CN111898487A - Human motion mode real-time identification method of flexible exoskeleton system - Google Patents
Human motion mode real-time identification method of flexible exoskeleton system Download PDFInfo
- Publication number
- CN111898487A CN111898487A CN202010678052.XA CN202010678052A CN111898487A CN 111898487 A CN111898487 A CN 111898487A CN 202010678052 A CN202010678052 A CN 202010678052A CN 111898487 A CN111898487 A CN 111898487A
- Authority
- CN
- China
- Prior art keywords
- mode
- human
- exoskeleton system
- flexible exoskeleton
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/0028—Force sensors associated with force applying means
Abstract
The invention discloses a real-time human motion mode identification method of a flexible exoskeleton system, which comprises the following steps: the flexible exoskeleton system acquires human body posture information and human-ground interaction force information in real time; setting an initial state of a human motion mode of the flexible exoskeleton system at an initial moment; the flexible exoskeleton system judges a human body motion mode which is possibly switched at the current moment according to the human body motion mode at the previous moment, then judges the identification condition of the human body motion mode switching according to the obtained human body posture signal and the human-ground interaction force signal at the current moment, and finally obtains the identification result of the human body motion mode at the current moment. The invention relates to a method for judging whether the state recognition condition of a human motion mode is satisfied or not by utilizing a state switching model and real-time measurement data of an exoskeleton system sensor, and obtaining a human motion mode recognition result in real time.
Description
Technical Field
The invention relates to the technical field of exoskeleton systems, in particular to a real-time human motion mode identification method of a flexible exoskeleton system.
Background
The exoskeleton system is a typical man-machine intelligent system, and combines the load bearing capacity of a machine and the advantages of free guidance of a human body, so that good cooperativity between the man and the machine is required to ensure the comfort of human body movement while realizing high-efficiency assistance.
The human motion pattern recognition technology is one of key technologies of the exoskeleton technology, plays a key role in cooperative control and flexible assistance of an exoskeleton system, and is characterized in that the motion pattern of a human body is calculated and estimated according to human posture information, human-computer interaction force information and human-ground interaction force information. The movement modes of a person in daily life mainly include standing, squatting, walking, running, jumping and other modes. For different motion modes, the muscle work doing mode and the skeleton force transmission mode of the human body are different. Therefore, the real-time recognition of the human motion mode has important significance on the wearing comfort and the walking flexibility of the exoskeleton system.
The traditional exoskeleton system is high in rigidity, a model is obtained by performing machine learning training on human-computer interaction force information and human posture information, and then pattern classification is obtained by performing model matching by using online data. However, for the flexible exoskeleton system, in order to improve wearing comfort and walking flexibility, the joints are designed by adopting a flexible connection technology, and human-computer interaction force information cannot be obtained. In addition, the machine learning method needs to perform learning training on sample data, and different people have different motion postures, large sample amount and difficult collection. In addition, when the pattern matching is performed online, data in a time period needs to be judged, the data calculation amount is large, the pattern matching result has time delay, and the real-time requirement of the exoskeleton system cannot be met. And the machine learning method has high complexity, needs a high-requirement hardware platform, and has very high application difficulty and cost.
In general, in the human motion mode real-time identification method of the traditional exoskeleton system, data acquisition is difficult, the motion postures, motion habits, body states and the like of different people are possibly different, the acquisition workload of sample data is huge, and the completion of different people is difficult; the real-time performance of the recognition result is difficult to guarantee, the recognition result is always delayed for a period of time, and the real-time performance of the recognition result is difficult to guarantee; the algorithm is complex, the application is difficult, the algorithm of machine learning is generally difficult, the calculation amount and the algorithm complexity are huge, and the requirement on a hardware platform in the application process is very high, so that the inconvenience is brought to engineering application.
Disclosure of Invention
Based on the above problems, the present invention aims to provide a real-time human motion pattern recognition method for a flexible exoskeleton system, which mainly solves the technical problem that the human motion pattern recognition method for the traditional exoskeleton system is not suitable for human motion pattern recognition of the flexible exoskeleton.
In order to solve the above problems, the present invention provides the following technical solutions:
the invention discloses a human motion mode real-time identification method of a flexible exoskeleton system, which is characterized by comprising the following steps of:
s1, the flexible exoskeleton system acquires human body posture information and human-ground interaction force information in real time;
s2, setting the initial state of the human motion mode of the flexible exoskeleton system at the initial moment;
s3, the flexible exoskeleton system judges the human body motion modes which can be switched at the current moment according to the human body motion modes at the previous moment, then judges the identification conditions of the human body motion mode switching according to the obtained human body posture signals and human-ground interaction force signals at the current moment, and finally obtains the results of the human body motion modes at the current moment;
and S4, repeating the previous step S3, and acquiring the recognition result of the human motion pattern at each moment until the system operation is finished.
Further, IMU inertia measurement devices for acquiring the human body posture signals are arranged on the back, the thighs, the crus and the feet of the flexible exoskeleton system, and pressure sensors for acquiring the human-ground interaction force signals are arranged on the feet of the flexible exoskeleton system.
Further, the human posture signal comprises joint angles of hip, knee and ankle joints of the human body and a posture angle of feet.
Further, the human motion modes include a standing mode, a walking assistance mode, a jumping mode, a squatting mode, a running mode and a transition mode.
Further, the switching of the human motion mode comprises six conditions:
q1, the last moment is the standing mode, and the flexible exoskeleton system respectively and sequentially judges the recognition condition of the squatting mode, the recognition condition of the jumping mode and the recognition condition of the standing mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q2, the last moment is the walking assisting mode, and the flexible exoskeleton system randomly and respectively judges the recognition condition of the standing mode, the recognition condition of the jumping mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q3, the last moment is the jumping mode, and the flexible exoskeleton system judges the identification condition of the standing mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q4, the last moment is the squatting mode, and the flexible exoskeleton system randomly and respectively judges the identification conditions of the standing mode and the jumping mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q5, the last moment is the running mode, and the flexible exoskeleton system respectively and sequentially judges the recognition condition of the standing mode, the recognition condition of the jumping mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
and Q6, the last moment is the transition mode, and the flexible exoskeleton system respectively judges the recognition condition of the squatting mode, the recognition condition of the jumping mode, the recognition condition of the standing mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
Further, the identification condition of the standing mode is as follows:
a. one of the feet of the flexible exoskeleton system is determined to be supported on the ground, i.e., the human-ground interaction force signal requiring the left foot or the right foot is greater than the set foot pressure threshold;
b. a change in a sole IMU measurement of the flexible exoskeleton system over a period of time is less than a set foot stance angle threshold;
c. a knee angle of the flexible exoskeleton system is less than a set knee angle threshold;
and if the three conditions are simultaneously met, the identification condition of the standing mode is reached.
Further, the identification conditions of the squatting mode are as follows:
a. the knee joint angles of the two legs of the flexible exoskeleton system are simultaneously greater than the set knee joint angle threshold, and the duration is greater than the set time threshold;
b. at least one of the feet of the flexible exoskeleton system is judged to be supported on the ground, i.e., the human-ground interaction force signal requiring the left foot or the right foot is greater than the set foot pressure threshold and the duration is greater than the set time threshold;
c. the last moment is the standing mode or the transition mode;
and if the three conditions are simultaneously met, the identification condition of the standing mode is reached.
Further, the recognition conditions of the skip mode are as follows:
the two feet of the flexible exoskeleton system leave the ground at the same time, namely, the man-machine interaction force signals of the left foot and the right foot are required to be smaller than the set foot pressure threshold at the same time, and the duration is longer than the set time threshold;
and if the condition is met, the recognition condition of the skip mode is reached.
Further, the running mode is identified by the following conditions:
a. the last moment is the standing mode, the transition mode or the walking assistance mode;
b. detecting that the duration of the support state in one gait cycle is less than a set time threshold;
and if the two conditions are met, the recognition condition of the running mode is reached.
Further, the identification condition of the transition mode is as follows:
a. the last moment is the standing mode;
b. one of the feet of the flexible exoskeleton system is off the ground at the current moment, i.e., the human-ground interaction force signal of the left foot or the right foot is required to be smaller than the set foot pressure threshold.
And if the two conditions are simultaneously met, the recognition condition of the transition mode is reached.
Further, the identification condition of the walking assistance mode is as follows: and when the identification conditions of the standing mode, the transition mode, the squatting mode, the jumping mode and the running mode are not met, judging as the walking assisting mode.
Further, the processor of the flexible exoskeleton system performs smooth filtering processing on the human body posture signal and the human-ground interaction force signal to eliminate noise and jitter influence.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a human motion mode real-time identification method of a flexible exoskeleton system, which judges whether a state identification condition of a human motion mode is satisfied or not by utilizing a state switching algorithm and real-time measurement data of an exoskeleton system sensor, obtains a human motion mode identification result in real time, is simple in method, convenient to apply, free of time delay of the identification result, and realizes engineering application of human motion mode identification.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a general block diagram of the flexible exoskeleton system of the present invention;
FIG. 2 is a flow chart of the human movement pattern recognition for the flexible exoskeleton system of the present invention;
FIG. 3 is a flow chart of the switching of the human body exercise mode under the condition that the standing mode is adopted at the last moment;
FIG. 4 is a flow chart of switching human body movement modes under the condition that the last moment is a walking assisting mode according to the present invention;
FIG. 5 is a flow chart of switching human body movement modes under the situation of jumping mode at the previous moment according to the present invention;
FIG. 6 is a flow chart of switching of human body exercise modes in the case of squat mode at the previous moment according to the present invention;
FIG. 7 is a flow chart of switching human body exercise mode in the case of running mode at the previous moment according to the present invention;
FIG. 8 is a flow chart of switching human body movement modes in the case of transition mode at the previous moment according to the present invention;
reference numerals:
1. a back; 2. a thigh; 3. a lower leg; 4. a foot section; 5. a Bowden wire; 6. a back frame; 7. binding bands; 8. a drive system.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1 to 2, the present embodiment discloses a method for real-time identifying human motion patterns of a flexible exoskeleton system, which comprises the following steps:
s1, the flexible exoskeleton system acquires human body posture information and human-ground interaction force information in real time;
s2, setting the initial state of the human motion mode of the flexible exoskeleton system at the initial moment;
s3, the flexible exoskeleton system judges the human body motion modes which can be switched at the current moment according to the human body motion modes at the previous moment, then judges the identification conditions of the human body motion mode switching according to the obtained human body posture signals and human-ground interaction force signals at the current moment, and finally obtains the results of the human body motion modes at the current moment;
and S4, repeating the previous step S3, and acquiring the recognition result of the human motion pattern at each moment until the system operation is finished.
As shown in fig. 1, a driving system 8 of the flexible exoskeleton system is installed on a back frame 6 and is connected with a shank 3 of the flexible exoskeleton system through a bowden cable 5, a part of the bowden cable 5 is inserted into a bowden cable sleeve, one end of the bowden cable sleeve is fixed on the driving system 8, the other end of the bowden cable sleeve is fixed on a thigh 2, and the driving system 8 realizes assistance and unloading of a knee joint through the retraction and release of the bowden cable 5, so that the flexible cooperative assistance control of a human body is realized.
The tension sensor is mounted on the shank 3 of the flexible exoskeleton system for measuring the torque output feedback of the drive system 8. An angular displacement sensor is arranged in the driving system 8 and used for measuring the position output feedback of the flexible exoskeleton system; the IMU inertia measurement devices are arranged on the back 1, the thighs 2, the shanks 3 and the feet 4 of the flexible exoskeleton system to acquire human posture information, and the pressure sensors are arranged on the feet 4 of the flexible exoskeleton system to acquire human-ground interaction force information.
For the mounting mode of the IMU inertia measurement device, specifically, a certain axis direction of the IMU inertia measurement device is the same as a sagittal axis of a human body, in the embodiment, the axis direction is an X axis direction, and an angle measurement range of the IMU inertia measurement device is 0-360 °. The human posture signal comprises the angle values of hip, knee and ankle joints of the human body and the posture angle of the foot. Specifically, in the standing state, the hip joint angle is defined as 90 °, the knee joint angle is defined as 0 °, the ankle joint angle is defined as 90 °, the hip joint angle is increased by swinging the thigh forward, the knee joint angle is increased by bending the knee, the toe of the foot is tilted upward, the ankle joint angle is decreased, and the foot posture angle is decreased. The foot posture angle is 180 degrees in a standing state, the toe is lifted upwards, the angle is increased, the toe is pressed downwards, and the angle is reduced.
The IMU inertia measurement device and the pressure sensor are arranged on an exoskeleton system, are bound on a human body through a flexible weaving technology, move along with the human body, measure human body posture information and human-ground interaction force information in real time, send detected signals to a processor of the flexible exoskeleton system through a bus transmission mode, and carry out smooth filtering and angle calculation on the signals by the processor. The processor of the flexible exoskeleton system carries out smooth filtering processing on human body posture signals and human-ground interaction force signals, and aims to eliminate noise influence.
Under the condition that a human body is in different motion modes, the human body posture angle information and the human-ground interaction force are different, and the processor of the flexible exoskeleton system extracts the motion mode characteristics according to the detected human body posture signal and the human-ground interaction force signal to switch the modes.
The human motion mode comprises a standing mode, a transition mode, a walking assistance mode, a squatting mode, a jumping mode and a running mode. The walking assisting mode comprises flat ground walking, stair ascending and descending and slope ascending and descending. In this embodiment, when the system first determines to switch the human motion mode state, the initial state of the human motion mode at the initial time is set to the standing mode.
As shown in fig. 3 to 8, the switching of the human motion mode includes six cases:
and Q1, as shown in fig. 3, the previous moment is a standing mode, and the flexible exoskeleton system respectively and sequentially judges the recognition condition of the squatting mode, the recognition condition of the jumping mode and the recognition condition of the standing mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
The determination sequence is: firstly, judging the identification condition of the squatting mode, and if the identification condition is met, switching to the squatting mode; if the skip mode is not met, then judging the identification condition of the skip mode, and if the identification condition is met, switching to the skip mode; and if the identification condition is not met, finally judging the identification condition of the standing mode, if the identification condition is met, continuously keeping the standing mode, and if the identification condition is not met, switching to a transition mode.
And Q2, as shown in fig. 4, the previous moment is a walking assistance mode, and the flexible exoskeleton system randomly and respectively judges the identification condition of the standing mode, the identification condition of the jumping mode and the identification condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
There is no explicit requirement for the determination order, and the determination order in this embodiment is: firstly, judging the identification condition of a standing mode, if so, switching to the standing mode, if not, then judging the identification condition of a jumping mode, if so, switching to the jumping mode, if not, finally judging the identification condition of a running mode, if so, switching to the running mode, and if not, keeping the walking assistance mode.
Q3, as shown in fig. 5, the previous time is the jumping mode, the flexible exoskeleton system determines the standing mode identification condition according to the human body posture signal and the human-ground interaction force signal acquired at the current time, if yes, the flexible exoskeleton system switches to the standing mode, and if not, the flexible exoskeleton system maintains the jumping mode.
And Q4, as shown in figure 6, the last moment is in a squatting mode, and the flexible exoskeleton system randomly and respectively judges the standing mode and the jumping mode recognition conditions according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
The order of identification is not explicitly required, and in the present embodiment, the order is: firstly, judging the identification condition of the standing mode, if so, switching to the standing mode, if not, then judging the identification condition of the jumping mode, if so, switching to the jumping mode, and if not, continuing to maintain the squatting mode.
Q5, as shown in fig. 7, the previous time is the running mode, and the sexual exoskeleton system sequentially and respectively determines the identification condition of the standing mode, the identification condition of the jumping mode and the identification condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current time.
The order of the determination is: firstly, judging the identification condition of a standing mode, if so, switching to the standing mode, if not, then judging the identification condition of a jumping mode, if so, switching to the jumping mode, if not, finally judging the identification condition of a running mode, if not, switching to a walking assisting mode, and if so, keeping the running mode.
And Q6, as shown in FIG. 8, the previous moment is a transition mode, and the flexible exoskeleton system randomly determines the recognition conditions of the squatting mode, the jumping mode, the standing mode and the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
The identification order is not explicitly required, and the determination order in the embodiment is: firstly, judging the identification condition of the squatting mode, and if the identification condition is met, switching to the squatting mode; if the skip mode is not satisfied, judging the recognition condition of the skip mode, and if the recognition condition is satisfied, switching to the skip mode; if the identification condition is not met, judging the identification condition of the standing mode, and if the identification condition is met, switching to the standing mode; if the running mode is not satisfied, the recognition condition of the running mode is judged, if the running mode is satisfied, the running mode is switched to, and if the running mode is not satisfied, the running mode is switched to the walking assisting mode.
The recognition conditions of the standing mode are as follows:
a. one of the feet of the flexible exoskeleton system is determined to be supported on the ground, i.e., the human-ground interaction force signal requiring either the left foot or the right foot is greater than the set foot pressure threshold, which in this embodiment is 3 kilograms.
b. The change of the measured value of the sole IMU of the flexible exoskeleton system in a period of time is smaller than the set foot posture angle threshold value, namely the posture of the foot is required to have no obvious change in the period of time. In this embodiment, the IMU measurements for both the left and right feet each vary by less than 10 degrees.
c. The knee angle of the flexible exoskeleton system is less than the set knee angle threshold, in this embodiment, both the left and right knee angles are less than 15 degrees,
and if the three conditions are required to be met simultaneously, the identification condition of the standing mode is achieved.
The recognition conditions of the squatting mode are as follows:
a. the knee joint angles of the two legs of the flexible exoskeleton system are simultaneously larger than the set knee joint angle threshold, and the duration is longer than the set time threshold, so that the two legs are required to simultaneously keep the knee bending state. In this embodiment, the left and right knee angles are each greater than 45 degrees and the duration is greater than 50 milliseconds.
b. At least one of the feet of the flexible exoskeleton system is judged to be supported on the ground and has a duration greater than a set time threshold, in this embodiment, the plantar pressure sensor measurement of the left or right foot is greater than 3 kilograms and the duration is greater than 50 milliseconds.
c. The last moment is in a standing mode or a transition mode, and other modes cannot be switched.
And if the three conditions are simultaneously met, the identification condition of the standing mode is reached.
Recognition conditions of the skip mode: the two feet of the flexible exoskeleton system leave the ground at the same time, namely, the man-machine interaction force signals of the left foot and the right foot are required to be smaller than the set foot pressure threshold at the same time, the duration is longer than the set time threshold, and in the embodiment, the sole pressure test quantity of the left foot or the right foot is smaller than 3 kilograms.
The running mode is identified by the following conditions:
a. the last moment is the standing mode, the transition mode or the walking assisting mode, and other modes are not switched.
b. And detecting that the duration of the support state in one gait cycle is less than a set time threshold, namely the duration of the support state in one gait cycle is less than 0.35 second.
The recognition conditions of the transition mode are as follows:
a. the last moment is the standing mode.
b. One of the feet of the flexible exoskeleton system leaves the ground at the present moment, namely, the human-ground interaction force signal of the left foot or the right foot is required to be smaller than the set foot pressure threshold value, and in the embodiment, the sole pressure of the left foot or the right foot is smaller than 3 kilograms.
The identification conditions of the walking assistance mode are as follows: and when the recognition conditions of the standing mode, the transition mode, the squatting mode, the jumping mode and the running mode are not met, judging as the walking assisting mode.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (12)
1. A human motion mode real-time identification method of a flexible exoskeleton system is characterized by comprising the following steps:
s1, the flexible exoskeleton system acquires human body posture information and human-ground interaction force information in real time;
s2, setting the initial state of the human motion mode of the flexible exoskeleton system at the initial moment;
s3, the flexible exoskeleton system judges the human body motion modes which can be switched at the current moment according to the human body motion modes at the previous moment, then judges the identification conditions of the human body motion mode switching according to the obtained human body posture signals and human-ground interaction force signals at the current moment, and finally obtains the results of the human body motion modes at the current moment;
and S4, repeating the previous step S3, and acquiring the recognition result of the human motion pattern at each moment until the system operation is finished.
2. The method of claim 1, wherein IMU inertial measurement units for acquiring the body posture signals are mounted on the back, thigh, calf and foot of the flexible exoskeleton system, and pressure sensors for acquiring the human-ground interaction force signals are mounted on the foot of the flexible exoskeleton system.
3. The method for real-time identification of human motion patterns for a flexible exoskeleton system of claim 1 wherein the human stance signals include joint angles and foot stance angles of the hips, knees and ankles of the human body.
4. The method for real-time identification of human motion patterns for a flexible exoskeleton system of claim 3 wherein the human motion patterns include a standing mode, a transition mode, a walking assist mode, a squat mode, a jump mode and a running mode.
5. The method of real-time human motion pattern recognition of a flexible exoskeleton system of claim 4 wherein the switching of human motion patterns comprises:
q1, the last moment is the standing mode, and the flexible exoskeleton system respectively and sequentially judges the recognition condition of the squatting mode, the recognition condition of the jumping mode and the recognition condition of the standing mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q2, the last moment is the walking assisting mode, and the flexible exoskeleton system randomly and respectively judges the recognition condition of the standing mode, the recognition condition of the jumping mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q3, the last moment is the jumping mode, and the flexible exoskeleton system judges the identification condition of the standing mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q4, the last moment is the squatting mode, and the flexible exoskeleton system randomly and respectively judges the identification conditions of the standing mode and the jumping mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
q5, the last moment is the running mode, and the flexible exoskeleton system respectively and sequentially judges the recognition condition of the standing mode, the recognition condition of the jumping mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment;
and Q6, the last moment is the transition mode, and the flexible exoskeleton system respectively randomly and respectively judges the recognition condition of the squatting mode, the recognition condition of the jumping mode, the recognition condition of the standing mode and the recognition condition of the running mode according to the human body posture signal and the human-ground interaction force signal acquired at the current moment.
6. The method for real-time identification of human motion patterns of a flexible exoskeleton system of claim 5 wherein the identification conditions of the stance mode are:
a. one of the feet of the flexible exoskeleton system is determined to be supported on the ground, i.e., the human-ground interaction force signal requiring the left foot or the right foot is greater than the set foot pressure threshold;
b. a change in a sole IMU measurement of the flexible exoskeleton system over a period of time is less than a set foot stance angle threshold;
c. a knee angle of the flexible exoskeleton system is less than a set knee angle threshold;
and if the three conditions are simultaneously met, the identification condition of the standing mode is reached.
7. The method for real-time identification of human movement patterns of a flexible exoskeleton system as claimed in claim 5 wherein the squat pattern is identified by the following conditions:
a. the knee joint angles of the two legs of the flexible exoskeleton system are simultaneously greater than the set knee joint angle threshold, and the duration is greater than the set time threshold;
b. at least one of the feet of the flexible exoskeleton system is judged to be supported on the ground, i.e., the human-ground interaction force signal requiring the left foot or the right foot is greater than the set foot pressure threshold and the duration is greater than the set time threshold;
c. the last moment is the standing mode or the transition mode;
and if the three conditions are simultaneously met, the identification condition of the standing mode is reached.
8. The method for real-time recognition of human motion patterns of a flexible exoskeleton system of claim 5, wherein the recognition conditions of the jumping pattern are:
the two feet of the flexible exoskeleton system leave the ground at the same time, namely, the man-machine interaction force signals of the left foot and the right foot are required to be smaller than the set foot pressure threshold at the same time, and the duration is longer than the set time threshold;
and if the condition is met, the recognition condition of the skip mode is reached.
9. The method for real-time identification of human movement patterns for a flexible exoskeleton system of claim 5 wherein the identification conditions of the running pattern are:
a. the last moment is the standing mode, the transition mode or the walking assistance mode;
b. detecting that the duration of the support state in one gait cycle is less than a set time threshold;
and if the two conditions are met, the recognition condition of the running mode is reached.
10. The method for real-time recognition of human motion patterns of a flexible exoskeleton system of claim 5, wherein the recognition conditions of the transition pattern are:
a. the last moment is the standing mode;
b. one of the feet of the flexible exoskeleton system is off the ground at the current moment, i.e., the human-ground interaction force signal of the left foot or the right foot is required to be smaller than the set foot pressure threshold.
And if the two conditions are simultaneously met, the recognition condition of the transition mode is reached.
11. The method for real-time recognition of human motion patterns of a flexible exoskeleton system of claim 5, wherein the recognition conditions of the walking assistance mode are as follows: and when the identification conditions of the standing mode, the transition mode, the squatting mode, the jumping mode and the running mode are not met, judging as the walking assisting mode.
12. The method as claimed in any one of claims 1 to 11, wherein the processor of the flexible exoskeleton system performs a smoothing filtering process on the human body posture signal and the human-ground interaction force signal to remove noise and jitter effects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678052.XA CN111898487A (en) | 2020-07-15 | 2020-07-15 | Human motion mode real-time identification method of flexible exoskeleton system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678052.XA CN111898487A (en) | 2020-07-15 | 2020-07-15 | Human motion mode real-time identification method of flexible exoskeleton system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111898487A true CN111898487A (en) | 2020-11-06 |
Family
ID=73191248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010678052.XA Pending CN111898487A (en) | 2020-07-15 | 2020-07-15 | Human motion mode real-time identification method of flexible exoskeleton system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898487A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560594A (en) * | 2020-11-30 | 2021-03-26 | 贵州航天控制技术有限公司 | Human body gait recognition method of flexible exoskeleton system |
| CN112949676A (en) * | 2020-12-29 | 2021-06-11 | 武汉理工大学 | Self-adaptive motion mode identification method of flexible lower limb assistance exoskeleton robot |
| CN113041102A (en) * | 2021-03-08 | 2021-06-29 | 上海傅利叶智能科技有限公司 | Method and device for controlling exoskeleton robot and rehabilitation robot |
| CN114947825A (en) * | 2022-04-29 | 2022-08-30 | 吉林大学 | Lower limb prosthesis continuous motion recognition method based on PSOGWO-SVM |
| CN116509689A (en) * | 2023-03-13 | 2023-08-01 | 深圳睿瀚医疗科技有限公司 | Rigid-flexible hybrid knee joint rehabilitation robot |
| CN116869521A (en) * | 2023-09-07 | 2023-10-13 | 贵州航天控制技术有限公司 | Human body movement pattern real-time identification method of lower limb assistance exoskeleton system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100094188A1 (en) * | 2008-10-13 | 2010-04-15 | Amit Goffer | Locomotion assisting device and method |
| US20140142475A1 (en) * | 2010-09-27 | 2014-05-22 | Vanderbilt University | Movement assistance device |
| CN106325273A (en) * | 2016-08-22 | 2017-01-11 | 中国科学院合肥物质科学研究院 | Multi-phase gait switching control system and control method for power-assisted exoskeleton robot |
| CN111015631A (en) * | 2019-12-24 | 2020-04-17 | 上海理工大学 | Flexible exoskeleton hand-assisted grasping training control method based on finite state machine |
-
2020
- 2020-07-15 CN CN202010678052.XA patent/CN111898487A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100094188A1 (en) * | 2008-10-13 | 2010-04-15 | Amit Goffer | Locomotion assisting device and method |
| US20140142475A1 (en) * | 2010-09-27 | 2014-05-22 | Vanderbilt University | Movement assistance device |
| CN106325273A (en) * | 2016-08-22 | 2017-01-11 | 中国科学院合肥物质科学研究院 | Multi-phase gait switching control system and control method for power-assisted exoskeleton robot |
| CN111015631A (en) * | 2019-12-24 | 2020-04-17 | 上海理工大学 | Flexible exoskeleton hand-assisted grasping training control method based on finite state machine |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560594A (en) * | 2020-11-30 | 2021-03-26 | 贵州航天控制技术有限公司 | Human body gait recognition method of flexible exoskeleton system |
| CN112949676A (en) * | 2020-12-29 | 2021-06-11 | 武汉理工大学 | Self-adaptive motion mode identification method of flexible lower limb assistance exoskeleton robot |
| CN112949676B (en) * | 2020-12-29 | 2022-07-08 | 武汉理工大学 | Self-adaptive motion mode identification method of flexible lower limb assistance exoskeleton robot |
| CN113041102A (en) * | 2021-03-08 | 2021-06-29 | 上海傅利叶智能科技有限公司 | Method and device for controlling exoskeleton robot and rehabilitation robot |
| CN113041102B (en) * | 2021-03-08 | 2023-10-31 | 上海傅利叶智能科技有限公司 | Method and device for controlling exoskeleton robot and rehabilitation robot |
| CN114947825A (en) * | 2022-04-29 | 2022-08-30 | 吉林大学 | Lower limb prosthesis continuous motion recognition method based on PSOGWO-SVM |
| CN116509689A (en) * | 2023-03-13 | 2023-08-01 | 深圳睿瀚医疗科技有限公司 | Rigid-flexible hybrid knee joint rehabilitation robot |
| CN116869521A (en) * | 2023-09-07 | 2023-10-13 | 贵州航天控制技术有限公司 | Human body movement pattern real-time identification method of lower limb assistance exoskeleton system |
| CN116869521B (en) * | 2023-09-07 | 2023-11-14 | 贵州航天控制技术有限公司 | Human body movement pattern real-time identification method of lower limb assistance exoskeleton system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898487A (en) | Human motion mode real-time identification method of flexible exoskeleton system | |
| Huo et al. | Fast gait mode detection and assistive torque control of an exoskeletal robotic orthosis for walking assistance | |
| CN105796286B (en) | Use the lower limb exoskeleton robot control method of air bag sensor | |
| US20140094345A1 (en) | Active robotic gait-training system and method | |
| CN108577854A (en) | Gait recognition method and gait ancillary equipment | |
| KR102163284B1 (en) | Wearable robot and control method for the same | |
| Hassan et al. | Exoskeleton robot control based on cane and body joint synergies | |
| CN110279557A (en) | A kind of lower limb rehabilitation robot control system and control method | |
| Li et al. | Estimating system state during human walking with a powered ankle-foot orthosis | |
| CN108283564A (en) | A kind of intelligent ankle-joint exoskeleton system of light-type rope driving | |
| CN106112985B (en) | Exoskeleton hybrid control system and method for lower limb walking aid machine | |
| CN110812127B (en) | Lower limb exoskeleton control method and device | |
| CN110721055B (en) | Control method of lower limb walking aid exoskeleton robot and exoskeleton robot | |
| CN112405504B (en) | Exoskeleton robot | |
| CN113143697B (en) | Control method and device for hip joint exoskeleton | |
| He et al. | A study on lower-limb muscle activities during daily lower-limb motions | |
| CN111568700A (en) | Gait control method, device and equipment for lower limb wearable robot | |
| Yi et al. | Continuous prediction of lower-limb kinematics from multi-modal biomedical signals | |
| Yan et al. | A novel adaptive oscillators-based control for a powered multi-joint lower-limb orthosis | |
| CN112223263A (en) | Man-machine cooperation real-time control method of flexible exoskeleton system | |
| CN110123329B (en) | Intelligent mechanical frame for matching with exercise-assisted lower limb exoskeleton to adjust human body position and control method thereof | |
| JP2002355236A (en) | Method to measure joint angle using biaxial acceleration sensor and electric stimulator | |
| Fleischer et al. | Embedded control system for a powered leg exoskeleton | |
| CN112560594A (en) | Human body gait recognition method of flexible exoskeleton system | |
| Liu et al. | Joint kinematics, kinetics and muscle synergy patterns during transitions between locomotion modes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |