Exoskeleton-based walking recognition method, signal collection shoe and exoskeleton

Abstract

The present disclosure relates to the technical field of wearable exoskeletons, and particularly relates to an exoskeleton-based walking recognition method, a signal collection shoe and an exoskeleton. The method comprises: acquiring plantar pressure data, wherein the plantar pressure data comprises pressure signals of specified foot positions of each side foot under the same detection duration when a user wearing an exoskeleton walks; determining representative gaits according to the plantar pressure data, wherein a plurality of time-continuous representative gaits can form a target gait timing; and generating walking recognition information according to the target gait timing and a preset gait timing. The embodiment does not need to establish a walking recognition model, and can quickly and reliably recognize walking by using the plantar pressure data, which is conducive to improving the efficiency and real-time performance of the exoskeleton in recognizing walking.

Description

Technical Field

[0001] This disclosure relates to the field of wearable exoskeleton technology, specifically to an exoskeleton-based walking recognition method, signal acquisition shoes, and an exoskeleton. Background Technology

[0002] As powerful wearable mechanical devices, human exoskeletons are increasingly attracting the attention of scholars and researchers both domestically and internationally, becoming a new research hotspot. Human exoskeletons require the rapid and accurate prediction of human movement intentions in order to effectively control walking, which is one category among many activity gaits.

[0003] Most existing technologies employ model recognition algorithms such as artificial neural networks and support vector machines to identify the walking motion of exoskeletons. However, these algorithms require processing large amounts of data, resulting in low efficiency in recognizing walking motion and impacting real-time performance. When the exoskeleton fails to recognize the user's walking intention in a timely manner, it can actually restrict the user's movement, affecting the smoothness of the interaction between the user and the exoskeleton.

[0004] Public content

[0005] One objective of this disclosure is to provide an exoskeleton-based walking recognition method, signal acquisition shoe, and exoskeleton, aiming to improve the problem of low efficiency in exoskeleton-based walking recognition.

[0006] In a first aspect, embodiments of this disclosure provide a walking recognition method based on an exoskeleton, comprising:

[0007] Acquire plantar pressure data, wherein the plantar pressure data includes pressure signals at specified foot positions on each foot during the same detection time when the user is walking while wearing the exoskeleton.

[0008] Based on the plantar pressure data, representative gait is determined, wherein multiple representative gait that are consecutive in time can form a target gait time sequence;

[0009] Based on the target gait timing and the preset gait timing, walking recognition information is generated.

[0010] Optionally, determining the representative gait based on the plantar pressure data includes:

[0011] Based on the plantar pressure data, a level signal is generated for each specified foot position;

[0012] Based on each of the stated level signals, a representative gait is determined.

[0013] Optionally, determining the representative gait based on each of the said level signals includes:

[0014] Detect the level change of each of the stated level signals;

[0015] Select the level signal whose level changes as the target level signal;

[0016] The representative gait is determined based on the level change of the target level signal.

[0017] Optionally, the target level signal includes a first level signal and a second level signal, and determining the representative gait based on the level change of the target level signal includes:

[0018] Given that the first level signal is the level signal of the right heel and the second level signal is the level signal of the right toe, if the level changes of both the first level signal and the second level signal are from low to high, then the gait represents the right foot landing; if the level changes of both the first level signal and the second level signal are from high to low, then the gait represents the right foot leaving the ground.

[0019] Given that the first level signal is the level signal of the left heel and the second level signal is the level signal of the left toe, if the level changes of both the first level signal and the second level signal are from low to high, then the representative gait is left foot landing; if the level changes of both the first level signal and the second level signal are from high to low, then the representative gait is left foot off the ground.

[0020] Optionally, generating a level signal for each specified foot position based on the plantar pressure data includes:

[0021] Based on the pressure signal at each specified foot position, generate a pressure comparison signal for each specified foot position;

[0022] Determine whether the pressure comparison signal at each specified foot position is greater than the pressure threshold corresponding to the specified foot position;

[0023] If the value is greater than the specified foot position, a high-level signal is generated for each of the specified foot positions.

[0024] If it is less than or equal to, a low-level signal is generated for each specified foot position.

[0025] Optionally, multiple preset gait time sequences are configured in a gait time sequence library, and the walking recognition information includes walking confirmation information or non-walking information. Generating walking recognition information based on the target gait time sequence and the preset gait time sequences includes:

[0026] Determine whether the target gait timing matches any preset gait timing in the gait timing library;

[0027] If a match is found, a walking confirmation message is generated;

[0028] If there is no match, non-walking information is generated.

[0029] Optionally, before generating walking recognition information, the method further includes:

[0030] Determine the time difference between two adjacent representative gaits;

[0031] Determine whether the time difference is within a specified time range corresponding to two adjacent representative gaits;

[0032] If present, then both adjacent representative gaits are determined to be normal gaits;

[0033] If not, then both adjacent representative gaits are determined to be abnormal gaits.

[0034] In a second aspect, embodiments of this disclosure provide a storage medium storing computer-executable instructions for causing a controller to execute the exoskeleton-based walking recognition method described above.

[0035] In a third aspect, embodiments of this disclosure provide a signal acquisition shoe, comprising:

[0036] The shoe itself;

[0037] Multiple sets of pressure sensor assemblies, each set of pressure sensors being arranged at a designated foot position on the shoe body;

[0038] The controller, electrically connected to each of the pressure sensors, is used to perform the exoskeleton-based walking recognition method described above.

[0039] In a fourth aspect, embodiments of this disclosure provide an exoskeleton, comprising:

[0040] Back frame assembly;

[0041] Waist frame assembly, connected to the back frame assembly;

[0042] Lower limb assembly, connected to the waist frame assembly; and

[0043] The aforementioned signal acquisition shoe is connected to the lower limb assembly.

[0044] In the exoskeleton-based gait recognition method provided in this embodiment, plantar pressure data is acquired. This plantar pressure data includes pressure signals at specified foot positions on each side of the foot during the same detection time when the user is walking while wearing the exoskeleton. Representative gaits are determined based on the plantar pressure data. Multiple consecutive representative gaits can form a target gait time sequence. Gait recognition information is generated based on the target gait time sequence and a preset gait time sequence. This embodiment eliminates the need to establish a gait recognition model; it can quickly and reliably recognize gait using plantar pressure data, which improves the efficiency and real-time performance of exoskeleton-based gait recognition. Attached Figure Description

[0045] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0046] Figure 1 This is a schematic diagram of the structure of an exoskeleton provided in an embodiment of the present disclosure;

[0047] Figure 2 for Figure 1 The diagram shows the structure of the signal acquisition shoe.

[0048] Figure 3 for Figure 1 The circuit structure diagram of the controller and multiple pressure sensing components in the signal acquisition shoe is shown.

[0049] Figure 4 for Figure 2 The diagram shows a first possible distribution of the pressure sensing components in the signal acquisition shoe.

[0050] Figure 5 for Figure 2 The diagram shows a second distribution of the pressure sensing components in the signal acquisition shoe.

[0051] Figure 6 for Figure 2 The diagram shown is a structural schematic of the signal acquisition shoe at the first angle, in which the upper and lower soles are omitted;

[0052] Figure 7 for Figure 2 The diagram shown is a structural schematic of the signal acquisition shoe at the second angle, in which the upper and lower soles are omitted;

[0053] Figure 8 for Figure 2 The diagram shown illustrates the disassembly of the signal acquisition shoe, where the signal box has been disassembled.

[0054] Figure 9 for Figure 2 The circuit structure diagram of the signal acquisition shoe is shown below;

[0055] Figure 10 A schematic diagram of the circuit structure of an exoskeleton provided in an embodiment of this disclosure;

[0056] Figure 11 A flowchart illustrating a walking recognition method based on an exoskeleton provided in this embodiment of the present disclosure;

[0057] Figure 12 for Figure 11 The flowchart of step S72 is shown below;

[0058] Figure 13 for Figure 12 The flowchart of step S722 is shown below;

[0059] Figure 14 A flowchart illustrating a walking recognition method based on an exoskeleton, as provided in another embodiment of this disclosure;

[0060] Figure 15 A timing diagram of a level signal in an application scenario provided by an embodiment of this disclosure;

[0061] Figure 16 This is a schematic diagram of the circuit structure of a controller provided in an embodiment of this disclosure. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0063] It should be noted that, unless there is a conflict, the various features in the embodiments of this disclosure can be combined with each other, all of which are within the protection scope of this disclosure. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this disclosure do not limit the data or execution order, but only distinguish identical or similar items with substantially the same function and effect.

[0064] This disclosure provides an exoskeleton; please refer to [link / reference]. Figure 1 The exoskeleton 100 includes a back frame assembly 200, a waist frame assembly 300, a lower limb assembly 400, and a signal acquisition shoe 500.

[0065] The back brace assembly 200 is used to secure the shoulders and back of the human body. The lumbar support assembly 300 is connected to the back brace assembly 200 and is used to secure the lower back of the human body. The lower limb assembly 400 is connected to the lumbar support assembly 300 and is used to secure the thighs and calves of the human body. The signal acquisition shoe 500 is connected to the lower limb assembly 400 and is used for wearing on the feet of the human body.

[0066] Please refer to the following: Figure 2 and Figure 3 The signal acquisition shoe 500 includes a shoe body 51, multiple pressure sensing components 52, and a controller 53. The controller 53 is electrically connected to each pressure sensing component 52. Each pressure sensor 52 is positioned at a designated foot location on the shoe body 51, including the right heel, right toe, right midfoot, left heel, left toe, and left midfoot.

[0067] In some embodiments, the shoe body 51 includes a first sole 54, a second sole 55, and a sensor bracket 56, wherein the sensor bracket 56 is disposed between the first sole 54 and the second sole 55. The side of the first sole 54 away from the sensor bracket 56 is used to conform to the sole of the human foot, and the side of the second sole 55 away from the sensor bracket 56 is used to contact the ground. A pressure sensing component 52 is embedded in the sensor bracket 56. The sensor bracket 56 can be a flexible bracket.

[0068] Please refer to the following: Figure 4 and Figure 5 The multiple pressure sensor assemblies include a first pressure sensor assembly 521, a second pressure sensor assembly 522, and a third pressure sensor assembly 523, wherein each pressure sensor assembly is disposed at a designated foot position on each side of the foot.

[0069] A first pressure sensor assembly 521 is located at the toe (10a), a second pressure sensor assembly 522 is located in the middle of the foot (10b), and a third pressure sensor assembly 523 is located in the heel (10c). The first pressure sensor assembly 521 collects the pressure applied by the user's toe to the first pressure sensor assembly 521, obtaining a pressure signal from the toe. The second pressure sensor assembly 522 collects the pressure applied by the user's middle of the foot to the second pressure sensor assembly 522, obtaining a pressure signal from the middle of the foot. The third pressure sensor assembly 523 collects the pressure applied by the user's heel to the third pressure sensor assembly 523, obtaining a pressure signal from the heel.

[0070] like Figure 4 and Figure 5As shown, for the right foot, the first pressure sensor assembly 521 is located at the toe of the right foot, the second pressure sensor assembly 522 is located in the middle of the right foot, and the third pressure sensor assembly 523 is located at the heel of the right foot.

[0071] The shoe body 51 has a center line O, which is the line connecting the toe and the heel. The first group of pressure sensor components 521 and the second group of pressure sensor components 522 are located on different sides of the center line O, and the third group of pressure sensor components 523 is located on the center line O. The first group of pressure sensor components 521, the second group of pressure sensor components 522 and the third group of pressure sensor components 523 are relatively evenly distributed, and pressure information of the toe, midfoot and heel of the human body can be collected by only three groups of pressure sensor components.

[0072] like Figure 4 As shown, the first pressure sensor assembly 521 can be located on the outer side of the centerline O, and the second pressure sensor assembly 522 can be located on the inner side of the centerline O.

[0073] like Figure 5 As shown, the first pressure sensor assembly 521 can also be located on the inner side of the center line O, and the second pressure sensor assembly 522 can also be located on the outer side of the center line O. It should be noted that the inner side of the center line O is the side of the signal acquisition shoe 500 where the center line O is located, which is closer to the other signal acquisition shoe 500; the outer side of the center line O is the side of the signal acquisition shoe 500 where the center line O is located, which is farther away from the other signal acquisition shoe 500.

[0074] Please refer to the following: Figure 6 and Figure 7 The signal acquisition shoe 500 also includes a signal box 57 and a quick-release structure 58. The signal box 57 houses the controller 53, and both the signal box 57 and the quick-release structure 58 are located on one side of the shoe body 51. The controller 53 receives pressure signals acquired by each set of pressure sensing components. The quick-release structure 58 is used to detachably connect the lower limb components of the exoskeleton.

[0075] The sensor bracket 56 is provided with mounting holes 560 for mounting pressure sensing components. Specifically, the mounting holes 560 have upper and lower layers. The upper and lower layers of mounting holes 560 are respectively located on the upper and lower surfaces of the sensor bracket 56, and are used to mount the upper and lower layers of pressure sensors respectively. Each pressure sensing component 52 includes a first pressure sensor 521 and a second pressure sensor 522. The first pressure sensor 521 and the second pressure sensor 522 are respectively mounted in the upper and lower layers of mounting holes 560, that is: the first pressure sensor 521 is mounted in the mounting hole 560 on the side of the sensor bracket 56 near the first sole 53, and the second pressure sensor 522 is mounted in the mounting hole 560 on the side of the sensor bracket 56 near the second sole 55.

[0076] The sensor bracket 56 is provided with a wiring groove 561. The wiring groove 561 is connected to the mounting hole 560 and is used for the wiring of the pressure sensor to pass through. One end of the wiring groove 561 extends to the side of the sensor bracket 56 near the signal box 57, so that the wiring of the pressure sensor can extend to the signal box 57 to realize electrical connection with the controller 53.

[0077] A wiring channel 561 is located on the side of the sensor bracket 56 near the upper sole. The wiring channel 561 connects to the upper mounting hole 560, and the wiring of the upper and lower pressure sensors shares a single wiring channel 561. The wiring channel 561 can extend to the side of the sensor bracket 56 near the lower sole and connect to the lower mounting hole 560, allowing the wiring of the lower pressure sensor to enter the wiring channel 561. An opening can also be provided between the wiring channel 561 and the lower mounting hole 560, through which the wiring of the lower pressure sensor can enter the wiring channel 561.

[0078] Please see Figure 8 The signal box 57 includes a box body 571 and a box cover 572. The box body 571 is fixed to one side of the shoe body 51, wherein the controller 53 is housed inside the box body 571, and the box cover 572 is placed over the opening of the box body 571 to close the box body 571.

[0079] Please see Figure 9The controller 53 is electrically connected to each group of pressure sensing components. The controller 53 is located on a control motherboard, which also includes multiple communication interfaces (COM), differential amplifier circuits, reset button circuits, GPIO button circuits, LED circuits, IMU sensors, CAN driver circuits, voltage conversion circuits, serial port debugging circuits, and program download interface circuits. Each communication interface (COM) is electrically connected to each group of pressure sensing components. The differential amplifier circuit amplifies the pressure signals collected by the pressure sensing components in a differential manner, obtaining an amplified pressure signal, which is then transmitted to the controller 53. The reset button circuit sends a reset signal to the controller 53, causing the controller 53 to perform a reset operation. The GPIO button circuit provides button signals to the controller 53, enabling the controller 53 to execute corresponding control logic based on the button signals. The LED circuit, controlled by the controller 53, generates red or green light. The IMU sensor detects the foot's swing angle and acceleration, transmitting these data to the controller, causing the controller 53 to execute the corresponding control logic. Under the control of controller 53, the CAN driver circuit communicates with upper-layer components based on the CAN communication protocol. The voltage conversion circuit, also under the control of controller 53, converts external 5V power to 3.3V for power supply. The serial port debugging circuit provides a debugging interface for debugging controller 53. The program download circuit, under the control of controller 53, downloads firmware to complete system upgrades or updates.

[0080] The quick-release structure 58 includes an L-shaped fastener 581 and a movable buckle 582. One end of the L-shaped fastener 581 is horizontally embedded in the shoe body 51, and the other end extends vertically upward. The movable buckle 582 is fixed to the L-shaped fastener. The movable buckle 582 is used to detachably connect the lower limb assembly of the exoskeleton. The movable buckle 582 can be a conventional buckle, and the signal acquisition shoe 500 can be detached from the lower limb assembly by pressing its two sides.

[0081] In some embodiments, please refer to Figure 10 The exoskeleton 100 also includes a main controller 601, a joint drive unit 602, a power module 603, a human-machine interface terminal 604, and a communication bus 605. The main controller 601 is connected to the joint drive unit 602, the power module 603, and the signal acquisition shoe 500 via the communication bus 605, and the human-machine interface terminal 604 is connected to the main controller 601.

[0082] The main controller 601 executes algorithms based on real-time acquired signals and outputs motion control commands. The joint drive unit 602, under the control of the main controller 601, performs motion mode switching and servo control. The motion mode can include position control, speed control, and torque control. The joint drive unit 602 can be a joint module integrating a motor servo system, encoder, driver, and motor, or it can be other power execution units, such as pneumatic or hydraulic transmission systems.

[0083] The power module 603 may include a power supply unit and a power management unit. Specifically, the power supply unit can be powered by a 24V or 36V battery pack. The power supply unit can be connected to the main controller 601, the joint drive unit 602, and the signal acquisition shoe 500 via power cables, providing power to these components. The power output from the power supply unit can be converted by a voltage conversion circuit to output +3.3V or 5V voltage to the signal acquisition shoe.

[0084] The human-machine interface terminal 604 is used for the human-machine interface (UI) display, and the displayed content may include real-time data monitoring, operation interface display, and status information display. Status information may include the battery status mentioned earlier. Communication between the human-machine interface terminal 604 and the main controller 601 can be achieved via wired Ethernet.

[0085] As another aspect of this disclosure, this disclosure provides a walking recognition method based on an exoskeleton. Please refer to... Figure 11 Exoskeleton-based walking recognition methods include:

[0086] S71: Acquire plantar pressure data, which includes pressure signals at specified foot positions on each side of the foot during the same detection time when the user is walking while wearing the exoskeleton.

[0087] In this step, the designated foot positions include the right heel, right toe, right middle of the foot, left heel, left toe, and left middle of the foot. Therefore, the designated foot positions for the right foot include the right heel, right toe, and right middle of the right foot, and the designated foot positions for the left foot include the left heel, left toe, and left middle of the left foot.

[0088] As mentioned above, in this embodiment, a pressure sensing component is installed at each designated foot position. The pressure sensing component may include any number of pressure sensors. That is, in addition to the two pressure sensors described above, in some embodiments, the pressure sensing component may include one or more pressure sensors.

[0089] When a user wears the exoskeleton for walking, their feet are fitted with signal-collecting shoes. The user's feet apply pressure to the soles of these shoes, and pressure sensors at designated foot locations collect the pressure exerted by the user's feet on the soles, thus generating a pressure signal.

[0090] Understandably, for a single leg, the leg drives the foot in movement. Walking can be viewed as a cyclical switching of the leg between a support phase and a swing phase, or a swing phase and a support phase. When the leg enters the support phase, the heel usually lands first, followed by the toes. When the leg enters the swing phase, the heel usually leaves the ground first, followed by the toes.

[0091] When the right leg enters the support phase, the left leg is already in the support phase. At this time, for the right foot, since the right heel lands first, the pressure sensor component of the right heel can sample the pressure signal first. Within a short time, the pressure sensor component of the right toe also lands and samples the pressure signal. At this time, for the left foot, both the left heel and the left toe have sampled pressure signals during the above process. As shown above, a set of plantar pressure data A1 = {Rh1, Rt1, Lh1, Lt1} can be obtained, where Rh represents the pressure signal of the right heel, Rt represents the pressure signal of the right toe, Lh represents the pressure signal of the left heel, and Lt represents the pressure signal of the left toe.

[0092] When the left leg enters the swing phase, the right leg is already in the support phase. At this time, for the left foot, since the left heel leaves the ground first, the pressure sensor component of the left heel is deactivated first, meaning it does not initially sample a pressure signal. Within a short time, the pressure sensor component of the left toe also leaves the ground, meaning it is subsequently deactivated and also does not sample a pressure signal. Meanwhile, for the right foot, both the right heel and right toe sample pressure signals during the above process. As shown above, a set of plantar pressure data A2 = {Rh2, Rt2, Lh2, Lt2} can be obtained.

[0093] When the left leg enters the support phase, the right leg is already in the support phase. At this time, for the left foot, since the left heel lands first, the pressure sensor component of the left heel can sample the pressure signal first. Within a short time, the pressure sensor component of the left toe also lands and samples the pressure signal. At this time, for the right foot, both the right heel and the right toe have sampled pressure signals during the above process. As shown above, a set of plantar pressure data A3 = {Rh3, Rt3, Lh3, Lt3} can be obtained.

[0094] When the right leg enters the swing phase, the left leg is already in the support phase. At this time, for the right foot, since the right heel leaves the ground first, the pressure sensor component of the right heel is deactivated first, meaning it does not initially sample a pressure signal. Within a short time, the pressure sensor component of the right toe also leaves the ground, meaning it is subsequently deactivated and also does not sample a pressure signal. Meanwhile, for the left foot, both the left heel and left toe have sampled pressure signals during the above process. As shown above, a set of plantar pressure data A4 = {Rh4, Rt4, Lh4, Lt4} can be obtained.

[0095] S72: Based on plantar pressure data, determine representative gait, where multiple representative gait with consecutive time can form the target gait sequence.

[0096] In this step, the representative gait is used to describe the walking state of the left / right foot when the user's left / right leg enters the swing phase or support phase. The representative gait includes right foot landing, left foot off the ground, left foot landing, and right foot off the ground.

[0097] In some embodiments, when the right leg enters the support phase from the swing phase, it represents a gait where the right foot is on the ground ①. When the left leg enters the swing phase from the support phase, it represents a gait where the left foot is off the ground ②. When the left leg enters the support phase from the swing phase, it represents a gait where the left foot is on the ground ③. When the right leg enters the swing phase from the support phase, it represents a gait where the right foot is off the ground ④.

[0098] Multiple representative gaits in temporal continuity refer to gaits that are sequential in time when each representative gait is determined in chronological order. The target gait sequence is composed of multiple representative gaits in temporal continuity.

[0099] Normally, when people walk, the movements of the left and right legs leading the feet are continuous. For example, when standing on both feet, the right leg begins to step forward, with the left leg supporting the weight. When the right leg enters the support phase, the left leg is still in the support phase; at this point, the gait can be described as the right foot landing①. After the right foot lands, when the left leg enters the swing phase, the right leg is already in the support phase; at this point, the gait can be described as the left foot leaving the ground②. When the left foot begins to land, the right leg is still in the support phase; at this point, the gait can be described as the left foot landing③. After the left foot lands, when the right leg enters the swing phase, the left leg is still in the support phase; at this point, the gait can be described as the right foot leaving the ground④.

[0100] Therefore, from a temporal perspective, the gait described above, representing the right foot landing ① -> left foot leaving the ground ② -> left foot landing ③ -> right foot leaving the ground ④, is continuous in time.

[0101] It is understandable that, considering that people start with different representative gaits, each representative gait will also present different forms in time. For example: left foot off the ground ② -> left foot on the ground ③ -> right foot off the ground ④ -> right foot on the ground ①, or left foot on the ground ③ -> right foot off the ground ④ -> right foot on the ground ① -> left foot off the ground ②, or right foot off the ground ④ -> right foot on the ground ① -> left foot off the ground ② -> left foot on the ground ③. The above representative gaits are also continuous in time.

[0102] Understandably, when people are not walking, the target gait timing does not conform to the normal walking timing described above.

[0103] S73: Generate walking recognition information based on the target gait timing and the preset gait timing.

[0104] In this step, the preset gait timing sequence is used to identify whether the target gait timing sequence meets the normal walking timing sequence. The preset gait timing sequence can be any one of the normal gait timing sequences {①,②,③,④}, {②,③,④,①}, {③,④,①,②}, and {④,①,②,③,}.

[0105] Preset gait timings can be configured in the gait timing library. The gait timing library is used to store at least one or more preset gait timings. The exoskeleton can access the gait timing library and retrieve preset gait timings.

[0106] Pedestrian identification information is used to identify whether a user is walking. This information includes walking confirmation information and non-walking information. Walking confirmation information indicates that the user is walking, while non-walking information indicates that the user is not walking.

[0107] In some embodiments, when the gait timing library stores a preset gait timing, the exoskeleton accesses the gait timing library to retrieve the preset gait timing, determines whether the target gait timing matches the preset gait timing, generates walking confirmation information if it matches, and generates non-walking information if it does not match.

[0108] In some embodiments, when the gait timing library stores at least two preset gait timing sequences, the exoskeleton accesses the gait timing library, retrieves each preset gait timing sequence in sequence, and determines whether the target gait timing sequence matches any preset gait timing sequence in the gait timing library. If they match, walking confirmation information is generated; if they do not match, non-walking information is generated.

[0109] In some embodiments, when the exoskeleton generates walking confirmation information, it enters a walking assistance mode to carry the user while walking, thus reducing the burden on the user. When the exoskeleton generates non-walking information, it does not need to enter the walking assistance mode, avoiding human-machine motion interference and improving the user experience.

[0110] Compared to existing technologies, this embodiment does not require the establishment of a walking recognition model. It can quickly and reliably recognize walking by using plantar pressure data, which is beneficial to improving the efficiency and real-time performance of exoskeleton walking recognition.

[0111] In some embodiments, when determining the representative gait, please refer to Figure 12 S72 includes:

[0112] S721: Generates a level signal for each specified foot position based on plantar pressure data.

[0113] S722: Determines the representative gait based on each level signal.

[0114] In S721, the level signal is a level generated based on the pressure signal at each specified foot position. Since the pressure sensing component at each specified foot position can sample the pressure signal applied by the user to the specified foot position, in order to facilitate subsequent analysis of the pressure signal and gait identification, this embodiment can convert the pressure signal into a level signal.

[0115] In some embodiments, this embodiment can generate a pressure comparison signal for each specified foot position based on the pressure signal for each specified foot position, and determine whether the pressure comparison signal for each specified foot position is greater than the pressure threshold corresponding to the specified foot position. If it is greater, a high-level signal for each specified foot position is generated; if it is less than or equal to, a low-level signal for each specified foot position is generated.

[0116] In some embodiments, the pressure signal at each specified foot position can be directly used as the pressure comparison signal at each specified foot position.

[0117] In some embodiments, when the pressure sensing component for each specified foot position includes a pressure sensor, the pressure signal collected by the pressure sensor can also be used as the pressure comparison signal for that specified foot position.

[0118] In some embodiments, when the pressure sensing component for each specified foot position includes at least two pressure sensors, the sum of the pressures from the at least two pressure sensors can be calculated, and the sum of the pressures can be divided by the number of pressure sensors to obtain a pressure comparison signal, wherein the sum of the pressures is the sum of the peak values ​​of each pressure signal.

[0119] For example, please continue reading Figure 4The pressure sensing component of the right heel 10a has two layers of pressure sensors, one above the other. The peak value of the pressure signal sampled by the first pressure sensor is e1, and the peak value of the pressure signal sampled by the second pressure sensor is e2. Therefore, the total pressure S1 = e1 + e2. Consequently, the first pressure comparison signal Avg1 = S1 / N1, where N1 = 2. Similarly, the second pressure comparison signal of the right heel 10c is Avg2 = S2 / N2, where S2 is the total pressure of the right heel, and N2 is the number of pressure sensors on the right heel.

[0120] In some embodiments, when determining whether the pressure comparison signal for each specified foot position is greater than a pressure threshold corresponding to that specified foot position, if the specified foot position is the toe, then it is determined whether the first pressure comparison signal for the toe is greater than a first pressure threshold, wherein the first pressure threshold is associated with a pressure sensing component for the toe. Similarly, if the specified foot position is the heel, then it is determined whether the second pressure comparison signal for the heel is greater than a second pressure threshold, wherein the second pressure threshold is associated with a pressure sensing component for the heel.

[0121] In some embodiments, when the first pressure comparison signal of the toe is greater than the first pressure threshold, it indicates that the toe is in contact with the ground; therefore, the first pressure comparison signal of the toe can be modulated into a high-level signal. When the first pressure comparison signal of the toe is not greater than the first pressure threshold, it indicates that the toe has detached from the ground or has not yet fully contacted the ground; therefore, the first pressure comparison signal of the toe can be modulated into a low-level signal. When the second pressure comparison signal of the heel is greater than the second pressure threshold, it indicates that the heel is in contact with the ground; therefore, the second pressure comparison signal of the heel can be modulated into a high-level signal. When the second pressure comparison signal of the heel is not greater than the second pressure threshold, it indicates that the heel has detached from the ground or has not yet fully contacted the ground; therefore, the second pressure comparison signal of the heel can be modulated into a low-level signal.

[0122] In some embodiments, when the sum of the first pressure comparison signal and the second pressure comparison signal is greater than a third pressure threshold, it indicates that the sole of the foot is in contact with the ground. When the sum of the first pressure comparison signal and the second pressure comparison signal is not greater than the third pressure threshold, it indicates that the sole of the foot has detached from the ground or has not made complete contact.

[0123] Normally, when a person's foot touches the ground, the pressure signal at different designated foot positions will exhibit different amplitude changes. For example, when the right foot touches the ground, the pressure signal at the right heel and the right toe will exhibit different amplitude changes. However, both the right heel and the right toe are in contact with the ground. Therefore, in order to generate level signals that can match different designated foot positions more accurately and reliably, this embodiment can pre-calculate the pressure threshold corresponding to each designated foot position so that the pressure comparison signal at each designated foot position can be compared with the pressure threshold corresponding to each designated foot position.

[0124] In some embodiments, when calculating the first pressure threshold of the toe, in this embodiment, subject A is selected to wear the signal acquisition shoes to walk, where the weight of subject A is W. Please continue to combine Figure 4 , in this embodiment, the pressure signals of all the pressure sensors on the toe 10a are filtered through a low-pass filter with a frequency of 6 Hz, and the peak values of the pressure signals of each pressure sensor are extracted, and the peak value average avgf1 of all the pressure sensors distributed on the toe 10a is obtained. In the above manner, this embodiment selects subject A for the peak value average avgf1 of n gait cycles, and obtains the average value of the n peak value averages avgf1 to obtain the optimal peak avgf2. Finally, this embodiment adopts a preset scaling factor k, where 0 < k < 1, and usually defaults to k = 0.6. Finally, the first pressure threshold th1 = k * avgf2.

[0125] Similarly, when calculating the second pressure threshold of the toe, in this embodiment, the peak value average avgf3 of all the pressure sensors distributed on the heel 10c is obtained, and the average value of the n peak value averages avgf3 is obtained to obtain the optimal peak avgf4. Finally, the second pressure threshold th2 = k * avgf4.

[0126] When calculating the third pressure threshold of the sole of the foot, in this embodiment, the peak value average avgf1 of all the pressure sensors distributed on the toe 10a and the peak value average avgf3 of all the pressure sensors distributed on the heel 10c are obtained respectively, and the average values of the n peak value averages avgf1 and avgf3 are obtained to obtain the optimal peak avgf5. Finally, the third pressure threshold th3 = k * avgf5.

[0127] In S722, this embodiment can select the level signals of the right heel, the right toe, the left heel, and the left toe within the same detection duration, and determine the gait according to the above four level signals.

[0128] Typically, when the right leg transitions from the swing phase to the support phase, the pressure sensor on the right heel detects pressure, causing the level of the right heel signal to change from low to high, denoted as rh0->rh1, where "r" represents the first letter of "right" and "h" represents the first and last letters of "heel," "0" indicates a low level, and "1" indicates a high level. Then, within a short time, the pressure sensor on the right toe also detects pressure, causing the level of the right toe signal to change from low to high, denoted as rt0->rh1, where "t" represents "toe." During this process, the level of the left heel and left toe signals remains unchanged; that is, both are at a high level. The level of the left heel signal is denoted as lh1->lh1, and the level of the left toe signal is denoted as lt1->lt1, where "l" represents the first and last letters of "left." Overall, when the right leg moves from the swing phase to the support phase, the set of level changes of the four level signals is {(rh0->rh1),(rt0->rh1),(lh1->lh1),(lt1->lt1)}.

[0129] Similarly, when the left leg moves from the support phase to the swing phase, the set of level changes of the four level signals is {(rh1->rh1),(rt1->rh1),(lh1->lh0),(lt1->lt0)}.

[0130] When the left leg moves from the swing phase to the support phase, the set of level changes of the four level signals is {(rh1->rh1),(rt1->rh1),(lh0->lh1),(lt0->lt1)}.

[0131] When the right leg moves from the support phase to the swing phase, the set of level changes of the four level signals is {(rh1->rh0),(rt1->rh0),(lh1->lh1),(lt1->lt1)}.

[0132] As mentioned above, there are multiple ways to distinguish the four gaits from the four sets of level changes to determine the representative gait:

[0133] The first method:

[0134] When the right leg transitions from the swing phase to the support phase, the change in the level of the right heel landing (rh0->rh1) can distinguish "the right leg transitioning from the swing phase to the support phase" from the other three scenarios, thus determining the representative gait as the right foot landing.

[0135] Similarly, when the left leg moves from the support phase to the swing phase, the change in the level of the left heel leaving the ground, lh1->lh0, can distinguish the "left leg moving from the support phase to the swing phase" from the other three situations, thereby determining that the representative gait is the left foot leaving the ground.

[0136] When the left leg transitions from the swing phase to the support phase, the change in the level of the left heel landing (lh0->lh1) can distinguish "the left leg transitioning from the swing phase to the support phase" from the other three situations, thus determining the representative gait as left foot landing.

[0137] When the right leg transitions from the support phase to the swing phase, the change in the level of the right heel leaving the ground (rh1->rh0) can distinguish "the right leg transitioning from the support phase to the swing phase" from the other three situations, thereby determining the representative gait as the right foot leaving the ground.

[0138] The second method:

[0139] When the right leg transitions from the swing phase to the support phase, the level change rt0->rt1 of the right toe landing can distinguish "the right leg transitioning from the swing phase to the support phase" from the other three situations, thereby determining the representative gait as right foot landing.

[0140] Similarly, when the left leg moves from the support phase to the swing phase, the change in the level of the left toe leaving the ground from lt1 to lt0 can distinguish "the left leg moving from the support phase to the swing phase" from the other three situations, thereby determining that the representative gait is the left foot leaving the ground.

[0141] When the left leg transitions from the swing phase to the support phase, the level change of the left toe landing from lt0 to lt1 can distinguish "the left leg transitioning from the swing phase to the support phase" from the other three situations, thereby determining the representative gait as left foot landing.

[0142] When the right leg transitions from the support phase to the swing phase, the change in the level of the right toe on the ground from rt1 to rt0 can distinguish the "right leg transitioning from the support phase to the swing phase" from the other three situations, thereby determining the representative gait as the right foot leaving the ground.

[0143] The third method:

[0144] The third method combines the level changes of the heel and toe under the same detection duration of the first and second methods to determine the representative gait. For example, when the right leg enters the support phase from the swing phase, the level changes of the right heel landing rh0->rh1 and the level changes of the right toe landing rt0->rt1 are combined to determine the representative gait as right foot landing.

[0145] The fourth method:

[0146] The fourth method is to combine the level changes of the right heel, right toe, left heel, and left toe during the same detection period to determine the representative gait.

[0147] The first method is the most efficient at determining representative gait. The second method is the next most efficient. The third method is relatively efficient and reliable. The fourth method is the most reliable.

[0148] In some embodiments, when a level change is detected in one of the level signals at each specified foot position in the plantar pressure data, the gait is determined based on each level signal, thus enabling rapid gait detection in this embodiment.

[0149] In some embodiments, please refer to Figure 13 S722 includes:

[0150] S7221: Detects level changes for each level signal.

[0151] S7222: Select the level signal whose level changes as the target level signal.

[0152] S7223: Determine the representative gait based on the level change of the target level signal.

[0153] In step S7221, this embodiment sequentially scans the level signal of each specified foot position on each side of the foot, for example, sequentially scanning the level signal of the right heel, the level signal of the right toe, the level signal of the left heel and the level signal of the left toe.

[0154] In step S7222, this embodiment detects whether each level signal changes from low to high or from high to low. If the level signal changes from low to high or from high to low, then the level signal is selected as the target level signal.

[0155] As mentioned earlier, when the right leg moves from the swing phase to the support phase, the voltage level of the right heel changes from low to high. Subsequently, the voltage level of the right toe changes from low to high. Therefore, both the voltage level of the right heel and the voltage level of the right toe can be considered target voltage levels. Similarly, when the left leg moves from the support phase to the swing phase, both the voltage level of the left heel and the voltage level of the left toe can be considered target voltage levels, which will not be elaborated upon here.

[0156] In step S7223, this embodiment can determine the representative gait according to any of the four methods described above. In some embodiments, the target level signal includes a first level signal and a second level signal. Given that the first level signal is the level signal of the right heel and the second level signal is the level signal of the right toe, if both the level changes of the first and second level signals are from low to high, the gait represents a right foot landing. If both the level changes of the first and second level signals are from high to low, the gait represents a right foot leaving the ground. Similarly, given that the first level signal is the level signal of the left heel and the second level signal is the level signal of the left toe, if both the level changes of the first and second level signals are from low to high, the gait represents a left foot landing. If both the level changes of the first and second level signals are from high to low, the gait represents a left foot leaving the ground.

[0157] Normally, a person's gait during walking is continuous. Specifically, the time difference between the heel strike of one foot and the heel lift-off of the other foot fluctuates within a specified time range, and / or, the time difference between heel lift-off and heel strike on the same side also fluctuates within a specified time range. However, in some abnormal situations, the above-mentioned time differences may fall outside the specified time range. For example, the time difference may be less than the minimum endpoint of the specified time range, or greater than the maximum endpoint of the specified time range.

[0158] In some embodiments, before generating walking recognition information, please refer to Figure 14 Exoskeleton-based walking recognition methods also include:

[0159] S74: Determine the time difference between two adjacent representative gaits.

[0160] S75: Determine whether the time difference is within the specified time range corresponding to the two adjacent representative gaits.

[0161] S76: If present, then both adjacent representative gaits are determined to be normal gaits;

[0162] S77: If not, then both adjacent representative gaits are determined to be abnormal gaits.

[0163] In S74, two adjacent representative gaits include a first representative gait and a second representative gait, with the time of the first representative gait being earlier than the time of the second representative gait. When the first representative gait is determined among two adjacent representative gaits, the control timer records the starting timing point. When the second representative gait is determined among two adjacent representative gaits, the control timer records the ending timing point. The difference between the ending timing point and the starting timing point is calculated to obtain the time difference.

[0164] In some embodiments, when the first representative gait of two adjacent representative gaits is determined, a reset signal is sent to the timer. The timer clears the recorded time point according to the reset signal and starts the timing operation.

[0165] In S75, the specified time range can be set by the designer based on experience.

[0166] Typically, the time difference between heel strike on one foot and heel liftoff on the other foot is 12% of the gait cycle time. For example, the time difference between heel strike on the right foot and heel liftoff on the left foot is 12% of the gait cycle time, or vice versa. The time difference between heel liftoff and landing on the same side is 38% of the gait cycle time. For example, the time difference between heel liftoff and landing on the left foot is 38% of the gait cycle time, or vice versa. Therefore, the specified time range corresponding to heel strike on one foot and heel liftoff on the other foot can be set to 8% to 15% of the gait cycle time, or the specified time range corresponding to heel liftoff and landing on the same side can be set to 30% to 45% of the gait cycle time.

[0167] In S76, if the time difference is within the specified time range corresponding to the two adjacent representative gaits, then the two adjacent representative gaits are determined to be normal gaits.

[0168] In S77, if the time difference is not within the specified time range corresponding to the two adjacent representative gaits, then the two adjacent representative gaits are determined to be abnormal gaits. For example, if the user starts with the right foot forward and supports the body with both feet, and stays there for a long time before the left foot leaves the ground to start walking, the detected time difference will be relatively large, and it can be considered that the user is not walking periodically. This can eliminate some abnormal movements, which is beneficial to improving the reliability of the system and avoiding misjudgment.

[0169] To illustrate the pedestrian recognition process in this embodiment of the disclosure in detail, this embodiment combines... Figure 15 The following is a detailed explanation of this:

[0170] Please see Figure 15 The user stands with both legs apart, and begins to swing their right leg as they step. The voltage changes of the right heel, right toe, left heel, and left toe as the right leg transitions from the swing phase to the support phase are as follows:

[0171] {(rh0->rh1),(rt0->rh1),(lh1->lh1),(lt1->lt1)}.

[0172] In this embodiment, the gait can be determined as right foot landing ① based on the changes in the voltage levels of the right heel and the right toe.

[0173] Once the right toe touches the ground, the exoskeleton sends a reset signal to the timer. The timer then clears the recorded time point based on the reset signal and starts the timing operation.

[0174] Next, as the left leg moves from the support phase to the swing phase, the set of level changes for the four level signals is as follows:

[0175] {(rh1->rh1),(rt1->rh1),(lh1->lh0),(lt1->lt0)}.

[0176] In this embodiment, the representative gait can be determined as left foot off the ground ② based on the level change of the left heel and the level change of the left toe.

[0177] Since the time difference between the right heel landing and the left heel leaving the ground is 12% of the gait cycle time, both right foot landing ① and left foot leaving the ground ② are normal gaits.

[0178] In addition, once the left toe is off the ground, the exoskeleton sends a reset signal to the timer. The timer then clears the recorded time point and starts timing based on the reset signal.

[0179] Next, as the left leg transitions from the swing phase to the support phase, the set of level changes for the four level signals is as follows:

[0180] {(rh1->rh1),(rt1->rh1),(lh0->lh1),(lt0->lt1)}.

[0181] In this embodiment, the representative gait can be determined as left foot landing ③ based on the level changes of the left heel and the left toe.

[0182] Since the time difference between the left heel leaving the ground and the left heel landing is 38% of the gait cycle time, both the left heel leaving the ground ② and the left heel landing ③ are normal gaits.

[0183] In addition, once the left toe touches the ground, the exoskeleton sends a reset signal to the timer. The timer then clears the recorded time point based on the reset signal and starts the timing operation.

[0184] Next, as the right leg moves from the support phase to the swing phase, the set of level changes for the four level signals is as follows:

[0185] {(rh1->rh0),(rt1->rh0),(lh1->lh1),(lt1->lt1)}.

[0186] In this embodiment, the gait can be determined as right foot off the ground ④ based on the level changes of the right heel and the right toe.

[0187] Since the time difference between the left heel landing and the right heel leaving the ground is 12% of the gait cycle time, both left foot landing ③ and right foot leaving the ground ④ are normal gaits.

[0188] In addition, once the right toe leaves the ground, the exoskeleton sends a reset signal to the timer. The timer then clears the recorded time point based on the reset signal and starts the timing operation.

[0189] And so on, without going into detail here.

[0190] Therefore, this embodiment yields the following target gait sequence: right foot landing ① -> left foot leaving the ground ② -> left foot landing ③ -> right foot leaving the ground ④. This embodiment compares the target gait sequence with the preset gait sequence. Since the two match, walking confirmation information is generated. The exoskeleton then enters walking assistance mode, carrying the user while walking, thus reducing the burden on the user.

[0191] It should be noted that in the above embodiments, there is no necessarily a certain order between the steps. Those skilled in the art can understand from the description of the embodiments of this disclosure that the steps may have different execution orders in different embodiments, that is, they may be executed in parallel or in interchange, etc.

[0192] Please see Figure 16 , Figure 16 This is a schematic diagram of the circuit structure of a controller provided in an embodiment of this disclosure. Figure 16 As shown, the controller 800 includes one or more processors 81 and a memory 82. Wherein, Figure 8 Take the 81 processor as an example.

[0193] Processor 81 and memory 82 can be connected via a bus or other means. Figure 16 Taking the example of a connection between China and Israel via a bus.

[0194] The memory 82, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the exoskeleton-based walking recognition method in the embodiments of this disclosure. The processor 81 implements the function of the exoskeleton-based walking recognition method provided in the above method embodiments by running the non-volatile software programs, instructions, and modules stored in the memory 82.

[0195] Memory 82 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 82 may optionally include memory remotely located relative to processor 81, which can be connected to processor 81 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0196] The program instructions / modules are stored in the memory 82 and, when executed by one or more processors 81, execute the exoskeleton-based walking recognition method in any of the above method embodiments.

[0197] This disclosure also provides a storage medium storing computer-executable instructions that are executed by one or more processors, for example... Figure 16 One of the processors 81 can enable the one or more processors to execute the exoskeleton-based walking recognition method in any of the above method embodiments.

[0198] This disclosure also provides a computer program product, the computer program product including a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions, which, when executed by a controller, cause the controller to perform any of the exoskeleton-based walking recognition methods described above.

[0199] The device or equipment embodiments described above are merely illustrative. The unit modules described as separate components may or may not be physically separate. The components shown as module units may or may not be physical units; that is, they may be located in one place or distributed across multiple network module units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0200] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0201] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and not to limit them; under the concept of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of this disclosure as described above, which are not provided in detail for the sake of brevity; although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A walking recognition method based on an exoskeleton, characterized in that, include: Acquire plantar pressure data, wherein the plantar pressure data includes pressure signals at specified foot positions on each foot during the same detection time when the user is walking while wearing the exoskeleton. Determining a representative gait based on the plantar pressure data includes: generating a level signal for each specified foot position based on the plantar pressure data; determining a representative gait based on each level signal; wherein multiple representative gaits that are consecutive in time can form a target gait time sequence. Based on the target gait timing and the preset gait timing, walking recognition information is generated.

2. The method according to claim 1, characterized in that, The step of determining the representative gait based on each of the said level signals includes: Detect the level change of each of the stated level signals; Select the level signal whose level changes as the target level signal; The representative gait is determined based on the level change of the target level signal.

3. The method according to claim 2, characterized in that, The target level signal includes a first level signal and a second level signal. Determining the representative gait based on the level change of the target level signal includes: Given that the first level signal is the level signal of the right heel and the second level signal is the level signal of the right toe, if the level changes of both the first level signal and the second level signal are from low to high, then the gait represents the right foot landing; if the level changes of both the first level signal and the second level signal are from high to low, then the gait represents the right foot leaving the ground. Given that the first level signal is the level signal of the left heel and the second level signal is the level signal of the left toe, if the level changes of both the first level signal and the second level signal are from low to high, then the representative gait is left foot landing; if the level changes of both the first level signal and the second level signal are from high to low, then the representative gait is left foot off the ground.

4. The method according to claim 1, characterized in that, The step of generating a level signal for each specified foot position based on the plantar pressure data includes: Based on the pressure signal at each specified foot position, generate a pressure comparison signal for each specified foot position; Determine whether the pressure comparison signal at each specified foot position is greater than the pressure threshold corresponding to the specified foot position; If the value is greater than the specified foot position, a high-level signal is generated for each of the specified foot positions. If it is less than or equal to, a low-level signal is generated for each specified foot position.

5. The method according to claim 1, characterized in that, Multiple preset gait time sequences are configured in a gait time sequence library. The walking recognition information includes walking confirmation information or non-walking information. The step of generating walking recognition information based on the target gait time sequence and the preset gait time sequence includes: Determine whether the target gait timing matches any preset gait timing in the gait timing library; If a match is found, a walking confirmation message is generated; If there is no match, non-walking information is generated.

6. The method according to any one of claims 1 to 5, characterized in that, Before generating walking recognition information, the following is also included: Determine the time difference between two adjacent representative gaits; Determine whether the time difference is within a specified time range corresponding to two adjacent representative gaits; If present, then both adjacent representative gaits are determined to be normal gaits; If not, then both adjacent representative gaits are determined to be abnormal gaits.

7. A storage medium, characterized in that, The device stores computer-executable instructions for causing the controller to perform the exoskeleton-based walking recognition method as described in any one of claims 1 to 6.

8. A signal acquisition shoe, characterized in that, include: The shoe itself; Multiple sets of pressure sensor assemblies, each set of pressure sensors is arranged at a designated foot position on the shoe body; A controller, electrically connected to each of the pressure sensors, is used to perform the exoskeleton-based walking recognition method as described in any one of claims 1 to 6.

9. An exoskeleton, characterized in that, include: Back frame assembly; Waist frame assembly, connected to the back frame assembly; Lower limb assembly, connected to the waist frame assembly; and The signal acquisition shoe as described in claim 8, wherein the signal acquisition shoe is connected to the lower limb assembly.

Images