecting the tissue oxygen supply status. When the patient's SpO2 < 90%, it indicates hypoxia and requires emergency intervention. The heart rate acquisition module is worn by the patient to collect the patient's heart rate variability (HRV) in real time. HRV is the root mean square value of the difference between consecutive RR intervals (the time interval between R wave peaks) on the electrocardiogram, reflecting the autonomic nervous system's ability to regulate the heart rhythm. The calculation method for HRV is as follows: Its normal range is 20-50ms. The lower the value, the more sympathetic nerve excitation (such as pain or fear in the patient), requiring timely intervention. A blood pressure monitoring module is worn on the patient to collect the patient's blood pressure variability (BPV) in real time. BPV is the standard deviation of the continuous difference in systolic blood pressure (SBP), reflecting the autonomic nervous system's ability to regulate the cardiovascular system. It is positively correlated with intraoperative stress response, and its calculation formula is:

[0048] (2) The hardware status data acquisition module, motion status data acquisition module, and physiological status data acquisition module in the multimodal data acquisition module transmit the acquired data information to the data storage-fusion-transmission chip. In the data storage-fusion-transmission chip, based on different risk monitoring functions, hardware risk quantification values ​​R of the surgical robot runaway dynamic disaster recovery monitoring method are formed respectively. mech Dynamic disaster recovery monitoring method for surgical robot out-of-control movement, quantification value of motion risk R motion And the physiological risk quantification value R of the dynamic disaster recovery monitoring method for uncontrolled surgical robots. bio .

[0049] (2.1) Quantitative value of surgical robot hardware risk R mech The data obtained from the hardware status data acquisition module is as follows:

[0050] Among them, R mech ω1 represents the quantified hardware risk value for dynamic disaster recovery in surgical robot outages; ω1 represents the current risk weight, reflecting the contribution of current to the hardware risk of the dynamic disaster recovery monitoring method for surgical robot outages. The higher the weight, the greater the impact of current anomalies on hardware risk; I represents the real-time acquisition current of the robotic arm motor by the current acquisition module; μ1 represents the current baseline mean, obtained through statistical analysis of historical normal operating data, representing the average current value of the motor under no abnormal load; σ1 represents the current standard deviation, used to quantify the fluctuation range of current, using 3σ1 as the normalization denominator, covering 99.7% of the normal distribution interval; ω2 represents the torque risk weight, reflecting the contribution of torque to the hardware risk of the dynamic disaster recovery monitoring method for surgical robot outages. The higher the weight, the greater the impact of torque anomalies on hardware risk; τ represents the real-time acquisition torque τ of the output shaft of the surgical robot robotic arm joint harmonic reducer by the torque acquisition module; τ MAX This represents the maximum safe torque, when τ > τ MAX At this time, there is a risk of mechanical structure damage; ω3 represents temperature weight, reflecting the sensitivity of motor temperature to hardware health status; T represents the surface temperature of the robotic arm motor collected in real time by the temperature acquisition module; T safe This represents the safe temperature threshold, when T>T safe At that time, temperature risk is rapidly amplified using an exponential function; ω4 represents the magnetic field weight, reflecting the impact of the magnetic field on the normal operation of the hardware; B x B y B z These represent the components of the magnetic field intensity vector at the robotic arm motor along the X, Y, and Z axes, respectively, acquired in real time by the magnetic field acquisition module in the selected coordinate system; B MAX Indicates the magnetic field interference threshold, when B x >B MAX Or B y >B MAX Or B z >B MAX At that time, the ambient magnetic field will affect the normal operation of the hardware.

[0051] (2.2) Quantitative value of sports risk R motion Data acquired through the motion state data acquisition module is used to obtain... Among them, R motion ω5 represents the quantified value of the dynamic disaster recovery motion risk of the surgical robot in the event of loss of control; ω5 represents the motion risk weight, reflecting the contribution of the motion speed and its changes of motion speed of the surgical robot's end effector to its risk of loss of control; v x v y v zThis indicates the speed of the surgical robot's end effector, which is collected in real time by the speed acquisition module; a x a y a z ω represents the acceleration of the surgical robot's end effector, which is collected in real time by the acceleration acquisition module; ω6 represents the surgical area risk weight, reflecting the contribution of the complexity of the surgical robot's operating area to its runaway risk; ρ represents the point cloud density of the surgical robot's end effector operating area, which is collected in real time by the point cloud acquisition module. normal This represents the baseline value for conventional point cloud density, when ρ > ρ normal When this time, it indicates that the difficulty of operation in the current operating area has increased; z depth This indicates the depth of the surgical robot's end effector operating area from the body surface entrance, as collected in real time by the depth acquisition module. The deeper the surgical robot's end effector penetrates into the human body, the higher the operational risk.

[0052] (2.3) Quantitative value of physiological risk of surgical robot malfunction R bio Data acquired through the physiological state data acquisition module is used to obtain... Where R bio This represents the quantified physiological risk value for dynamic disaster recovery in surgical robot malfunction; ω6 represents the blood oxygen risk weight, reflecting the contribution of blood oxygen status to the risk of the patient's vital signs; SpO2 represents the patient's blood oxygen saturation collected in real time by the blood oxygen acquisition module, and when blood oxygen saturation decreases, the blood oxygen risk is rapidly amplified through an exponential function; ω7 represents the heart rate and blood pressure variability risk weight, reflecting the contribution of the patient's heart rate and blood pressure variability to the risk of the patient's vital signs; HRV represents the patient's heart rate variability collected in real time by the heart rate acquisition module. Heart rate variability HRV is the root mean square value of the difference between consecutive RR intervals (the time interval between R wave peaks) on the electrocardiogram, reflecting the autonomic nervous system's ability to regulate the heart rhythm. The calculation method for heart rate variability HRV is as follows: HRV norml This represents the normal value for heart rate variability; BPV represents the real-time blood pressure variability of the patient collected by the blood pressure acquisition module. Blood pressure variability (BPV) is the standard deviation of the continuous differences in systolic blood pressure (SBP), reflecting the autonomic nervous system's ability to regulate the cardiovascular system. Its calculation formula is: BPV norml This indicates the normal range for blood pressure variability.

[0053] (3) Quantify the hardware risk R of the surgical robot out of control formed in step (2). mech Quantitative value of the risk of uncontrolled movement of surgical robots (R) motion And the physiological risk quantification value R of surgical robot malfunction bio The data is transmitted to the communication module in the risk monitoring and braking control module via the data storage-fusion-transmission chip in the multimodal data acquisition module.

[0054] (4) Quantify the hardware risk value R obtained by the communication module in the risk monitoring and braking control module. mech Quantitative value of sports risk R motion and physiological risk quantification value R bio The data is transmitted to the data fusion module within the risk monitoring and braking control module. In the data fusion module, the acquired data is further processed, and the comprehensive risk quantification value R is obtained through the comprehensive risk monitoring function. mix : Where, α k (t) represents the time function of risk weights for different modules, α mech α represents the risk weight of the hardware module. motion Represents the risk weight of the motion module, α bio This represents the risk weight of the physiological module, whose initial value and how it changes over time are set according to different types of surgery; R k R represents the hardware risk quantification value. mech Quantitative value of sports risk R motion and physiological risk quantification value R bio β represents the cross-coupling factor, which reflects the impact of changes in the risk quantification values ​​of multiple modules over time on the overall risk change. The specific value is set according to different types of surgery.

[0055] (5) In the data fusion module of the risk monitoring and braking control module, based on the obtained comprehensive risk quantification value R mix Hardware risk quantification value R mech Quantitative value of sports risk R motion and physiological risk quantification value R bio The following table categorizes the risk levels of loss of control for surgical robots.

[0056] Table 1

[0057]

[0058]

[0059] Among them, R mech-safe This indicates the hardware risk and safety threshold; the specific value is set according to different types of surgeries. motion-safe This indicates the safety threshold for exercise risk; the specific value is set according to the different types of surgery. (R) bio-safe This represents the physiological risk safety threshold, the specific value of which is set according to the different types of surgery; R mix-1 This represents the low-risk threshold of the comprehensive quantitative value; the specific value is set according to the different types of surgeries. (R) mix-2This represents the risk threshold in the comprehensive quantitative value; the specific value is set according to the different types of surgeries. (R) mix-3 This represents the high-risk threshold of the comprehensive quantitative value, and its value is set according to different types of surgery.

[0060] (6) When the intelligent surgical robot is in the L4-ultra-high risk state, in the risk monitoring and braking control module, the data fusion module sends a physical braking signal to the braking module control circuit. The braking module control circuit starts to work and supplies power to the semiconductor bridge transducer in the micro-detonation physical braking module. The semiconductor bridge transducer releases high-temperature plasma under the electrothermal effect to drive the energetic charge to generate an electro-explosion effect. The energetic charge detonates and shears the edge of the flying blade, and drives the sheared flying blade to move at high speed in the flying blade acceleration chamber. Through the detonation energy output hole, the power module of the intelligent surgical robot is physically damaged, and the real-time braking of the surgical robot is realized.

Claims

1. A runaway braking system for a micro-detonation surgical robot based on energy level jumps, characterized in that: It includes a multimodal data acquisition module, a risk monitoring and braking control module, and a micro-detonation physical braking module; The multimodal data acquisition module includes a hardware status data acquisition module, a motion status data acquisition module, a physiological status data acquisition module, and a data storage-fusion-transmission chip; The hardware status data acquisition module includes a current acquisition module, a torque acquisition module, a temperature acquisition module, and a magnetic field acquisition module; the motion status data acquisition module includes a speed acquisition module, an acceleration acquisition module, a point cloud acquisition module, and a depth acquisition module; the physiological status data acquisition module includes a blood oxygen acquisition module, a heart rate acquisition module, and a blood pressure acquisition module; the risk monitoring and braking control module includes a communication module, a data fusion module, and a braking module control circuit.

2. The runaway braking system for a micro-detonation surgical robot based on energy level jump according to claim 1, characterized in that: The micro-detonation physical braking module includes a semiconductor bridge transducer, an energetic charge, a charge ring, a flyer plate, a flyer plate acceleration chamber, and a detonation energy output port.

3. A runaway braking method for a micro-detonation surgical robot based on energy level jumps, characterized in that: Includes the following steps: (1) The robot's mechanical arm motor current, mechanical arm joint reducer output shaft torque, mechanical arm motor temperature and magnetic field strength at the mechanical arm motor are collected by the hardware status data acquisition module; the robot's end effector three-dimensional translational velocity component and three-dimensional translational acceleration component in the coordinate system, as well as the point cloud density of the end effector operation area and the depth of the operation area from the body surface entrance are collected by the motion status data acquisition module. The physiological state data acquisition module collects the patient's blood oxygen saturation, heart rate variability, and blood pressure variability; (2) Transmit the data collected in step (1) to the data storage-fusion-transmission chip, and convert the robot hardware risk quantification value R generated according to the risk monitoring function. mech Robot motion risk quantification value R motion and the robot physiological risk quantification value R bio The data is transmitted to the communication module and data fusion module, where a comprehensive risk quantification value R is obtained through a comprehensive risk monitoring function. mix ; α k (t) is the time function of risk weights for different modules, α mech For the risk weight of the hardware module, α motion For the risk weight of the motion module, α bio Risk weights for the physiological module; R k The hardware risk quantification value R mech Quantitative value of sports risk R motion and physiological risk quantification value R bio β is the cross-coupling factor; (3) In the data fusion module, based on the comprehensive risk quantification value R mix Hardware risk quantification value R mech Quantitative value of sports risk R motion and physiological risk quantification value R bio The risk of robots going out of control is classified into low risk, medium risk, high risk, and ultra-high risk levels; among them, ω1 is the current risk weight; I is the robot arm motor current; μ1 is the current baseline mean; σ1 is the current standard deviation; ω2 is the torque risk weight; τ is the output shaft torque of the robot arm joint reducer; τ MAX ω3 represents the maximum safe torque; ω3 is the temperature weight; T is the surface temperature of the robotic arm motor; T safe ω4 represents the safe temperature threshold; ω4 represents the magnetic field weight; B x Let B be the component of the magnetic field strength vector along the X-axis at the robot arm motor. y B is the component along the Y-axis. z B represents the component along the Z-axis; MAX The threshold for magnetic field interference; Among them, R motion ω5 represents the quantification value of robot motion risk; v represents the motion risk weight. x v y v z For the speed of the robot's end effector; a x a y a z ω6 represents the acceleration of the robot's end effector; ω6 represents the risk weight of the surgical area; ρ represents the point cloud density of the robot's end effector's operating area. normal z is the baseline value for point cloud density. depth The depth of the robot's end effector operating area from the body surface inlet; Among them, R bio ω6 represents the physiological risk quantification value for the robot; ω6 represents the blood oxygen risk weight; SpO2 represents the patient's blood oxygen saturation; ω7 represents the risk weight for heart rate and blood pressure variability; HRV represents the patient's heart rate variability; BPV represents the patient's blood pressure variability; BPV norml These are normal values ​​for blood pressure variability; (4) When the high-risk threshold R mix-3 ≤R mix or R mech R motion R bio When the safety threshold is exceeded, the robot is in an extremely high-risk state. The data fusion module sends a physical braking signal to the braking module control circuit. The braking module control circuit supplies power to the semiconductor bridge transducer in the micro-detonation physical braking module. The semiconductor bridge transducer releases high-temperature plasma under the electrothermal effect to drive the energetic charge to produce an electro-explosion effect. The energetic charge detonates and shears the edge of the flying blade, and drives the detonation energy output hole of the sheared flying blade, physically damaging the robot's power module to brake.

4. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (1), the heart rate variability 5. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (1), the blood pressure variability 6. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (3), when R mix <R mix-1 And R mech <R mech-safe And R motion <R motion-safe And R bio-safe At that time, the robot is in a low-risk situation, and the data fusion module records the robot's work in real time; Among them, R mech-safe Hardware risk security threshold; R motion-safe R represents the safety threshold for sports risks. bio-safe The physiological risk safety threshold; R mix-1 The low-risk threshold is a comprehensive quantitative value.

7. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (3), when R mix-1 ≤R mix <R mix-2 or R mech R motion R bio If any of the following exceeds the safety threshold, the robot is at medium risk, and the robotic arm motors slow down. Among them, R mix-1 As a comprehensive quantitative value, the low-risk threshold, R mix-2 R is the risk threshold in the comprehensive quantitative value. mix-3 The high-risk threshold is a comprehensive quantitative value.

8. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (3), when R mix-2 ≤R mix <R mix-3 or R mech R motion R bio If either of the following two conditions exceeds the safety threshold, the robot is at high risk and the robotic arm motors will stop; among them, R mix-2 R is the risk threshold in the comprehensive quantitative value. mix-3 The high-risk threshold is a comprehensive quantitative value.

9. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (3), when B x >B MAX Or B y >B MAX Or B z >B MAX At that time, the environmental magnetic field affects the operation of the hardware.

10. The runaway braking method for a micro-detonation surgical robot based on energy level jump according to claim 3, characterized in that: In step (3), when T>T safe At that time, the temperature risk is amplified through an exponential function.

Images