Cambliance training equipment

Abstract

The invention discloses sword skill training equipment and relates to the technical field of training equipment. The fixed main frame body carries a mechanical arm system, a control system and an evaluation system; the tail end of the target feeding mechanical arm is provided with an induction sword target; the tail end of the sword holding mechanical arm is provided with an auxiliary training sword; the sensing training sword is provided with a motion sensor for recognizing the sword holding posture and the sword outlet speed of the trainer in real time; the induction shield is provided with an induction system for detecting defense times of the trainee; the heart rate sensor recognizes the heart rate change of the trainee in real time; the control system comprises a data analysis module, a feedback adjustment module, a trajectory planning module and a safety protection module. The evaluation system evaluates the response time, sword motion and heart rate of the trainee. The equipment main body is provided with an induction sword target and an auxiliary training sword, meanwhile, a trainer is provided with an induction training sword and an induction shield, the training difficulty can be automatically adjusted by combining a sensing detection and control method, the intelligent degree is high, and the sword operation performance of the trainer can be optimized.

Description

Technical Field

[0001] The invention relates to the technical field of training equipment, in particular to a swordsmanship training device. Background Art

[0002] As an important field of competitive sports and self-defense skills training, the technical development of swordsmanship training has always revolved around the accuracy of actual combat simulation and the scientific nature of training. The traditional training model relies on manual sparring and fixed targets, and has inherent defects such as the unquantifiable training intensity and the lack of real-time feedback on the standardization of movements. Although modern electronic devices have introduced basic sensing technology to record the number and strength of strikes, it is still difficult to achieve dynamic interaction in offensive and defensive coordinated training, let alone simulate the multi-dimensional technical movements in real confrontations.

[0003] The current mainstream training equipment generally has the following technical limitations:

[0004] Insufficient flexibility of mechanical actuators: Most mechanical devices with rigid structures have problems such as stiff motion trajectory and delayed response when simulating complex actions such as slashing, stabbing, and blocking. They cannot restore the flexibility requirements of real swordsmanship and are prone to causing joint injuries to trainees.

[0005] Single dimension of data collection: Existing systems mostly focus on monitoring limb movement trajectories, ignoring the simultaneous analysis of physiological indicators such as heart rate and muscle reaction speed, resulting in a lack of scientific basis for training intensity assessment and body load management;

[0006] Fixed training mode: The fixed preset difficulty level is difficult to adapt to the advanced needs of trainees with different skill levels, especially in high-level attack and defense conversion training, it is impossible to dynamically adjust the strategy according to real-time performance;

[0007] Lack of equipment coordination: Offensive and defensive training equipment often operate independently, making it impossible to build a training scenario in which the attack and defense are linked, resulting in significant differences between training results and actual confrontations.

[0008] In addition, existing technologies have low support for personalized training and lack solutions that organically integrate action standardization, physiological status monitoring, and intelligent difficulty adjustment. Especially when simulating real confrontations, how to balance the dynamic response speed and motion compliance of mechanical devices, and how to establish a comprehensive analysis model for multi-source heterogeneous data, have become key technical bottlenecks restricting the intelligent development of fencing training equipment. Therefore, there is an urgent need for an integrated training device that can achieve high-fidelity action simulation, multi-dimensional physiological monitoring, offensive and defensive coordinated training, and intelligent difficulty adjustment, in order to promote the innovation of fencing training technology towards scientific and precise directions. Summary of the invention

[0009] In view of the problem that existing sword training equipment lacks interactive mechanism and has poor flexibility, the present invention provides a sword training device, which is equipped with an inductive sword target and an auxiliary training sword for the device body, and an inductive training sword and an inductive shield for the trainee. Combined with the sensor detection and control method, the training difficulty can be automatically adjusted, the degree of intelligence is high, and it helps to optimize the sword performance of the trainee.

[0010] To achieve the above-mentioned object, the present invention adopts the following technical scheme: a sword training device, including a fixed main frame, a mechanical arm system, an inductive training sword, an inductive shield, a heart rate sensor, a control system and an evaluation system;

[0011] The fixed main frame is equipped with a robotic arm system, a control system and an evaluation system;

[0012] The robotic arm system comprises a target delivery robotic arm and a sword holding robotic arm, wherein a sensing sword target is installed at the end of the target delivery robotic arm, and a force sensor is provided on the sensing sword target. The target delivery robotic arm is controlled by a control system to drive the sensing sword target to perform a target delivery action, and an auxiliary training sword is installed at the end of the sword holding robotic arm. The sword holding robotic arm is controlled by a control system to drive the auxiliary training sword to simulate a swordsmanship action.

[0013] The induction training sword is provided with a motion sensor capable of identifying the trainee's sword holding posture and sword drawing speed in real time;

[0014] The induction shield is provided with an induction system capable of detecting the number of defense times of the trainee;

[0015] The heart rate sensor recognizes the heart rate changes of the trainee in real time;

[0016] The control system includes a data analysis module, a feedback adjustment module, a trajectory planning module and a safety protection module; the data analysis module collects the force, time and frequency data of the trainee hitting the inductive sword target through a force sensor, and analyzes the accuracy of the trainee hitting the inductive sword target with the inductive training sword in combination with the control data of the target delivery action of the target delivery mechanical arm; the feedback adjustment module sets an evaluation index, and according to the difference between the evaluation index and the accuracy obtained by the data analysis module, automatically adjusts the frequency and speed of the target delivery mechanical arm driving the inductive sword target to deliver the target through a PID control method with neural network parameter adjustment; the trajectory planning module generates the expected trajectory of the auxiliary training sword by using a trajectory interpolation method based on a preset sword action database; the safety protection module is provided with a visual recognition system and a safety interlock system, the visual recognition system monitors the distance between the auxiliary training sword and the trainee in real time, the safety interlock system detects the force value of the auxiliary training sword through a pressure sensor, and cuts off the power supply through an emergency power-off switch if the distance between the auxiliary training sword and the trainee or the force value of the auxiliary training sword exceeds the warning value;

[0017] The evaluation system combines the collected data of the motion sensor and the heart rate sensor with the training duration to evaluate the trainee's reaction time, swordsmanship movements and heart rate.

[0018] Furthermore, the target delivery robotic arm and the sword holding robotic arm both adopt four-degree-of-freedom robotic arms, including a 60kg·cm servo arranged at the upper arm joint and three 20kg·cm servos respectively arranged at the elbow joint, the forearm joint and the hand joint. The control data sent by the control system is parsed by a CAN protocol analyzer and sent to each servo to realize the motion control of the robotic arm.

[0019] Furthermore, the induction system of the induction shield sets conductive foam in the interlayer of the induction shield and converts its resistance change into a voltage signal in combination with a voltage divider circuit and transmits it to the control system, thereby identifying the number of times the induction shield blocks the auxiliary training sword, and subtracting the number of times the auxiliary training sword is swung by the sword-holding mechanical arm from the number of times the induction shield blocks, to obtain the number of times the trainee successfully defends.

[0020] Furthermore, the PID control method formula of the neural network parameter adjustment is as follows:

[0021]

[0022] v target =v max (1-FI)

[0023] u(t)=K p (v target -v actual )

[0024] In the formula, FI is the fatigue index, HR is the current heart rate, and HR rest is the resting heart rate, HR max =220-age, v target is the target delivery rate, v max is the maximum target delivery rate, u(t) is the control quantity acting on the target delivery manipulator, K p is the PID parameter, v actual is the actual target delivery rate.

[0025] Furthermore, the reaction time is evaluated by calculating the time interval from when the target delivery robot arm drives the inductive sword target to start the target delivery action to when the inductive training sword hits the surface of the inductive sword target as the trainee's reaction time.

[0026] Furthermore, the evaluation of the swordplay movements is carried out by sensing the motion sensor on the training sword to obtain the trainee's sword-holding posture and sword-drawing speed, and constructing a swordplay movement standardization evaluation model based on the convolutional neural network CNN. The input of the model is the time series data of the angle and speed of the motion sensor in three directions in space, the time length is the standard execution time of each action, and the output is a score of 0 to 1. The closer the score is to 1, the more standard the action is.

[0027] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention equips the main body of the device with an inductive sword target and an auxiliary training sword, and equips the trainee with an inductive training sword and an inductive shield, supports a training mode of fencing target shooting and shield defense in coordination with each other, and by combining various sensing detection and control methods, can automatically adjust the training difficulty according to the level of the trainee, thereby providing a personalized training experience, adopts two four-degree-of-freedom robotic arms to achieve high-performance smooth control of the inductive sword target and the auxiliary training sword, simulates fencing movements, and through comprehensive sensing motion sensor data, heart rate sensor data and training duration, can evaluate the trainee's reaction time, fencing movements and heart rate, provide comprehensive feedback for the trainee, is suitable for personalized training of various scenarios and difficulties, and through real-time monitoring and feedback, helps to optimize the trainee's fencing performance, provides more accurate and flexible support for fencing training, has a high degree of intelligence, and has important significance and application value for the innovation and development of fencing training technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the overall structure of the swordsmanship training device of the present invention;

[0029] Figure 2 It is a system block diagram of the swordsmanship training device of the present invention.

[0030] In the figure: 1. Fixed main frame; 2. Target delivery robotic arm; 3. Sword holding robotic arm; 4. Inductive sword target; 5. Inductive training sword; 6. Inductive shield. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0032] like Figure 1-2 As shown, a sword training device includes a fixed main frame 1, a mechanical arm system, an induction training sword 5, an induction shield 6, a heart rate sensor, a control system and an evaluation system.

[0033] The fixed main frame 1 is equipped with a robotic arm system, a control system and an evaluation system.

[0034] The mechanical arm system includes a target delivery mechanical arm 2 and a sword holding mechanical arm 3, wherein the target delivery mechanical arm 2 is provided with an inductive sword target 4 at the end thereof, and the inductive sword target 4 is provided with a force sensor capable of collecting the force of the trainee hitting the target position, and the target delivery mechanical arm 2 is controlled by the control system to drive the inductive sword target 4 to perform the target delivery action, so as to assist in guiding and detecting the sword holding attack of the trainee; the sword holding mechanical arm 3 is provided with an auxiliary training sword at the end thereof, and the sword holding mechanical arm 3 is controlled by the control system to drive the auxiliary training sword to simulate the sword fighting action, so as to assist in guiding and practicing the shield holding defense of the trainee. The target delivery mechanical arm 2 and the sword holding mechanical arm 3 both adopt a four-degree-of-freedom mechanical arm, including a 60kg·cm steering gear arranged at the upper arm joint and three 20kg·cm steering gears arranged at the elbow joint, the forearm joint and the hand joint respectively, and the control data sent by the control system is parsed by the CAN protocol analyzer and sent to each steering gear to realize the action control of the target delivery mechanical arm 2 and the sword holding mechanical arm 3, and the power supply adopts a 24V adjustable power supply.

[0035] The induction training sword 5 is held by the trainee, and the induction training sword 5 is provided with a motion sensor which can recognize the sword holding posture and sword drawing speed of the trainee in real time.

[0036] The induction shield 6 is held by the trainee. The induction shield 6 is provided with an induction system capable of detecting whether the swordplay action output by the auxiliary training sword controlled by the sword-holding mechanical arm 3 is successfully defended by the trainee. Specifically, the induction system refers to a conductive foam arranged in the interlayer of the induction shield 6. When hit by the auxiliary training sword, the resistance of the conductive foam decreases. Combined with the voltage divider circuit, the resistance change is converted into a voltage signal and transmitted to the control system, so as to identify the number of times the induction shield 6 resists the auxiliary training sword. The number of times the auxiliary training sword is blocked by the sword-holding mechanical arm 3 is subtracted from the number of times the induction shield 6 resists, and the number of times the trainee successfully defends can be determined.

[0037] The heart rate sensor is worn by the trainee and can identify the trainee's heart rate changes in real time.

[0038] The control system controls the target delivery robot arm 2 and the sword holding robot arm 3, wherein:

[0039] The control of the target delivery robot 2 can adaptively change the target delivery rhythm, including a data analysis module and a feedback adjustment module. The data analysis module collects the force, time and frequency data of the trainee hitting the inductive sword target 4 through a force sensor, and combines the control data of the target delivery action of the target delivery robot 2 to analyze the accuracy of the trainee hitting the inductive sword target 4 with the inductive training sword 5. The feedback adjustment module sets an evaluation index, and according to the difference between the evaluation index and the accuracy obtained by the data analysis module, the PID control method with neural network parameter adjustment is used to automatically adjust the frequency and speed of the target delivery robot 2 to drive the inductive sword target 4 to deliver the target. If the accuracy is higher than the evaluation index, the frequency and speed of the target delivery are accelerated, otherwise, the frequency and speed of the target delivery are slowed down to achieve targeted changes in the training rhythm. Among them, the core formula of the PID control method with neural network parameter adjustment is as follows:

[0040]

[0041] v target =v max (1-FI)

[0042] u(t)=K p (v target -v actual )

[0043] In the formula, FI is the fatigue index, HR is the current heart rate, and HR rest is the resting heart rate, HR max =220-age, v target is the target delivery rate, v max is the maximum target delivery rate, u(t) is the control quantity acting on the target delivery manipulator, K p is the PID parameter, v actual is the actual target delivery rate;

[0044] The control of the sword-holding mechanical arm 3 can set the swordplay movements and safety braking protection simulated by the auxiliary training sword, including a trajectory planning module and a safety protection module. The trajectory planning module uses a trajectory interpolation method to generate the expected trajectory of the auxiliary training sword based on a preset swordplay movement database. The safety protection module is equipped with a visual recognition system and a safety interlocking system. The visual recognition system monitors the distance between the auxiliary training sword and the trainee in real time. The safety interlocking system detects the force value of the auxiliary training sword through a pressure sensor. If the distance between the auxiliary training sword and the trainee or the force value of the auxiliary training sword exceeds the warning value, the power supply is cut off through the emergency power-off switch to ensure the safety of the training process.

[0045] The evaluation system combines the collected data of the motion sensor and the heart rate sensor with the training duration to evaluate the trainee's reaction time, swordplay movements and heart rate after the training, wherein:

[0046] The reaction time is evaluated by calculating the time interval from when the target delivery robot arm 2 drives the induction sword target 4 to start the target delivery action to when the trainee hits the surface of the induction sword target 4 with the induction training sword 5, as the trainee's reaction time;

[0047] For the evaluation of swordplay movements, the motion sensor on the training sword 5 is used to obtain the trainee's sword-holding posture and sword-drawing speed. A swordplay movement standardization evaluation model is constructed based on the convolutional neural network CNN. Its input is the time series data of the angle and speed of the motion sensor in three directions in space. The time length is the standard execution time of each action. The output is a score of 0 to 1. The closer the score is to 1, the more standard the action.

[0048] The heart rate assessment combines the trainee's heart rate data and training duration, and uses a preset physiological model to assess the trainee's endurance level.

[0049] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other forms of assembly without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations within the meaning and range of equivalents of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0050] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A swordsmanship training device, characterized in that: It includes a fixed main frame (1), a mechanical arm system, an induction training sword (5), an induction shield (6), a heart rate sensor, a control system and an evaluation system; The fixed main frame (1) is equipped with a robotic arm system, a control system and an evaluation system; The mechanical arm system comprises a target delivery mechanical arm (2) and a sword holding mechanical arm (3); a sensing sword target (4) is installed at the end of the target delivery mechanical arm (2); the sensing sword target (4) is provided with a force sensor; the target delivery mechanical arm (2) is controlled by a control system to drive the sensing sword target (4) to perform a target delivery action; an auxiliary training sword is installed at the end of the sword holding mechanical arm (3); the sword holding mechanical arm (3) is controlled by a control system to drive the auxiliary training sword to simulate a swordsmanship action; The induction training sword (5) is provided with a motion sensor capable of identifying the sword holding posture and sword drawing speed of the trainee in real time; The induction shield (6) is provided with an induction system capable of detecting the number of defense times of the trainee; The heart rate sensor recognizes the heart rate changes of the trainee in real time; The control system comprises a data analysis module, a feedback adjustment module, a trajectory planning module and a safety protection module; the data analysis module collects the force, time and frequency data of the trainee hitting the inductive sword target (4) through a force sensor, and analyzes the accuracy of the trainee hitting the inductive sword target (4) with the inductive training sword (5) in combination with the control data of the target delivery action of the target delivery mechanical arm (2); the feedback adjustment module sets an evaluation index, and according to the difference between the evaluation index and the accuracy obtained by the data analysis module, automatically adjusts the frequency and speed of the target delivery mechanical arm (2) driving the inductive sword target (4) to deliver the target through a PID control method with neural network parameter adjustment; the trajectory planning module generates the expected trajectory of the auxiliary training sword by using a trajectory interpolation method based on a preset sword action database; the safety protection module is provided with a visual recognition system and a safety interlocking system, the visual recognition system monitors the distance between the auxiliary training sword and the trainee in real time, the safety interlocking system detects the force value of the auxiliary training sword through a pressure sensor, and cuts off the power supply through an emergency power off switch if the distance between the auxiliary training sword and the trainee or the force value of the auxiliary training sword exceeds the warning value; The evaluation system combines the collected data of the motion sensor and the heart rate sensor with the training duration to evaluate the trainee's reaction time, swordsmanship movements and heart rate.

2. A sword training device according to claim 1, characterized in that: The target delivery robot arm (2) and the sword holding robot arm (3) both adopt four-degree-of-freedom robot arms, including a 60kg·cm steering gear arranged at the upper arm joint and three 20kg·cm steering gears respectively arranged at the elbow joint, the lower arm joint and the hand joint. The control data sent by the control system is analyzed by a CAN protocol analyzer and sent to each steering gear to realize the motion control of the robot arm.

3. A swordsmanship training device according to claim 1, characterized in that: The induction system of the induction shield (6) is configured with conductive foam in the interlayer of the induction shield (6), and combined with a voltage divider circuit, the resistance change is converted into a voltage signal and transmitted to the control system, thereby identifying the number of times the induction shield (6) blocks the auxiliary training sword, and subtracting the number of times the auxiliary training sword is swung by the sword-holding mechanical arm (3) from the number of times the induction shield (6) blocks, thereby obtaining the number of times the trainee successfully defends.

4. The sword training device according to claim 1, characterized in that: The formula of the PID control method for neural network parameter adjustment is as follows: V target =v max (1-FI) u(t)=K p (v target -v actual ) In the formula, FI is the fatigue index, HR is the current heart rate, and HR rest is the resting heart rate, HR max =220-age, v target is the target delivery rate, v max is the maximum target delivery rate, u(t) is the control quantity acting on the target delivery manipulator, K p is the PID parameter, v actual is the actual target delivery rate.

5. The sword training device according to claim 1, characterized in that: The reaction time is evaluated by calculating the time interval from the time when the target delivery mechanical arm (2) drives the inductive sword target (4) to start the target delivery action to the time when the inductive training sword (5) hits the surface of the inductive sword target (4) as the trainee's reaction time.

6. The sword training device according to claim 1, characterized in that: The evaluation of the swordplay action is carried out by sensing the motion sensor on the training sword (5) to obtain the trainee's sword holding posture and sword drawing speed, and constructing a swordplay action standard evaluation model based on a convolutional neural network (CNN). The input is the time series data of the angle and speed of the motion sensor in three directions in space, the time length is the standard execution time of each action, and the output is a score of 0 to 1. The closer the score is to 1, the more standard the action is.

Images