An exoskeleton gait detection method based on multi-point calibration and wearable device

Abstract

The present invention provides an exoskeleton gait detection method and wearable device based on multi-point calibration. The method includes continuously acquiring the angle values ​​of the user's left and right hip joints during movement. Based on the acquired left and right hip joint angle values, two waveforms are used to represent the gait of the left and right hip joints, respectively. The user's gait cycle is divided based on the gait waveform of the left hip joint and the gait waveform of the right hip joint. A preset number of gait cycles are recorded. The gait waveform of the left hip joint and the gait waveform of the right hip joint containing the recorded gait cycles are fitted to form a fitted waveform to complete exoskeleton gait detection. The method proposed in the present invention achieves motion detection through multi-point calibration, eliminating the need for prediction algorithms based on scene judgment, pattern recognition, etc. in the prior art. The total amount of data required to be collected is small, the computational complexity is low, and false alarms are less likely to occur. At the same time, it has the advantages of low cost and high real-time performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of motion analysis, and in particular relates to an exoskeleton gait detection method based on multi-point calibration and a wearable device. Background Art

[0002] Gait refers to the posture and behavioral characteristics of the human body when walking. It is the process of moving the body in a certain direction through a series of continuous movements of the hips, knees, ankles, and toes. Gait involves factors such as behavioral habits, occupation, education, age, and gender, and is also affected by various diseases. The control of walking is very complex, including central commands, body balance and coordination control, involving the coordinated movement of the joints and muscles of the lower limbs, and is also related to the posture of the upper limbs and trunk. Disorders in any link may affect gait, and abnormalities may be compensated or masked. Normal gait is stable, periodic and rhythmic, directional, coordinated, and individual.

[0003] Gait analysis is an examination method for studying walking patterns. It aims to reveal the key links and influencing factors of gait abnormalities through biomechanical and kinematic means, thereby guiding rehabilitation assessment and treatment. It can be applied to clinical diagnosis, efficacy evaluation, mechanism research, exercise guidance, robotics and other aspects.

[0004] The main method currently used in gait analysis is to identify gait phases using machine learning and posture information based on prediction algorithms such as scene judgment and pattern recognition. However, this method has low real-time performance, requires large amounts of collected data and computational complexity, and has complex models and algorithms. In addition, important information may be missed or misreported, and there is also a certain probability of error. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention proposes an exoskeleton gait detection method based on multi-point calibration, which includes:

[0006] Continuously obtain the angle values ​​of the user's left and right hip joints;

[0007] Based on the obtained left and right hip joint angle values, two waveforms are used to represent the gait of the left hip joint and the right hip joint respectively;

[0008] Dividing the user's gait cycles based on the gait waveform diagram of the left hip joint and the gait waveform diagram of the right hip joint, and recording a preset number of gait cycles; the recorded gait cycles do not include abnormal gaits;

[0009] The gait waveform graph of the left hip joint and the gait waveform graph of the right hip joint containing the recorded gait cycle are fitted to form a fitting waveform graph to complete the exoskeleton gait detection.

[0010] Specifically, abnormal gait is distinguished by comparing the gaits of the left hip joint and the right hip joint of the user. The comparison of the gaits of the left hip joint and the right hip joint of the user includes:

[0011] Calibrate at least two time points in the gait cycle when the left and right hip joints reach specific angles, use the time points in the current gait cycle and the previous gait cycle when the first specific angle and the second specific angle are reached as the first time point and the second time point, respectively, compare the timing of the first time point and the second time point in the current gait cycle and the previous gait cycle, replace at least one of the first specific angle and the second specific angle with another calibrated specific angle, and continue to compare until a preset number of time differences are compared; the previous gait cycle does not include an abnormal gait;

[0012] If the time sequence of the first time point and the second time point of the previous gait cycle is consistent with the time sequence of the first time point and the second time point of the current gait cycle, it is determined that the current gait cycle of the user does not include an abnormal gait;

[0013] If the timing of the first time point and the second time point of the previous gait cycle is inconsistent with the timing of the first time point and the second time point of the current gait cycle, it is determined that the current gait cycle of the user includes an abnormal gait.

[0014] Furthermore, the comparison of the gait of the left hip joint and the right hip joint of the user further includes:

[0015] For the same hip joint, the first time point and the second time point are selected, and the time difference between the first time point and the second time point in the current gait cycle and the previous gait cycle is compared;

[0016] If the difference between the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset first error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0017] If the difference between the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle exceeds the first error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

[0018] Preferably, the comparison of the gait of the left hip joint and the right hip joint of the user further includes:

[0019] The time difference between the first time point when the left hip joint reaches the first specific angle and the second time point when the left hip joint reaches the second specific angle is set as the first time difference, and the time difference between the first time point when the right hip joint reaches the first specific angle and the second time point when the right hip joint reaches the second specific angle is set as the second time difference;

[0020] If the difference between the first time difference and the second time difference does not exceed a preset second error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0021] If the difference between the first time difference and the second time difference exceeds the second error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

[0022] Optionally, the time points at which the left and right hip joints reach specific angles during any gait cycle include:

[0023] The time points when the left and right hip joints reached their maximum angle values ​​respectively;

[0024] The time points when the left and right hip joints reached the minimum angle values ​​respectively;

[0025] The point in time when both the left and right hip joints reach the same angle value.

[0026] Preferably, the method further comprises:

[0027] If the current gait cycle of the user is the user's first gait cycle, the method for determining whether the current gait cycle includes an abnormal gait includes:

[0028] Calibrate at least two time points in the current gait cycle when the left and right hip joints reach specific angles. For the same hip joint, use the time points in the current gait cycle and a preset standard gait cycle when the first specific angle and the second specific angle reach the same angle as the first time point and the second time point, respectively. After comparing the time difference between the first time point and the second time point in the current gait cycle and the standard gait cycle, replace at least one of the first specific angle and the second specific angle with another calibrated specific angle and continue the comparison until the preset number of time differences are compared.

[0029] If the difference between the time difference between the first time point and the second time point of the standard gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset third error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0030] If the difference between the time difference between the first time point and the second time point of the standard gait cycle and the time difference between the first time point and the second time point of the current gait cycle exceeds the third error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

[0031] Preferably, the method further comprises:

[0032] If the current gait cycle of the user is not the user's first gait cycle, and the gait cycles before the current gait cycle of the user all contain abnormal gaits, the current gait cycle of the user is set as the user's first gait cycle.

[0033] Furthermore, the method further comprises:

[0034] If it is determined that the first gait cycle does not include an abnormal gait, the waveform of the first gait cycle is replaced by the waveform of the standard gait cycle.

[0035] Specifically, fitting the gait waveform graph of the left hip joint and the gait waveform graph of the right hip joint containing the recorded gait cycle to form a fitting waveform graph to complete the exoskeleton gait detection includes:

[0036] Different weights are assigned to the maximum angle values ​​of the left and right hip joints, the minimum angle values ​​of the left and right hip joints, and the waveform effective values ​​of the gait waveform graphs of the left and right hip joints;

[0037] Based on the assigned weights, at least one of the waveforms of the gait waveform diagrams of the left and right hip joints is vertically translated to superimpose the waveforms of the gait waveform diagrams of the left and right hip joints to form a superimposed waveform; the waveform intersection of the superimposed waveform is the time point when the left hip joint and the right hip joint reach the same angle value;

[0038] The fitting waveform graph is obtained by vertically translating the waveform intersection of the superimposed waveform to the horizontal coordinate axis of the coordinate system to complete the exoskeleton gait detection.

[0039] The present invention also proposes a wearable device for wearing on the left and right hip joints of a user to implement the exoskeleton gait detection method based on multi-point calibration as described above. The wearable device includes a sensing device and a prompting device. The sensing device is used to continuously obtain the angle values ​​of the left and right hip joints of the user when they move. The prompting device is used to prompt the user when the user's gait is abnormal.

[0040] The present invention has at least the following beneficial effects:

[0041] The exoskeleton gait detection method based on multi-point calibration proposed in the present invention does not require the use of prediction algorithms based on scene judgment, pattern recognition, etc. in the existing technology, and is not affected by scene factors. The detection method has a simple and uncomplicated process, high real-time performance, and low computational complexity. Therefore, missed reports, false reports, and large errors are extremely rare, and the cost required to implement the method is low.

[0042] Furthermore, the exoskeleton gait detection method based on multi-point calibration proposed in the present invention can flexibly adapt to the needs of different users according to weight distribution, and can enable users to achieve self-calibration when using it for the first time through a preset standard gait cycle. At the same time, users can also save the data of their normal gait cycle as a standard gait cycle for use as a standard gait cycle next time.

[0043] Therefore, the present invention provides an exoskeleton gait detection method and wearable device based on multi-point calibration. The method proposed in the present invention realizes motion detection through multi-point calibration, and does not need to use the prediction algorithms based on scene judgment, pattern recognition, etc. in the existing technology. The total amount of data to be collected is small, the amount of calculation is not large, and it is not easy to have missed reports or false alarms. At the same time, it also has the advantages of low cost, high real-time performance and small error. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A schematic diagram of the process of the exoskeleton gait detection method based on multi-point calibration provided in Example 1;

[0046] Figure 2 A schematic diagram of a process for forming a fitting waveform diagram;

[0047] Figure 3 Schematic diagram of the gait waveforms of the left and right hip joints before fitting;

[0048] Figure 4 This is a schematic diagram of the superposition of the gait waveforms of the left and right hip joints. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] Hereinafter, various embodiments of the present invention will be described more fully. The present invention can have various embodiments, and modifications and variations can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present invention to the specific embodiments disclosed herein, but rather that the present invention should be construed to encompass all modifications, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of the present invention.

[0051] Hereinafter, the terms "include" or "may include" used in various embodiments of the present invention indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present invention, the terms "include", "have" and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be understood as excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing.

[0052] In various embodiments of the present invention, the expression "or" or "at least one of A or / and B" includes any or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0053] The expressions (such as "first", "second", etc.) used in the various embodiments of the present invention may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used to distinguish one element from other elements. For example, a first user device and a second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present invention, a first element may be referred to as a second element, and similarly, a second element may also be referred to as a first element.

[0054] It should be noted that, in the present invention, unless otherwise expressly specified or defined, terms such as "mounted," "connected," and "fixed" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in the present invention based on specific circumstances.

[0055] In the present invention, those skilled in the art need to understand that the terms indicating orientation or positional relationships herein are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0056] The terms used in various embodiments of the present invention are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the present invention. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as those of ordinary skill in the art generally understood by the various embodiments of the present invention. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having idealized meaning or too formal meaning, unless clearly defined in various embodiments of the present invention.

[0057] Example 1

[0058] This embodiment proposes an exoskeleton gait detection method based on multi-point calibration. The multi-point calibration realizes motion detection without using the prediction algorithms based on scene judgment, pattern recognition, etc. in the existing technology. The total amount of data required to be collected is small, the amount of calculation is not large, and it is not easy to miss or report false alarms. At the same time, it has the advantages of low cost and high real-time performance. Figure 1 , the exoskeleton gait detection method based on multi-point calibration includes:

[0059] S100: Continuously obtain angle values ​​of the user's left and right hip joints during movement.

[0060] In this embodiment, the angle values ​​of the left and right hip joints during movement are detected by encoders connected to the linkage mechanisms installed at the user's left and right hip joints. When the user's left and right hip joints move, the linkage mechanisms installed at the user's left and right hip joints move synchronously. The movement of the linkage mechanisms is correlated with the movement of the user's left and right hip joints. Therefore, the encoder can obtain the angle values ​​of the user's left and right hip joints during movement based on the movement of the linkage mechanisms.

[0061] It should be noted that an encoder is a device that compiles and converts signals (such as bit streams) or data into a signal form that can be used for communication, transmission and storage.

[0062] S200: Based on the acquired left and right hip joint angle values, two waveform graphs are used to represent the gait of the left hip joint and the right hip joint respectively.

[0063] Specifically, please refer to Figure 2 The gait waveforms for the left and right hip joints are plotted with time as the horizontal axis and the angle values ​​of the left and right hip joints as the vertical axis. After using waveforms to represent the movements of the left and right hip joints, both the left and right hip joint gait waveforms resemble regular waveforms similar to sine and cosine waves.

[0064] S300: Dividing the user's gait cycles based on the gait waveform diagram of the left hip joint and the gait waveform diagram of the right hip joint, and recording a preset number of gait cycles; the recorded gait cycles do not include abnormal gaits.

[0065] In this embodiment, the gaits of three complete gait cycles are recorded. For example, if the first gait cycle, the second gait cycle, and the third gait cycle do not contain abnormal gaits, the gaits of the first, second, and third gait cycles are recorded as the gaits of the three complete gait cycles;

[0066] If the second gait cycle and the fourth gait cycle contain abnormal gaits, and the first gait cycle, the third gait cycle, and the fifth gait cycle do not contain abnormal gaits, the gaits of the first, third, and fifth gait cycles are recorded as the gaits of three complete gait cycles.

[0067] It should be noted that this embodiment shows the situation of recording three complete gait cycles, but it cannot be understood as a limitation on the number of recorded gait cycles. The number of recorded gait cycles can be adjusted according to the user's actual movement process and other needs, for example, recording more than three or less than three gait cycles.

[0068] S400: Fitting the gait waveform of the left hip joint and the gait waveform of the right hip joint containing the recorded gait cycle to form a fitting waveform to complete the exoskeleton gait detection.

[0069] Specifically, abnormal gait is distinguished by abnormality determination. In this embodiment, abnormality determination is achieved by comparing the gaits of the left hip joint and the right hip joint of the user. The comparison of the gaits of the left hip joint and the right hip joint of the user includes:

[0070] Calibrate the time points at which the left and right hip joints reach specific angles in the gait cycle, use the time points at which the first specific angle and the second specific angle are reached in the current gait cycle and the previous gait cycle as the first time point and the second time point, respectively, compare the timing of the first time point and the second time point in the current gait cycle and the previous gait cycle, and then replace at least one of the first specific angle and the second specific angle with another calibrated specific angle and continue the comparison until a preset number of time differences are compared;

[0071] If the time sequence of the first time point and the second time point of the previous gait cycle is consistent with the time sequence of the first time point and the second time point of the current gait cycle, it is determined that the user's current gait cycle does not include an abnormal gait;

[0072] If the timing of the first time point and the second time point of the previous gait cycle is inconsistent with the timing of the first time point and the second time point of the current gait cycle, it is determined that the current gait cycle of the user includes an abnormal gait.

[0073] Furthermore, the comparison of the gait of the user's left hip joint and right hip joint also includes:

[0074] For the same hip joint, the first time point and the second time point are selected, and the time difference between the first time point and the second time point in the current gait cycle and the previous gait cycle is compared;

[0075] If the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset first error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0076] If the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle exceeds a first error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

[0077] Preferably, the comparison of the gait of the user's left hip joint and right hip joint further includes:

[0078] The time difference between the first time point when the left hip joint reaches the first specific angle and the second time point when the left hip joint reaches the second specific angle is set as the first time difference, and the time difference between the first time point when the right hip joint reaches the first specific angle and the second time point when the right hip joint reaches the second specific angle is set as the second time difference;

[0079] If the difference between the first time difference and the second time difference does not exceed a preset second error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0080] If the difference between the first time difference and the second time difference exceeds the second error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

[0081] It should be noted that the number of time points at which the left and right hip joints reach specific angles during any gait cycle that are calibrated is at least two; optionally, the time points at which the left and right hip joints reach specific angles during any gait cycle that are calibrated include:

[0082] The time points when the left and right hip joints reached their maximum angle values ​​respectively;

[0083] The time points when the left and right hip joints reached the minimum angle values ​​respectively;

[0084] The point in time when both the left and right hip joints reach the same angle value.

[0085] It should be noted that the changes in the amplitude of the user's left and right legs can be known through the angle values ​​of the left and right hip joints. The time points when the left hip joint and the right hip joint reach the maximum angle values ​​mentioned above are respectively the time points when the leg raising amplitudes of the left and right legs are the highest; the time points when the left hip joint and the right hip joint reach the minimum angle values ​​mentioned above are respectively the time points when the leg raising amplitudes of the left and right legs are the lowest; the time points when the left hip joint and the right hip joint reach the same angle values ​​are respectively the time points when the leg raising amplitudes of the left and right legs are the same.

[0086] It should also be noted that if the user's left and right hip joints are moving in the form of walking or running, the time point when the left hip joint and the right hip joint reach the same angle value, that is, the time point when the left and right legs are raised with the same amplitude, can be regarded as the user being in a standing state or an approximate standing state. Therefore, this time point can also be referred to as the "zero position", which is the starting position of a complete gait cycle of the user, that is, the starting position of the waveform of a gait cycle of the gait waveform diagram of the user's left and right hip joints.

[0087] In this embodiment, the time points at which the left and right hip joints reach specific angles include the time points at which the left hip joint and the right hip joint reach their maximum angle values, and the time points at which the left hip joint and the right hip joint reach their minimum angle values, respectively.

[0088] Please refer again Figure 2 , wherein the peaks of the gait waveform graph of the left hip joint and the gait waveform graph of the right hip joint are the time points when the left hip joint and the right hip joint reach the maximum angle values, and the troughs of the gait waveform graph of the left hip joint and the right hip joint are the time points when the left hip joint and the right hip joint reach the minimum angle values.

[0089] In this embodiment, under the premise that five time points are calibrated within a gait cycle, after comparing the five calibrated time points in pairs, there are a total of 10 groups of time differences when the left and right hip joints reach specific angles, which may specifically include the time difference Δt1 between the left hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value, the time difference Δt2 between the right hip joint reaching the maximum angle value and the right hip joint reaching the minimum angle value, the time difference Δt3 between the left hip joint and the right hip joint respectively reaching the maximum angle value, the time difference Δt4 between the left hip joint and the right hip joint respectively reaching the minimum angle value, etc. 10 groups of time differences are not listed one by one in this embodiment.

[0090] It should be noted that the aforementioned "selecting several groups of time differences in the previous gait cycle and comparing them with the corresponding time differences in the current gait cycle to determine whether the gait cycle contains an abnormal gait" can include a combination of any number of time differences in the above 10 groups of time differences as the benchmark time difference for determining whether the current gait cycle contains an abnormal gait. For example, the time difference Δt1 between the left hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value, the time difference Δt2 between the right hip joint reaching the maximum angle value and the right hip joint reaching the minimum angle value, the time difference Δt3 between the left hip joint and the right hip joint reaching the maximum angle value respectively, and the time difference Δt4 between the left hip joint and the right hip joint reaching the minimum angle value respectively are selected as the benchmark for determining whether the current gait cycle contains an abnormal gait. In the case where a combination of a larger number of groups of time differences is selected as the benchmark for determination, the accuracy of determining whether the user's current gait cycle contains an abnormal gait will also be higher.

[0091] It should be noted that the number of time differences that can be selected as comparison benchmarks is determined by the number of calibrated time points in each gait cycle. When the number of calibrated time points in each gait cycle is not five, the number of time differences that can be selected as comparison benchmarks will also change accordingly.

[0092] In a specific embodiment, if the movement pattern of the left and right hip joints of the user in a certain gait cycle is significantly different from the movement pattern of the left and right hip joints in the previous normal gait cycle, for example, if at least one of the differences between Δt1, Δt2, Δt3 and Δt4 of the gait cycle and Δt1, Δt2, Δt3 and Δt4 corresponding to the previous normal gait cycle exceeds a first error threshold, it can be determined that this gait cycle contains an abnormal gait.

[0093] It should be noted that the above method can be used to determine whether the user's gait is abnormal in different gait cycles. This determination is based on a comparison of the user's current gait cycle with the previous normal gait cycle, but does not include a comparison between different hip joints. In order to compare the symmetry of the left and right hip joints and prevent the situation where the user's left and right gaits have large differences, the method for determining whether a gait cycle contains an abnormal gait further includes:

[0094] Mark at least two time points during the gait cycle when the left and right hip joints reach the same specific angle, and compare the time difference between the time points when the left and right hip joints reach the same specific angle;

[0095] If the time difference between the time points at which the left and right hip joints reach the same specific angle does not exceed the preset half-step error threshold, it is determined that the user's current gait cycle does not contain abnormal gait;

[0096] If the time difference between the time points at which the left and right hip joints reach the same specific angle exceeds the half-step error threshold, it is determined that the user's current gait cycle contains an abnormal gait.

[0097] Exemplarily, the time points at which the left hip joint and the right hip joint reach the maximum angle value and the time points at which the left hip joint and the right hip joint reach the minimum angle value are calibrated within the gait cycle, and the time difference Δt1 between the left hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value and the time difference Δt2 between the right hip joint reaching the maximum angle value and the right hip joint reaching the minimum angle value are obtained, and the difference between Δt1 and Δt2 is compared to see whether it exceeds the half-step error threshold;

[0098] If the difference between Δt1 and Δt2 does not exceed the half-step error threshold, it is determined that the user's current gait cycle does not contain abnormal gait.

[0099] If the difference between Δt1 and Δt2 exceeds the half-step error threshold, it is determined that the user's current gait cycle contains an abnormal gait.

[0100] In a specific embodiment, if the user's left leg moves faster and the right leg moves slower in a certain gait cycle, and the speed difference between the left and right legs (i.e., the difference between Δt1 and Δt2 selected in this embodiment) exceeds the half-step error threshold, then it is determined that this gait cycle contains an abnormal gait.

[0101] Furthermore, in order to enable the user to determine whether the current gait cycle contains an abnormal gait when performing left and right hip joint movements for the first time, the method for determining whether the current gait cycle contains an abnormal gait also includes:

[0102] A standard gait cycle is preset. If the user's current gait cycle is the user's first gait cycle, the time difference in the current gait cycle is compared with the time difference corresponding to the standard gait cycle to determine whether the user's current gait cycle contains an abnormal gait. The specific method for determining whether the first gait cycle contains an abnormal gait includes:

[0103] Calibrate at least two time points in the current gait cycle when the left and right hip joints reach specific angles. For the same hip joint, use the time points in the current gait cycle and the preset standard gait cycle when the first specific angle and the second specific angle are reached as the first time point and the second time point, respectively. After comparing the time difference between the first time point and the second time point in the current gait cycle and the standard gait cycle, replace at least one of the first specific angle and the second specific angle with another calibrated specific angle and continue the comparison until the preset number of time differences are compared;

[0104] If the difference between the time difference between the first time point and the second time point of the standard gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset third error threshold, it is determined that the user's current gait cycle does not include an abnormal gait;

[0105] If the time difference between the first and second time points of the standard gait cycle and the time difference between the first and second time points of the current gait cycle exceeds a third error threshold, it is determined that the user's current gait cycle contains an abnormal gait.

[0106] In this way, this method can detect the user's first gait based on a pre-set gait standard, effectively avoiding the situation where an abnormal gait cannot be detected during the user's first gait cycle. In one specific embodiment, the standard gait is forward walking, and the pre-set standard gait cycle corresponds to the user's forward walking posture. If the user walks backward during the first gait cycle, the pre-set standard gait cycle can be used to detect that the user's first gait cycle contains an abnormal gait.

[0107] Furthermore, the method further comprises:

[0108] If the current gait cycle of the user is not the user's first gait cycle, and the gait cycles before the current gait cycle of the user all contain abnormal gaits, the current gait cycle of the user is set as the user's first gait cycle.

[0109] Preferably, the method further comprises:

[0110] If it is determined that the first gait cycle does not contain an abnormal gait, the waveform of the first gait cycle is replaced by the waveform of the standard gait cycle, so that when the user performs the left and right hip joints for the first time, he can judge whether the first gait cycle contains an abnormal gait through the replaced new standard gait cycle.

[0111] Furthermore, on the premise of determining the time point when the left and right hip joints that need to be calibrated reach a specific angle, and determining the time difference selected on this basis as a judgment basis for judging whether the gait cycle contains an abnormal gait, it is also possible to choose to only save the time difference data in the first gait cycle as a judgment basis for abnormal gait, as the time difference data for judging whether the first gait cycle contains an abnormal gait, so as to maximize the storage space required for saving the waveform data of the standard gait cycle.

[0112] Specifically, please refer to Figure 3 , step S400 includes:

[0113] S410: According to actual conditions, different weights are assigned to the maximum angle values ​​of the left and right hip joints, the minimum angle values ​​of the left and right hip joints, and the waveform effective values ​​of the gait waveform diagrams of the left and right hip joints.

[0114] It should be noted that the method for calculating the effective value of the waveform of the waveform diagram is a prior art and will not be described in detail in this solution. The proportion of weights assigned can be allocated according to the user's gait. For example, when the maximum amplitude that the user's left and right legs can reach when lifting their legs is relatively different, the maximum angle values ​​of the left and right hip joints will also be relatively different. In this case, the maximum angle values ​​of the left and right hip joints can be assigned a lower weight, and the minimum angle values ​​of the left and right hip joints can be assigned a higher weight to reduce the influence of the maximum angle values ​​of the left and right hip joints, so as to facilitate the superposition of the two waveforms of the gait waveform diagrams of the left and right hip joints in the subsequent steps.

[0115] S420: Based on the assigned weights, at least one of the waveforms of the gait waveforms of the left and right hip joints is vertically translated to superimpose the waveforms of the gait waveforms of the left and right hip joints to form a waveform diagram as shown in FIG. Figure 4 The superimposed waveforms are shown.

[0116] For example, in a specific embodiment, the waveform effective value of the gait waveform diagram of the left and right hip joints is assigned a weight of 100%, and the maximum angle value of the left and right hip joints and the minimum angle value of the left and right hip joints are assigned a weight of 0%. In this way, the waveforms of the gait waveform diagram of the left and right hip joints can be superimposed by simply aligning the simulation lines representing the waveform effective values ​​of the gait waveform diagram of the left and right hip joints through vertical translation.

[0117] In another embodiment, a weight of 30% is assigned to the maximum angle value of the left and right hip joints, a weight of 40% is assigned to the minimum angle value of the left and right hip joints, and a weight of 30% is assigned to the effective value of the waveform of the gait waveform diagram of the left and right hip joints. That is, based on the assigned weights, the waveforms of the gait waveform diagram of the left and right hip joints are superimposed by obtaining the optimal solution for the difference between the maximum angle, minimum angle, and effective wave value of the left and right hip joints.

[0118] S430: Obtain a fitted waveform graph by vertically translating the intersection of the superimposed waveforms onto the horizontal coordinate axis of the coordinate system to complete the exoskeleton gait detection.

[0119] It should be noted that the intersection of the superimposed waveforms is the intersection of the gait waveforms of the left and right hip joints, and is also the time point when the left hip joint and the right hip joint reach the same angle value, that is, the "zero position" mentioned in the previous article. After vertically translating the intersection of the superimposed waveforms to the horizontal coordinate axis of the coordinate system (that is, the x-axis in the coordinate system), the required fitting waveform graph can be obtained. Through this fitting waveform graph, the user's gait cycle can be better divided, and it is also convenient for users to see the overall gait during exercise more intuitively and clearly.

[0120] by Figure 4 For example, Figure 4 The t3, t′3, and t6 shown in the figure are the intersection points of the superimposed gait waveforms of the left and right hip joints. By vertically translating t3, t′3, and t6 to the x-axis, the superimposed waveform is moved to the x-axis to obtain a fitting waveform diagram.

[0121] Please refer again Figure 2 、 Figure 4 , t1 and t′1 are the time points when the right hip joint reaches the maximum angle value, t2 and t′2 are the time points when the left hip joint reaches the minimum angle value, t3, t′3, and t6 are the time points when the left and right hip joints reach the same angle value, t4 and t′4 are the time points when the left hip joint reaches the maximum angle value, and t5 and t′5 are the time points when the right hip joint reaches the minimum angle value (t′5 is not shown in the figure);

[0122] Among them, t1, t2, t3, t4, and t5 are the calibrated time points in each gait cycle, and t′1, t′2, t′3, t′4, and t′5 are the calibrated time points in the gait cycle of the second joint activity. On the premise that the first gait cycle does not contain abnormal gait, the difference between the time differences of t1 and t4, t2 and t5, t1 and t5, t2 and t4 and the corresponding time differences of t′1 and t′4, t′2 and t′5, t′1 and t′5, and t′2 and t′4 can be used to determine whether the user has an abnormal gait in the second gait cycle.

[0123] It should be noted that the time difference between t1 and t5 is the time difference Δt1 between the left hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value, and the time difference between t′1 and t′5 is the time difference Δt′1 between the left hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value; the time difference between t2 and t4 is the time difference Δt2 between the right hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value, and the time difference between t′2 and t′4 is the time difference Δt′2 between the right hip joint reaching the maximum angle value and the left hip joint reaching the minimum angle value; the time difference between t1 and t4 is the time difference Δt3 between the left and right hip joints respectively reaching the maximum angle values, and the time difference between t′1 and t′4 is the time difference Δt′3 between the left and right hip joints respectively reaching the maximum angle values; the time difference between t2 and t5 is the time difference Δt4 between the left and right hip joints respectively reaching the minimum angle values, and the time difference between t′2 and t′5 is the time difference Δt′4 between the left and right hip joints respectively reaching the minimum angle values.

[0124] If the differences between Δt1 and Δt′1, Δt2 and Δt′2, Δt3 and Δt′3, and Δt4 and Δt′4 do not exceed the first error threshold, it is determined that the user's current gait cycle does not contain an abnormal gait;

[0125] If at least one of the differences between Δt1 and Δt′1, Δt2 and Δt′2, Δt3 and Δt′3, and Δt4 and Δt′4 exceeds the first error threshold, it is determined that the user's current gait cycle contains an abnormal gait.

[0126] It should be noted that the first error threshold, the second error threshold, and the third error threshold mentioned above may be the same or different values.

[0127] It should also be noted that the method of this embodiment is applied to exoskeleton gait by detecting the hip joint movement angle, but can also be applied in the same way to activities such as ankle joint movement, knee joint movement, shoulder joint movement, elbow joint movement and wrist joint movement that require joint rotation to a certain angle.

[0128] Example 2

[0129] A wearable device is provided, which is configured to be worn at the left and right hip joints of a user to implement the exoskeleton gait detection method based on multi-point calibration as provided in Example 1, the method comprising:

[0130] S100: Continuously obtain angle values ​​of the user's left and right hip joints during movement.

[0131] S200: Based on the acquired joint angles, two waveforms are used to represent the gait of the left hip joint and the right hip joint, respectively.

[0132] S300: Dividing the user's gait cycles based on the gait waveform diagram of the left hip joint and the gait waveform diagram of the right hip joint, and recording a preset number of gait cycles; the recorded gait cycles do not include abnormal gaits.

[0133] S400: Fitting the gait waveform of the left hip joint and the gait waveform of the right hip joint containing the recorded gait cycle to form a fitting waveform to complete the exoskeleton gait detection.

[0134] Specifically, the wearable device includes a sensing device and a prompting device. The sensing device is used to continuously obtain the angle values ​​of the user's left and right hip joints when they move, and the prompting device is used to prompt the user when the user's gait is abnormal.

[0135] Furthermore, the sensing device includes a connecting rod mechanism and an encoder, and the connecting rod mechanism is provided at the left and right hip joints of the user. The angle values ​​of the left and right hip joints during movement obtained in step S100 are recognized by the encoders connected to the connecting rod mechanism provided at the left and right hip joints of the user.

[0136] When the user's left and right hip joints move, the connecting rod mechanisms set at the user's left and right hip joints will move synchronously, and the movement mode of the connecting rod mechanism is related to the movement of the user's left and right hip joints. Therefore, the encoder can obtain the angle value of the user's left and right hip joints when they move through the movement of the connecting rod mechanism.

[0137] In a specific embodiment, the wearable device proposed in this embodiment can be mounted on the left and right hip joints of the user in a complete or incomplete ring-like structure, so that the wearable device can be worn on the left and right hip joints of the user.

[0138] In summary, the present invention provides an exoskeleton gait detection method and wearable device based on multi-point calibration. The method proposed in the present invention realizes motion detection through multi-point calibration, and does not need to use the prediction algorithms based on scene judgment, pattern recognition, etc. in the existing technology. The total amount of data to be collected is small, the amount of calculation is not large, and it is not easy to have missed reports or false alarms. At the same time, it also has the advantages of low cost, high real-time performance, and small error.

[0139] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An exoskeleton gait detection method based on multi-point calibration, characterized in that: The method comprises: Continuously obtain the angle values ​​of the user's left and right hip joints; Based on the obtained left and right hip joint angle values, two waveforms are used to represent the gait of the left hip joint and the right hip joint respectively; The user's gait cycles are divided based on the gait waveform of the left hip joint and the gait waveform of the right hip joint, and a preset number of gait cycles are recorded; the recorded gait cycles do not include abnormal gaits, and abnormal gaits are distinguished by comparing the gaits of the left hip joint and the right hip joint of the user; Fitting the gait waveform graph of the left hip joint and the gait waveform graph of the right hip joint containing the recorded gait cycle to form a fitting waveform graph to complete exoskeleton gait detection; The comparison of the gait of the user's left hip joint and right hip joint includes: Calibrate at least two time points in the gait cycle when the left and right hip joints reach specific angles, use the time points in the current gait cycle and the previous gait cycle when the first specific angle and the second specific angle are reached as the first time point and the second time point, respectively, compare the timing of the first time point and the second time point in the current gait cycle and the previous gait cycle, replace at least one of the first specific angle and the second specific angle with another calibrated specific angle, and continue to compare until the time differences between a preset number of different time points are compared; the previous gait cycle does not include an abnormal gait; If the time sequence of the first time point and the second time point of the previous gait cycle is consistent with the time sequence of the first time point and the second time point of the current gait cycle, it is determined that the current gait cycle of the user does not include an abnormal gait; If the timing of the first time point and the second time point of the previous gait cycle is inconsistent with the timing of the first time point and the second time point of the current gait cycle, it is determined that the current gait cycle of the user includes an abnormal gait.

2. The exoskeleton gait detection method based on multi-point calibration according to claim 1, characterized in that: The comparison of the gait of the user's left hip joint and right hip joint further includes: selecting the first time point and the second time point for the same hip joint, and comparing the time difference between the first time point and the second time point in the current gait cycle and the previous gait cycle; If the difference between the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset first error threshold, it is determined that the user's current gait cycle does not include an abnormal gait; If the difference between the time difference between the first time point and the second time point of the previous gait cycle and the time difference between the first time point and the second time point of the current gait cycle exceeds the first error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

3. The exoskeleton gait detection method based on multi-point calibration according to claim 1, characterized in that: The comparison of the gait of the user's left hip joint and right hip joint further includes: The time difference between the first time point when the left hip joint reaches the first specific angle and the second time point when the left hip joint reaches the second specific angle is set as the first time difference, and the time difference between the first time point when the right hip joint reaches the first specific angle and the second time point when the right hip joint reaches the second specific angle is set as the second time difference; If the difference between the first time difference and the second time difference does not exceed a preset second error threshold, it is determined that the user's current gait cycle does not include an abnormal gait; If the difference between the first time difference and the second time difference exceeds the second error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

4. The exoskeleton gait detection method based on multi-point calibration according to any one of claims 1 to 3, characterized in that: The time points at which the left and right hip joints reach specific angles during any gait cycle include: The time points when the left and right hip joints reached their maximum angle values ​​respectively; The time points when the left and right hip joints reached the minimum angle values ​​respectively; The point in time when both the left and right hip joints reach the same angle value.

5. The exoskeleton gait detection method based on multi-point calibration according to claim 1, characterized in that: The method further comprises: If the current gait cycle of the user is the user's first gait cycle, the method for determining whether the current gait cycle includes an abnormal gait includes: Calibrate at least two time points in the current gait cycle when the left and right hip joints reach specific angles. For the same hip joint, use the time points in the current gait cycle and a preset standard gait cycle when the first specific angle and the second specific angle reach the same angle as the first time point and the second time point, respectively. After comparing the time difference between the first time point and the second time point in the current gait cycle and the standard gait cycle, replace at least one of the first specific angle and the second specific angle with another calibrated specific angle and continue the comparison until the preset number of time differences are compared. If the difference between the time difference between the first time point and the second time point of the standard gait cycle and the time difference between the first time point and the second time point of the current gait cycle does not exceed a preset third error threshold, it is determined that the user's current gait cycle does not include an abnormal gait; If the difference between the time difference between the first time point and the second time point of the standard gait cycle and the time difference between the first time point and the second time point of the current gait cycle exceeds the third error threshold, it is determined that the user's current gait cycle includes an abnormal gait.

6. The exoskeleton gait detection method based on multi-point calibration according to claim 5, characterized in that: The method further comprises: If the current gait cycle of the user is not the user's first gait cycle, and the gait cycles before the current gait cycle of the user all contain abnormal gaits, the current gait cycle of the user is set as the user's first gait cycle.

7. The exoskeleton gait detection method based on multi-point calibration according to claim 6, characterized in that: The method further comprises: If it is determined that the first gait cycle does not include an abnormal gait, the waveform of the first gait cycle is replaced by the waveform of the standard gait cycle.

8. The exoskeleton gait detection method based on multi-point calibration according to claim 1, characterized in that: The step of fitting the gait waveform of the left hip joint and the gait waveform of the right hip joint containing the recorded gait cycle to form a fitting waveform to complete the exoskeleton gait detection comprises: Different weights are assigned to the maximum angle values ​​of the left and right hip joints, the minimum angle values ​​of the left and right hip joints, and the waveform effective values ​​of the gait waveform graphs of the left and right hip joints; Based on the assigned weights, at least one of the waveforms of the gait waveform diagrams of the left and right hip joints is vertically translated to superimpose the waveforms of the gait waveform diagrams of the left and right hip joints to form a superimposed waveform; the waveform intersection of the superimposed waveform is the time point when the left hip joint and the right hip joint reach the same angle value; The fitting waveform graph is obtained by vertically translating the waveform intersection of the superimposed waveform to the horizontal coordinate axis of the coordinate system to complete the exoskeleton gait detection.

9. A wearable device, characterized in that: Used to be worn on the left and right hip joints of a user to implement the method described in any one of claims 1 to 8, the wearable device includes a sensing device and a prompting device, the sensing device is used to continuously obtain the angle values ​​of the left and right hip joints of the user when they move, and the prompting device is used to prompt the user when the user's gait is abnormal.

Images