Exoskeleton robots and their anomaly detection methods, devices and media

Abstract

This invention discloses an exoskeleton robot and its anomaly detection method, device, and medium. The method includes: detecting actual pressure data of the joints of the exoskeleton robot during an action cycle; determining an anomaly detection control line; based on the actual pressure data during the action cycle, calculating a minimum cumulative distance using a dynamic time adjustment algorithm; determining whether the minimum cumulative distance exceeds the anomaly detection control line; and if the minimum cumulative distance exceeds the anomaly detection control line a preset number of times over multiple action cycles, an anomaly alarm is triggered. This invention enables real-time, intelligent detection of the exoskeleton robot.

Description

Technical Field

[0001] This invention relates to the field of exoskeleton robot technology, and in particular to an exoskeleton robot and its abnormality detection method, device and medium. Background Technology

[0002] An exoskeleton robot is a wearable device typically composed of a mechanical structure, sensors, batteries, and electronic control systems. It utilizes an external structure to provide protection, support, and reinforcement to a living organism, thereby enhancing the user's mobility, protection, and adaptability. They are designed to work in conjunction with the joints and muscles of the human body to assist, enhance, or restore motor abilities. Exoskeleton robots can be used in rehabilitation therapy to help patients regain muscle function, and can also assist people with disabilities in achieving greater independence, such as helping stroke patients relearn to walk or helping patients with spinal cord injuries strengthen their muscles.

[0003] When an exoskeleton robot malfunctions, it needs to be detected and alarms triggered promptly to prevent harm to the user. The stress conditions experienced by the exoskeleton robot are a crucial performance indicator, especially at the joints, which are highly sensitive to stress. However, the stress conditions on the exoskeleton robot change over time as movements continue; furthermore, it's impossible to maintain uniform control at all times because variations in speed and timing can occur between repetitions of the same action. This makes anomaly detection in exoskeleton robots challenging. Summary of the Invention

[0004] The present invention aims to at least partially solve the technical problems in related technologies. Therefore, the first objective of the present invention is to provide an anomaly detection method for exoskeleton robots, which enables real-time and intelligent detection of the exoskeleton robot.

[0005] The second objective of this invention is to provide an anomaly detection device for an exoskeleton robot.

[0006] A third objective of this invention is to provide a computer-readable storage medium.

[0007] The fourth objective of this invention is to provide an exoskeleton robot.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solution:

[0009] An anomaly detection method for an exoskeleton robot includes:

[0010] Detect the actual pressure data of the joints of the exoskeleton robot during the motion cycle;

[0011] Identify the anomaly detection control line;

[0012] Based on the actual pressure data within the action cycle, the minimum cumulative distance is calculated using a dynamic time adjustment algorithm. It is then determined whether the minimum cumulative distance exceeds the anomaly detection control line. If the minimum cumulative distance exceeds the anomaly detection control line a preset number of times within multiple action cycles, an anomaly alarm is triggered.

[0013] Preferably, the method further includes determining the action cycle, wherein determining the action cycle includes:

[0014] Collect pressure data when multiple actions are not triggered as noise data when the action does not occur;

[0015] The noise data is statistically analyzed, and the upper and lower boundaries of the noise data are determined using Chebyshev's inequality.

[0016] The upper and lower boundaries of the noise data are used to determine the action triggering and termination time, thereby determining the action triggering time and the action termination time, and the action cycle is determined based on the action triggering time and the action termination time.

[0017] Preferably, the step of using the upper and lower boundaries of the noise data to determine the action triggering and termination time includes:

[0018] If the pressure data remains within the noise boundary, and the pressure data exceeds the upper and / or lower boundary of the noise data three times consecutively, then the time when the pressure data first exceeds the upper and / or lower boundary of the noise data is determined as the action trigger time.

[0019] If, after the action is triggered, the pressure data detected three times consecutively are within the noise boundary, then the time when the pressure data detected for the first time is within the noise boundary is determined as the action end time.

[0020] Preferably, the determination of the anomaly detection control line includes:

[0021] Detect multiple sets of normal pressure data of the joints of the exoskeleton robot during normal movement within the movement cycle;

[0022] Normalize multiple sets of normal pressure data;

[0023] The average of multiple sets of normal pressure data after normalization is used to obtain multiple sets of standardized pressure data.

[0024] The normalized sets of normal pressure data and the normalized sets of pressure data are dynamically time-adjusted using the dynamic time adjustment algorithm to calculate the cumulative distance of each set of normal pressure data.

[0025] The mean and standard deviation of the cumulative distance of each group of normal pressure data are calculated so as to determine the abnormality detection control line based on the mean and standard deviation.

[0026] Preferably, the step of calculating the minimum cumulative distance based on actual pressure data within the action cycle using a dynamic time adjustment algorithm includes:

[0027] Normalize multiple sets of actual pressure data within the action cycle;

[0028] The normalized sets of actual pressure data and the normalized sets of pressure data are dynamically adjusted using the dynamic time adjustment algorithm to obtain the minimum cumulative distance.

[0029] Preferably, the specific steps of the dynamic time adjustment algorithm include:

[0030] Multiple sets of normalized pressure data are obtained, and the multiple sets of normalized pressure data form a first array; multiple sets of standardized pressure data are obtained, and the multiple sets of standardized pressure data form a second array, wherein any data point in the first array and any data point in the second array constitute a data point;

[0031] Create a cumulative distance matrix;

[0032] Determine the cumulative distance of all data points and populate the cumulative distance matrix to determine the minimum cumulative distance from the cumulative distance matrix.

[0033] Preferably, determining the cumulative distance of data points includes:

[0034] Determine the Euclidean distance between the data points;

[0035] Determine the cumulative distance between the three adjacent data points to the left, bottom, and bottom left of the given data point;

[0036] The minimum cumulative distance is determined from the cumulative distances of three adjacent data points of the data point;

[0037] The cumulative distance of a data point is obtained by summing the Euclidean distance of the data point and the minimum cumulative distance determined from the cumulative distances of the three adjacent data points.

[0038] To achieve the above objectives, a second aspect of the present invention provides an anomaly detection device for an exoskeleton robot, comprising:

[0039] Pressure sensors are installed at the joints of the exoskeleton robot to detect the actual pressure data of the joints during the movement cycle.

[0040] The system includes a central processing unit (CPU) and a buzzer alarm. The CPU is connected to both the pressure sensor and the buzzer alarm. The CPU is used to determine the anomaly detection control line. Based on the actual pressure data within the action cycle, it calculates the minimum cumulative distance using a dynamic time adjustment algorithm and determines whether the minimum cumulative distance exceeds the anomaly detection control line. If, within multiple action cycles, the minimum cumulative distance exceeds the anomaly detection control line a preset number of times, the CPU controls the buzzer alarm to sound an anomaly alarm.

[0041] To achieve the above objectives, a third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the above-described method for detecting anomalies in an exoskeleton robot.

[0042] To achieve the above objectives, a fourth aspect of the present invention provides an exoskeleton robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for detecting anomalies in the exoskeleton robot.

[0043] This invention has at least the following technical effects:

[0044] This invention provides an anomaly detection scheme for exoskeleton robots. Specifically, the scheme first determines the motion cycle, then detects multiple sets of normal pressure data for the exoskeleton robot's joints during normal movement within the motion cycle, and determines multiple sets of standardized pressure data and control lines based on these normal pressure data. Next, it detects the actual pressure data of the exoskeleton robot's joints within the motion cycle. Then, based on the multiple sets of actual pressure data and standardized pressure data, a dynamic time adjustment algorithm is used to dynamically adjust the time, calculating an index, i.e., a minimum cumulative distance. The minimum cumulative distance is compared with the determined control lines; if the distance exceeds the control lines for a preset number of times, an alarm is triggered by a buzzer. Therefore, this invention enables real-time, intelligent detection of exoskeleton robots.

[0045] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0046] Figure 1 This is a flowchart of an anomaly detection method for an exoskeleton robot according to an embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram illustrating the action triggering and termination judgment in an embodiment of the present invention.

[0048] Figure 3This is a schematic diagram of the anomaly detection device for an exoskeleton robot according to an embodiment of the present invention. Detailed Implementation

[0049] The following describes this embodiment in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the invention, and should not be construed as limiting the invention.

[0050] The exoskeleton robot of this embodiment and its anomaly detection method, device and medium are described below with reference to the accompanying drawings.

[0051] Figure 1 This is a flowchart of an anomaly detection method for an exoskeleton robot according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0052] Step S1: Detect the actual pressure data of the joints of the exoskeleton robot during the motion cycle.

[0053] Step S2: Determine the anomaly detection control line.

[0054] Step S3: Based on the actual pressure data within the action cycle, the minimum cumulative distance is calculated using a dynamic time adjustment algorithm. It is then determined whether the minimum cumulative distance exceeds the abnormal detection control line. If the minimum cumulative distance exceeds the abnormal detection control line a preset number of times within multiple action cycles, an abnormal alarm is triggered.

[0055] Specifically, a pressure sensor and a buzzer alarm can be installed at the joints of the exoskeleton robot. The exoskeleton robot can also be equipped with a central processing unit (CPU) that can incorporate an anomaly detection algorithm. The pressure sensor detects the force applied to the joints of the exoskeleton robot, collecting pressure signals (actual pressure data) in real time and converting them into electrical signals. These electrical signals are then transmitted to the CPU. The CPU processes the electrical signals, using a dynamic time adjustment algorithm to calculate a target, i.e., the minimum cumulative distance, and compares it with a predetermined control line. Actions exceeding the control line are marked as "A". When multiple consecutive actions within multiple action cycles are marked as "A", the buzzer alarm at the joint is triggered; otherwise, the alarm is not triggered.

[0056] In one embodiment of the present invention, the method further includes determining the action cycle, which includes: collecting pressure data when multiple actions are not triggered as noise data when the action does not occur; performing statistical analysis on the noise data, and using Chebyshev's inequality to determine the upper and lower boundaries of the noise data, such as... Figure 2As shown, the upper and lower boundaries of the noise data are used to determine the action triggering and termination time, and the action cycle is determined based on the action triggering and termination time.

[0057] Specifically, the upper and lower boundaries of the noise data are used to determine the action triggering and termination time, including: when the pressure data is continuously within the noise boundary, if the pressure data detected three times consecutively exceeds the upper and / or lower boundaries of the noise data, the time when the pressure data first exceeds the upper and / or lower boundaries of the noise data is determined as the action triggering time; after the action is triggered, if the pressure data detected three times consecutively is within the noise boundary, the time when the pressure data first is within the noise boundary is determined as the action termination time.

[0058] Specifically, the pressure sensor readings are collected when the action is not triggered multiple times; these readings represent noise data when no action occurs. The noise data is then statistically analyzed to calculate the mean μ and variance σ. 2 Using Chebyshev's inequality, with the upper bound at μ+5σ and the lower bound at μ-5σ, 96% of the noise falls within this interval. The Chebyshev inequality is as follows:

[0059]

[0060] Where P represents the probability of the event occurring, x represents the data collected by the pressure sensor when the action is not triggered, and σ represents the standard deviation.

[0061] Furthermore, the pressure data collected by the pressure sensor is traversed sequentially over time. When the pressure data remains within the noise boundary and suddenly exceeds the noise boundary three times consecutively, it is considered an action trigger. Once the action is triggered, if the pressure data remains within the noise boundary three times consecutively, the action is considered complete. The signal value at the midpoint between the action trigger and the action completion time is extracted and used as the pressure sensor signal value for one action cycle.

[0062] In one embodiment of the present invention, determining the anomaly detection control line includes: detecting multiple sets of normal pressure data of the joint parts of the exoskeleton robot during normal movement within the movement cycle; normalizing the multiple sets of normal pressure data; averaging the normalized multiple sets of normal pressure data to obtain multiple sets of standardized pressure data; dynamically adjusting the normalized multiple sets of normal pressure data and the multiple sets of standardized pressure data using a dynamic time adjustment algorithm to calculate the cumulative distance of each set of normal pressure data; and calculating the mean and standard deviation of the cumulative distance of each set of normal pressure data to determine the anomaly detection control line based on the mean and standard deviation.

[0063] Specifically, we first collect signal data from multiple sets of pressure sensors on a normal exoskeleton robot during its motion cycle, i.e., we collect multiple sets of normal pressure data. Then, we perform normalization processing on each set of normal pressure data separately.

[0064] P i P represents the normal pressure data at time i. max P represents the maximum normal pressure data within the action cycle. min Let represent the minimum normal pressure data within the action cycle. Then, the normalized normal pressure data can be expressed as:

[0065] The average of multiple sets of normalized normal pressure data is calculated in chronological order to obtain a new two-dimensional pressure-time array, which serves as the standardized pressure data. The normalized values ​​of each set of normal pressure data and the standardized pressure data are dynamically adjusted over time to calculate the cumulative distance for each set of normal pressure data. The cumulative distance for each set of normal pressure data is then statistically analyzed to obtain the average cumulative distance u for all sets of normal pressure data. d and standard deviation σ d Then, the upper and lower boundaries are calculated as control lines for anomaly detection. The upper limit is u. d +5σ d The lower limit is u d -5σ d .

[0066] In actual operation, the minimum cumulative distance can be calculated using a dynamic time adjustment algorithm based on the actual pressure data within the action cycle, and then compared with the control line. Calculating the minimum cumulative distance using the dynamic time adjustment algorithm based on the actual pressure data within the action cycle includes: normalizing multiple sets of actual pressure data within the action cycle; and dynamically adjusting the normalized sets of actual pressure data with multiple sets of standardized pressure data using the dynamic time adjustment algorithm to calculate the minimum cumulative distance.

[0067] Specifically, pressure sensor data is collected in real time when the action occurs. Sensor data within the action cycle is obtained based on the action trigger and end times. The real-time collected data within the action cycle is normalized. The normalized actual pressure data and standardized pressure data are dynamically time-adjusted, and the minimum cumulative distance between the two sets of data after dynamic time adjustment is calculated. The calculated minimum cumulative distance is compared with preset control lines. If it exceeds the upper or lower limit of the control, it is considered an abnormal action and marked as A; otherwise, it is marked as G. When five consecutive A markings occur, a buzzer alarm is triggered to sound an abnormality alarm. Five is an empirical value and can be adjusted according to actual conditions. If there are many false alarms, the number of times can be increased; if there are many missed alarms, the number of times can be decreased.

[0068] In one embodiment of the present invention, the specific steps of the dynamic time adjustment algorithm include: acquiring multiple sets of normalized pressure data, forming a first array; acquiring multiple sets of standardized pressure data, forming a second array, wherein any data point in the first array and any data point in the second array constitute a data point; creating a cumulative distance matrix; determining the cumulative distance of all data points and filling the cumulative distance matrix to determine the minimum cumulative distance from the cumulative distance matrix.

[0069] The process of determining the cumulative distance of a data point includes: determining the Euclidean distance of the data point; determining the cumulative distance of the three adjacent data points to the left, bottom, and bottom left of the data point; determining the minimum cumulative distance from the cumulative distances of the three adjacent data points; and summing the Euclidean distance of the data point and the minimum cumulative distance determined from the cumulative distances of the three adjacent data points to obtain the cumulative distance of the data point.

[0070] The purpose of dynamic time adjustment is to compress or stretch the normalized signal value in the time dimension, so that the actions of different groups are aligned as much as possible, thereby avoiding judgment errors caused by differences in action speed or time displacement. The specific method is as follows:

[0071] (1) Obtain multiple sets of normalized pressure data to form the first array R = [r1, r2, ... r2]. m Then, multiple sets of standardized stress data are acquired to form a second array B = [b1, b2, ..., b...]. n ], where r m For the normalized pressure data of the m-th group, b n This represents the standardized pressure data for the nth group.

[0072] (2) Determine the metric to be used when calculating the distance. Here, Euclidean distance is used for the metric.

[0073] (3) Dynamic Programming Table Initialization: Create a cumulative distance matrix, i.e., a two-dimensional array, with a size of (n+1)(m+1). Initialize the first row and the first column so that the cumulative distance D(0,0) of the starting point (data point (0,0)) is 0, and set D(b) to 0. i ,0) and D(0,r) j ) represents infinity or a very large number, indicating an initial invalid value.

[0074] (4) Fill the cumulative distance matrix: Use dynamic programming to fill the cumulative distance matrix. For each data point (b i ,r j ), calculate the cumulative distance D(b) of the data point. i ,r j).

[0075] (5) The method for calculating the value of this data point is the Euclidean distance d(b) of the current data point. i ,r j The sum of the minimum cumulative distances between the point and its three adjacent points (left, bottom, and bottom left). The specific calculation formula is:

[0076] D(b i ,r j )=d(b i ,r j )+min{D(b i-1 ,r j ), D(b i ,r j-1 ), D(b i-1 ,r j-1 (2)

[0077] Wherein, D(b) i-1 ,r j ), D(b i ,r j-1 ), D(b i-1 ,r j-1 ) are data points (b) i ,r j The cumulative distance between the three adjacent points on the left, bottom, and bottom left.

[0078] (6) Calculate the minimum cumulative distance and fill it. After the cumulative distance matrix is ​​filled, D(b) n ,r m The minimum cumulative distance between two time series data B and R is the dynamic time warping distance between the two sets of time series data B and R. It can be compared with the control line.

[0079] Figure 3 This is a schematic diagram of the anomaly detection device for an exoskeleton robot according to an embodiment of the present invention. Figure 3 As shown, the anomaly detection device of the exoskeleton robot includes a pressure sensor, a central processing unit, and a buzzer alarm connected in sequence. The pressure sensor is installed at the joints of the exoskeleton robot to detect the actual pressure data of the joints during the movement cycle. The central processing unit is connected to both the pressure sensor and the buzzer alarm. The central processing unit determines the anomaly detection control line, calculates the minimum cumulative distance based on the actual pressure data during the movement cycle using a dynamic time adjustment algorithm, and determines whether the minimum cumulative distance exceeds the anomaly detection control line. If, within multiple movement cycles, the minimum cumulative distance exceeds the anomaly detection control line a preset number of times, the buzzer alarm is activated to sound an anomaly alarm.

[0080] It should be noted that the specific implementation of the abnormality detection device for the exoskeleton robot in this embodiment can be found in the specific implementation of the abnormality detection method for the exoskeleton robot described above. To avoid redundancy, it will not be repeated here.

[0081] In summary, this invention can promptly detect anomalies in exoskeleton robots, preventing potential dangers. It employs a calculation method based on Chebyshev's inequality to determine the complete stages of action triggering and termination through signals. Furthermore, it utilizes a dynamic time adjustment method to evaluate the pressure signals of actions, avoiding false alarms caused by signals at different speeds and time displacements, thus achieving intelligent anomaly detection in exoskeleton robots.

[0082] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for anomaly detection in an exoskeleton robot.

[0083] Furthermore, the present invention also provides an exoskeleton robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned abnormality detection method for the exoskeleton robot.

[0084] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0085] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Various modifications and substitutions to the present invention will be apparent to those skilled in the art after reading the above description. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. An anomaly detection method for an exoskeleton robot, characterized in that, include: Detect the actual pressure data of the joints of the exoskeleton robot during the motion cycle; Identify the anomaly detection control line; The upper and lower boundaries of the noise data are used to determine the action triggering and termination time, and the action cycle is determined based on the action triggering and termination time. Based on the actual pressure data within the action cycle, the minimum cumulative distance is calculated through a dynamic time adjustment algorithm. It is then determined whether the minimum cumulative distance exceeds the abnormality detection control line. If the minimum cumulative distance exceeds the abnormality detection control line a preset number of times within multiple action cycles, an abnormality alarm is triggered. The step of using the upper and lower boundaries of the noise data to determine the action triggering and termination time includes: If the pressure data remains within the noise boundary, and the pressure data exceeds the upper and / or lower boundary of the noise data three times consecutively, then the time when the pressure data first exceeds the upper and / or lower boundary of the noise data is determined as the action trigger time. If, after the action is triggered, the pressure data detected three times consecutively are within the noise boundary, then the time when the pressure data detected for the first time is within the noise boundary is determined as the action end time. The determination of the anomaly detection control line includes: Detect multiple sets of normal pressure data of the joints of the exoskeleton robot during normal movement within the movement cycle; Normalize multiple sets of normal pressure data; The average of multiple sets of normal pressure data after normalization is used to obtain multiple sets of standardized pressure data. The normalized sets of normal pressure data and the normalized sets of pressure data are dynamically time-adjusted using the dynamic time adjustment algorithm to calculate the cumulative distance of each set of normal pressure data. The mean and standard deviation of the cumulative distance of each group of normal pressure data are calculated so as to determine the abnormality detection control line based on the mean and standard deviation.

2. The anomaly detection method for an exoskeleton robot as described in claim 1, characterized in that, Also includes: Collect pressure data when multiple actions are not triggered as noise data when the action does not occur; The noise data is statistically analyzed, and the upper and lower boundaries of the noise data are determined using Chebyshev's inequality.

3. The anomaly detection method for an exoskeleton robot as described in claim 1, characterized in that, The minimum cumulative distance is calculated using a dynamic time adjustment algorithm based on actual pressure data within the action cycle, including: Normalize multiple sets of actual pressure data within the action cycle; The normalized sets of actual pressure data and the normalized sets of pressure data are dynamically adjusted using the dynamic time adjustment algorithm to obtain the minimum cumulative distance.

4. The anomaly detection method for an exoskeleton robot as described in claim 3, characterized in that, The specific steps of the dynamic time adjustment algorithm include: Multiple sets of normalized pressure data are obtained, and the multiple sets of normalized pressure data form a first array; multiple sets of standardized pressure data are obtained, and the multiple sets of standardized pressure data form a second array, wherein any data point in the first array and any data point in the second array constitute a data point; Create a cumulative distance matrix; Determine the cumulative distance of all data points and populate the cumulative distance matrix to determine the minimum cumulative distance from the cumulative distance matrix.

5. The anomaly detection method for an exoskeleton robot as described in claim 4, characterized in that, Determine the cumulative distance of the data points, including: Determine the Euclidean distance between the data points; Determine the cumulative distance between the three adjacent data points to the left, bottom, and bottom left of the given data point; The minimum cumulative distance is determined from the cumulative distances of three adjacent data points of the data point; The cumulative distance of a data point is obtained by summing the Euclidean distance of the data point and the minimum cumulative distance determined from the cumulative distances of the three adjacent data points.

6. An anomaly detection device for an exoskeleton robot, characterized in that, An anomaly detection method for implementing the exoskeleton robot as described in any one of claims 1-5 includes: Pressure sensors are installed at the joints of the exoskeleton robot to detect the actual pressure data of the joints during the movement cycle. The system includes a central processing unit (CPU) and a buzzer alarm. The CPU is connected to both the pressure sensor and the buzzer alarm. The CPU is used to determine the anomaly detection control line. Based on the actual pressure data within the action cycle, it calculates the minimum cumulative distance using a dynamic time adjustment algorithm and determines whether the minimum cumulative distance exceeds the anomaly detection control line. If, within multiple action cycles, the minimum cumulative distance exceeds the anomaly detection control line a preset number of times, the CPU controls the buzzer alarm to sound an anomaly alarm.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the anomaly detection method for the exoskeleton robot as described in any one of claims 1-5.

8. An exoskeleton robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the anomaly detection method for the exoskeleton robot as described in any one of claims 1-5.

Images