Exoskeleton-based gait determination method, exoskeleton and electronic device

Abstract

The present disclosure relates to the field of human bionics, and discloses a gait determination method based on an exoskeleton, an exoskeleton and an electronic device. The gait determination method based on the exoskeleton comprises: acquiring a waist inclination angle, wherein the waist inclination angle is an inclination angle of a human waist relative to a reference direction after the human wears the exoskeleton; determining a direction characteristic value, wherein the direction characteristic value is used to represent a moving direction of a human leg relative to a corresponding side mechanical leg in the exoskeleton; and determining a gait according to the waist inclination angle and the direction characteristic value. The embodiment does not need to process too much gait characteristic data, and can determine the gait by using the waist inclination angle and the direction characteristic value, which is beneficial to improve the recognition efficiency of the gait, so as to efficiently control the exoskeleton to work, thereby improving the coordination between the exoskeleton and the human body.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of human bionics, and particularly relates to a gait determination method based on an exoskeleton, an exoskeleton and an electronic device. BACKGROUND

[0002] As wearable mechanical devices with strong functions, human mechanical exoskeletons are increasingly valued by many scholars and researchers at home and abroad and become a new research hotspot. Human mechanical exoskeletons need to quickly and accurately predict human motion intentions so as to effectively control the walking of human mechanical exoskeletons. Therefore, human mechanical exoskeletons need to determine the gait of a human body, and main gaits include a sitting gait, a standing gait, a slow running gait, a walking gait, an up-stair gait and a down-stair gait.

[0003] The prior art generates 86 gait characteristic data for the above six kinds of activities, and the 86 gait characteristic data include the average value (6), the standard deviation (6), the average absolute difference (6), the average synthetic acceleration (2), the time difference between the peak values (6) and the merged distribution (60) of each axis. Since there are many gait characteristic data, the prior art needs to consume more operation time to process the above gait characteristic data, so as to determine the gait. Therefore, the efficiency of determining the gait by the prior art is not high.

[0004] SUMMARY

[0005] An object of an embodiment of the present disclosure is to provide a gait determination method based on an exoskeleton, an exoskeleton and an electronic device, and to improve the problem that the efficiency of determining the gait by the prior art is relatively low.

[0006] In a first aspect, an embodiment of the present disclosure provides a gait determination method based on an exoskeleton, comprising:

[0007] obtaining a waist inclination angle, wherein the waist inclination angle is an inclination angle of a waist of a human body relative to a reference direction after the human body wears the exoskeleton;

[0008] determining a direction characteristic value, wherein the direction characteristic value is used to represent a moving direction of a leg of the human body relative to a corresponding side mechanical leg in the exoskeleton;

[0009] determining a gait according to the waist inclination angle and the direction characteristic value.

[0010] Optionally, the exoskeleton comprises a trunk mechanical part and an angle sensor, the angle sensor is installed on a waist position of the trunk mechanical part, and the angle sensor abuts against the waist of the human body after the human body wears the exoskeleton, and is used to collect the waist inclination angle.

[0011] Optionally, determining the direction characteristic value comprises:

[0012] acquiring a leg pressure signal, wherein the mechanical leg is provided with a pressure detection component, when the human leg approaches or moves away from the corresponding mechanical leg, the human leg triggers the pressure detection component to generate different leg pressure signals;

[0013] determining a pressure direction according to the leg pressure signal;

[0014] determining a direction feature value according to the pressure direction.

[0015] Optionally, the leg pressure signal includes a first leg pressure signal and / or a second leg pressure signal;

[0016] The pressure detection component includes a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on the opposite sides of the human leg before and after;

[0017] The pressure detection component at the first pressure detection point can detect the first leg pressure signal when the human leg approaches the corresponding mechanical leg;

[0018] The pressure detection component at the second pressure detection point can detect the second leg pressure signal when the human leg moves away from the corresponding mechanical leg.

[0019] Optionally, the determining of the pressure direction according to the leg pressure signal includes:

[0020] If the first pressure detection point detects the first leg pressure signal, it is determined that the pressure direction is a positive pressure direction;

[0021] If the second pressure detection point detects the second leg pressure signal, it is determined that the pressure direction is a negative pressure direction;

[0022] If neither the first pressure detection point nor the second pressure detection point detects the leg pressure signal, it is determined that the pressure direction is a neutral pressure direction.

[0023] Optionally, the determining of the pressure direction according to the leg pressure signal includes:

[0024] determining a pressure change trend according to the first leg pressure signal and the second leg pressure signal;

[0025] If the pressure change trend is that the first leg pressure signal becomes stronger and the second leg pressure signal becomes weaker, it is determined that the pressure direction is a positive pressure direction;

[0026] if the pressure change trend is that the first leg pressure signal becomes weak from strong and the second leg pressure signal becomes strong from weak, it is determined that the pressure direction is a negative pressure direction;

[0027] if the pressure change trend is that the first leg pressure signal and the second leg pressure signal remain unchanged, it is determined that the pressure direction is a neutral pressure direction.

[0028] Optionally, the determining the direction feature value according to the pressure direction comprises:

[0029] if the pressure direction is a positive pressure direction, it is determined that the direction feature value is a positive feature value, wherein the positive feature value is used to represent that the human leg is close to the corresponding side mechanical leg in the exoskeleton;

[0030] if the pressure direction is a negative pressure direction, it is determined that the direction feature value is a negative feature value, wherein the negative feature value is used to represent that the human leg is away from the corresponding side mechanical leg in the exoskeleton;

[0031] if the pressure direction is a neutral pressure direction, it is determined that the direction feature value is a neutral feature value, wherein the neutral feature value is used to represent that the relative position of the human leg and the corresponding side mechanical leg in the exoskeleton remains unchanged.

[0032] Optionally, the gait comprises at least one of a sitting gait, a standing gait, a slow running gait, a walking gait, an up-stair gait and a down-stair gait, and the determining the gait according to the waist inclination angle and the direction feature value comprises:

[0033] inputting the waist inclination angle, the direction feature value and the leg pressure signal into an SVM classifier to obtain the gait.

[0034] In a second aspect, the embodiments of the present disclosure provide an exoskeleton, comprising:

[0035] a trunk mechanical part;

[0036] an angle sensor installed at a waist position of the trunk mechanical part, abutting against the human waist when the human wears the exoskeleton, used to detect an inclination angle of the human waist relative to a reference direction to obtain a waist inclination angle;

[0037] a mechanical leg connected with the trunk mechanical part;

[0038] a sensor module installed on the mechanical leg, used to detect a moving direction of the human leg relative to the corresponding side mechanical leg in the exoskeleton to obtain a direction feature value;

[0039] a power assembly mounted on the trunk mechanical part and connected with the mechanical leg parts;

[0040] a controller mounted on the trunk mechanical part and electrically connected with the angle sensor, the sensor module and the power assembly, for executing the above-mentioned exoskeleton-based gait determination method and controlling the power assembly to drive the mechanical leg parts to work according to the gait.

[0041] Optionally, the sensor module comprises a pressure detection assembly mounted on the corresponding mechanical leg part, which is triggered by the human leg part to generate a leg pressure signal when the human leg part approaches or moves away from the corresponding mechanical leg part.

[0042] Optionally, the leg pressure signal comprises a first leg pressure signal and / or a second leg pressure signal.

[0043] The pressure detection assembly comprises a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on opposite sides of the human leg part.

[0044] The pressure detection assembly can detect a first leg pressure signal when the human leg part approaches the corresponding mechanical leg part at the first pressure detection point.

[0045] The pressure detection assembly can detect a second leg pressure signal when the human leg part moves away from the corresponding mechanical leg part at the second pressure detection point.

[0046] In a third aspect, the embodiments of the present disclosure provide a storage medium storing computer executable instructions for causing an electronic device to execute the above-mentioned exoskeleton-based gait determination method.

[0047] In a fourth aspect, the embodiments of the present disclosure provide an electronic device comprising:

[0048] at least one processor; and

[0049] a memory in communication connection with the at least one processor; wherein

[0050] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned exoskeleton-based gait determination method.

[0051] In the exoskeleton-based gait determination method provided in this embodiment, the waist tilt angle is obtained. This waist tilt angle is the tilt angle of the human waist relative to a reference direction when the human wears the exoskeleton. A directional feature value is determined, representing the direction of movement of the human leg relative to the corresponding mechanical leg on the exoskeleton. The gait is determined based on the waist tilt angle and the directional feature value. This embodiment does not require processing excessive gait feature data; the gait can be determined using only the waist tilt angle and the directional feature value, which improves gait recognition efficiency and enables efficient control of the exoskeleton, thereby enhancing the coordination between the exoskeleton and the human body. Attached Figure Description

[0052] 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.

[0053] Figure 1 This is a schematic diagram of the structure of an exoskeleton provided in an embodiment of the present disclosure;

[0054] Figure 2 A schematic diagram of the circuit structure of an exoskeleton provided in an embodiment of this disclosure;

[0055] Figure 3 A left view of an exoskeleton provided in an embodiment of this disclosure;

[0056] Figure 4 for Figure 1 The diagram shows the structure of the hip joint and the mechanical leg.

[0057] Figure 5 A flowchart illustrating an exoskeleton-based gait determination method provided in this embodiment of the present disclosure;

[0058] Figure 6 A schematic diagram of the structure of an exoskeleton-based gait determination device provided in an embodiment of this disclosure;

[0059] Figure 7 This is a schematic diagram of the circuit structure of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0060] 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.

[0061] It should be noted that various features of the embodiments of the present disclosure can be combined with each other, and all within the protection scope of the present disclosure, if there is no conflict. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. Furthermore, the "first", "second", "third" and the like used in the present disclosure do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0062] The present disclosure provides an exoskeleton, please refer to Figure 1 With Figure 2 , the exoskeleton 100 includes a trunk mechanical part 200, an angle sensor 300, a mechanical leg part 400, a sensor module 500, a power assembly 600 and a controller 700.

[0063] The trunk mechanical part 200 is used to carry the power assembly 600 and various components, wherein the trunk mechanical part 200 is a bionic structure, and the shape of the trunk mechanical part 200 is adapted to the shape of the body.

[0064] In some embodiments, the trunk mechanical part 200 includes a trunk mechanical body 21 and a hip joint part 22, and the hip joint part 22 is connected with the trunk mechanical part 22, wherein the trunk mechanical body 21 is plate-shaped, and the hip joint part 22 is a bionic structure of the human hip, and the shape of the hip joint part 22 is adapted to the shape of the human hip.

[0065] The angle sensor 300 is installed on the waist position of the trunk mechanical part 200, wherein when the human body wears the exoskeleton 100, the angle sensor 300 abuts against the waist of the human body, and is used to detect the inclination angle of the waist of the human body relative to the reference direction, so as to obtain the waist inclination angle. The waist inclination angle is used to represent the degree of deviation of the waist of the human body from the reference direction, wherein the reference direction is a fixed reference direction defined by the designer. In some embodiments, the reference direction is a direction perpendicular to the ground. Generally, when the exoskeleton is in a standing state, the plane where the trunk mechanical part 200 is located will pass through the perpendicular line perpendicular to the ground, therefore, the reference line of the reference direction is parallel to the plane where the trunk mechanical part 200 is located.

[0066] In some embodiments, the waist position of the trunk mechanical part 200 is provided with a waist connecting belt, and the angle sensor 300 is arranged on the waist connecting belt. When the human body wears the exoskeleton 100, the waist connecting belt can be closely connected to the waist of the human body, and the angle sensor 300 can also abut against the waist of the human body. When the waist of the human body bends or tilts, the waist of the human body will drive the waist connecting belt and the angle sensor 300 to move in the same direction, and the angle sensor 300 can detect the tilt angle of the waist of the human body relative to the reference direction to obtain the waist tilt angle.

[0067] In some embodiments, the angle sensor 300 is an IMU sensor or a gyroscope.

[0068] The mechanical leg part 400 is used to support the ground to drive the trunk mechanical part 200 to move, wherein the mechanical leg part 400 is a bionic structure of the human leg, and the shape of the mechanical leg part 400 is matched with the shape of the human leg.

[0069] In some embodiments, please combine Figure 3 With Figure 4 , the mechanical leg part 400 includes a left mechanical leg part 41 and a right mechanical leg part 42.

[0070] The left mechanical leg part 41 and the right mechanical leg part 42 are respectively installed on opposite sides of the hip joint part 22. The left mechanical leg part 41 includes a left mechanical thigh part 411, a left knee joint part 412, and a left mechanical shank part 413, and the left mechanical thigh part 411 is connected to the left mechanical shank part 413 through the left knee joint part 412.

[0071] The right mechanical leg part 42 includes a right mechanical thigh part 421, a right knee joint part 422, and a right mechanical shank part 423, and the right mechanical thigh part 421 is connected to the right mechanical shank part 423 through the right knee joint part 422.

[0072] In some embodiments, the left mechanical thigh part 411, the left mechanical shank part 413, the right mechanical thigh part 421, and the right mechanical shank part 423 are all provided with a binding belt, and when the human body wears the exoskeleton 100, the binding belt of each side of the thigh and the shank part can be used to stabilize the human body on the exoskeleton 100, so that the human leg and the mechanical leg part can be closely attached.

[0073] The sensor module 500 is installed on the mechanical leg 400, and is configured to detect a moving direction of the human leg relative to the corresponding mechanical leg in the exoskeleton 100, so as to obtain a direction characteristic value. For example, the sensor module 500 is configured to detect a moving direction of the left human leg (left human thigh, left human calf, right human leg, right human thigh, right human calf) relative to the left mechanical leg 41 (left mechanical thigh, left mechanical calf, right mechanical leg, right mechanical thigh, right mechanical calf), so as to obtain a direction characteristic value.

[0074] The direction characteristic value is configured to represent the moving direction of the human leg relative to the corresponding mechanical leg in the exoskeleton 100. In some embodiments, the direction characteristic value can be represented by data in any data format, such as the direction characteristic value being 0, which is configured to represent that the human leg is close to the corresponding mechanical leg in the exoskeleton 100. For example, the direction characteristic value is 1, which is configured to represent that the human leg is away from the corresponding mechanical leg in the exoskeleton 100.

[0075] The power assembly 600 is installed on the trunk mechanical part 200 and connected with the mechanical leg 400, and is configured to drive the mechanical leg 400 to work. In some embodiments, the power assembly 600 is a hydraulic driving mechanism composed of an oil tank, a hydraulic pump, a hydraulic cylinder, a motor, a pipeline and a solenoid valve.

[0076] The controller 700 is installed on the trunk mechanical part 200 and electrically connected with the angle sensor 300, the sensor module 500 and the power assembly 600, and is configured to execute the gait determination method based on the exoskeleton described in various embodiments below, and control the power assembly 600 to drive the mechanical leg 200 to work according to the gait.

[0077] In some embodiments, when the controller 700 determines that the gait is a sitting gait, a standing gait, a jogging gait, a walking gait, a stair climbing gait or a stair descending gait, the controller 700 controls the power assembly 600 to drive the mechanical leg 200 to perform a sitting operation, a standing operation, a jogging operation, a walking operation, a stair climbing operation or a stair descending operation.

[0078] In some embodiments, the sensor module 500 is a pressure detection assembly, which is arranged on the mechanical leg 200. When the human leg is close to or away from the corresponding mechanical leg, the human leg triggers the pressure detection assembly to generate different leg pressure signals.

[0079] In some embodiments, the leg pressure signal includes a first leg pressure signal and / or a second leg pressure signal. The pressure detection assembly includes a first pressure detection point and a second pressure detection point, which are respectively located on the front and back sides of the human leg. When the human wears the exoskeleton, the first pressure detection point is opposite to the front side of the mechanical leg, wherein the front side of the mechanical leg is the side of the mechanical leg facing the forward direction of the exoskeleton. The second pressure detection point is opposite to the back side of the mechanical leg, wherein the back side of the mechanical leg is the side opposite to the front side. It should be noted that the "front" and "back" directions herein are consistent with the front side and the back side of the human leg.

[0080] The pressure detection assembly can detect the first leg pressure signal of the human leg when the human leg is close to the corresponding side of the mechanical leg at the first pressure detection point. The pressure detection assembly can detect the second leg pressure signal of the human leg when the human leg is away from the corresponding side of the mechanical leg at the second pressure detection point, so as to improve the reliability of the pressure detection assembly in following the moving direction of the human leg and the corresponding side of the mechanical leg. It should be noted that the "close to" and "away from" mentioned herein are both with reference to the position in the mechanical leg corresponding to the first pressure detection point. When the human leg is close to the reference point, it is considered that the human leg is close to the mechanical leg. When the human leg is away from the reference point, it is considered that the human leg is away from the mechanical leg.

[0081] When the human leg (left human leg / left human thigh / left human calf / right human leg / right human thigh / right human calf) is close to the corresponding side of the mechanical leg (left mechanical leg / left mechanical thigh / left mechanical calf / right mechanical leg / right mechanical thigh / right mechanical calf), the human leg presses the pressure detection assembly at the first pressure detection point, triggering the pressure detection assembly to generate the first leg pressure signal.

[0082] When the human leg (left human leg / left human thigh / left human calf / right human leg / right human thigh / right human calf) is away from the corresponding side of the mechanical leg (left mechanical leg / left mechanical thigh / left mechanical calf / right mechanical leg / right mechanical thigh / right mechanical calf), the human leg presses the pressure detection assembly at the second pressure detection point, triggering the pressure detection assembly to generate the second leg pressure signal.

[0083] In some embodiments, the mechanical leg comprises a ring-shaped accommodating portion which can at least partially surround the side of the human leg facing the mechanical leg and the side of the human leg away from the mechanical leg when the human body wears the exoskeleton, and the pressure detection assembly is arranged on the ring-shaped accommodating portion, wherein the first pressure detection point of the pressure detection assembly is located at a first position of the ring-shaped accommodating portion, and the second pressure detection point of the pressure detection assembly is located at a second position of the ring-shaped accommodating portion, the first position being a position of the ring-shaped accommodating portion opposite to the front side of the human leg, and the second position being a position of the ring-shaped accommodating portion opposite to the back side of the human leg. It can be understood that the first position is the reference point described above.

[0084] In some embodiments, the pressure detection assembly is arranged to extend around the inner side of the ring-shaped accommodating portion, so as to comprehensively detect the leg pressure signals generated when the human leg moves away from or approaches the mechanical leg.

[0085] In some embodiments, since the muscle activity and bone activity of the knee joint of the human body are more obvious under various gaits, in order to more reliably and sensitively collect the actions of the human body under different gaits, a ring-shaped accommodating portion can be formed on the side of the mechanical thigh and / or the mechanical lower leg close to the knee joint portion, and a pressure detection assembly can be arranged on the ring-shaped accommodating portion.

[0086] The first pressure detection assembly is arranged at the position of the left mechanical thigh close to the left knee joint portion, and the second pressure detection assembly is arranged at the position of the left mechanical lower leg close to the left knee joint portion. The third pressure detection assembly is arranged at the position of the right mechanical thigh close to the right knee joint portion, and the fourth pressure detection assembly is arranged at the position of the right mechanical lower leg close to the right knee joint portion.

[0087] It can be understood that since the mechanical leg can be the left mechanical thigh or the left mechanical lower leg or the right mechanical thigh or the right mechanical lower leg, correspondingly, the ring-shaped accommodating portion can be the first ring-shaped accommodating portion or the second ring-shaped accommodating portion or the third ring-shaped accommodating portion or the fourth ring-shaped accommodating portion, wherein the first ring-shaped accommodating portion is formed on the side of the left mechanical thigh close to the knee joint portion, the second ring-shaped accommodating portion is formed on the side of the left mechanical lower leg close to the knee joint portion, the third ring-shaped accommodating portion is formed on the side of the right mechanical thigh close to the knee joint portion, and the fourth ring-shaped accommodating portion is formed on the side of the right mechanical lower leg close to the knee joint portion.

[0088] Correspondingly, the number of pressure detection assemblies is four, the first ring-shaped accommodating portion is provided with the first pressure detection assembly, the second ring-shaped accommodating portion is provided with the second pressure detection assembly, the third ring-shaped accommodating portion is provided with the third pressure detection assembly, and the fourth ring-shaped accommodating portion is provided with the fourth pressure detection assembly.

[0089] It is also understood that for each annular accommodating portion, the pressure detection assembly includes a first pressure detection point and a second pressure detection point, as previously described, the first pressure detection point is located at the first position of the annular accommodating portion, and the second pressure detection point is located at the second position of the annular accommodating portion.

[0090] In some embodiments, the annular accommodating portion is in the shape of a knee pad or a C letter, wherein the annular accommodating portion can be integrally formed with the knee of the mechanical leg.

[0091] In some embodiments, the pressure detection assembly can be a thin film pressure sensor, wherein the thin film pressure sensor is in the shape of a strip.

[0092] In some embodiments, the pressure detection assembly includes a first pressure detector and a second pressure detector, the first pressure detector is configured to provide the first pressure detection point, and is arranged at the first position of the annular accommodating portion. The second pressure detector is configured to provide the second pressure detection point, and is arranged at the second position of the annular accommodating portion. When the human leg approaches the mechanical leg and presses the first pressure detector at the first pressure detection point, the first pressure detector generates a first leg pressure signal, and thus, by detecting the first leg pressure signal, it can be determined that the human leg approaches the mechanical leg. When the human leg is away from the mechanical leg and presses the second pressure detector at the second pressure detection point, the second pressure detector generates a second leg pressure signal, and thus, by detecting the second leg pressure signal, it can be determined that the human leg is away from the mechanical leg.

[0093] It is understood that when a human wears an exoskeleton in different gaits, the inclination angle of the waist can change, and different leg pressure signals can be collected. Please refer to Table 1:

[0094] Table 1

[0095]

[0096] Table 2

[0097]

[0098]

[0099] It should be noted that the above gait analysis data, all of which involve leg movement, are taken as an example with the left foot in front, and all of which are based on the data collected at the beginning of the posture.

[0100] As shown in Table 1, the "left lower leg relative movement direction" label is used to represent the relative movement direction between the left human lower leg and the left mechanical lower leg, the "left upper leg relative movement direction" label is used to represent the relative movement direction between the left human upper leg and the left mechanical upper leg, the "right lower leg relative movement direction" label is used to represent the relative movement direction between the right human lower leg and the right mechanical lower leg, the "right upper leg relative movement direction" label is used to represent the relative movement direction between the right human upper leg and the right mechanical upper leg, the "waist" label is used to represent the relative movement direction between the human waist and the reference direction, and the "no force" label is used to represent that the relative position between the human leg and the corresponding mechanical leg remains unchanged, i.e., the human leg is not in contact with the corresponding mechanical leg.

[0101] As shown in Table 1, when the human body wears the exoskeleton and performs different gaits, the movement direction between the human leg and the mechanical leg will be different, and the inclination angle of the human waist relative to the reference direction will also be different.

[0102] As shown in Table 1, when the gait is sitting, when the human body wears the exoskeleton and sits down, the human leg is in a first position far away from each pressure detection component and in a second position close to each pressure detection component.

[0103] When the gait is standing, when the human body wears the exoskeleton and stands, the human leg remains between the first position and the second position.

[0104] When the gait is jogging, when the human body wears the exoskeleton and jogs, first, when the left foot steps forward, the left lower leg and the left upper leg are relatively close to the first position, and since the right lower leg and the right upper leg need to be bent and support the ground, the human body causes the second position of the right mechanical leg of the exoskeleton to be close to the right lower leg and the right upper leg of the human body, i.e., causes the first position of the right mechanical leg of the exoskeleton to be far away from the right lower leg and the right upper leg of the human body, and at the same time, when jogging, the inclination angle of the waist of the human body can reach 10 degrees to 30 degrees.

[0105] When the gait is walking, the process of the human leg moving away from or close to the mechanical leg is the same as that in the case of jogging, and the difference is that the inclination angle of the waist of the human body when walking is less than that when jogging.

[0106] When the gait is climbing stairs, when the human body wears the exoskeleton and climbs stairs, first, when the left foot steps forward, the left lower leg and the left upper leg are relatively close to the first position, at the same time, in order to help the human body load and climb the stairs, the human body leans forward, and the right knee of the human body is slightly bent, at this time, the right upper leg exerts force forward, and the right lower leg exerts force backward, i.e., the right upper leg is relatively close to the first position of the corresponding pressure detection component, and the right lower leg is relatively close to the second position of the corresponding pressure detection component.

[0107] When the gait is going down the stairs, the human body wears the exoskeleton and goes down the stairs, first, when the left foot steps forward, the left thigh is lifted up and the left shank is stretched out, thus, the left shank and the left thigh are relatively close to the first position of the corresponding pressure detection component, at the same time, in order to keep balance, the human body slightly leans back and the right knee of the human body slightly bends, the right shank and the right thigh bear the whole weight, at this time, the right thigh exerts force backward and the right shank exerts force forward, that is, the right thigh is relatively close to the second position of the corresponding pressure detection component and the right shank is relatively close to the first position of the corresponding pressure detection component.

[0108] As shown in Table 2, since the first leg pressure signal can represent the positive pressure direction exerted on the pressure detection component by the human leg when the human leg is close to the mechanical leg at the first pressure detection point, the positive pressure direction can represent the moving direction of the human leg close to the mechanical leg. The second leg pressure signal can represent the negative pressure direction exerted on the pressure detection component by the human leg when the human leg is away from the mechanical leg at the second pressure detection point, the negative pressure direction can represent the moving direction of the human leg away from the mechanical leg. The waist inclination angle can represent the inclination angle of the human waist relative to the reference direction, thus, by comprehensively determining the gait through the first leg pressure signal, the second leg pressure signal and the waist inclination angle.

[0109] In some embodiments, the pressure detection component is a thin film pressure sensor, the pressure detection component is arranged to extend around the inner side surface of the annular accommodating portion, when the human leg is close to the corresponding side mechanical leg, the pressure detection component is exerted with pressure at the first pressure detection point, the first leg pressure signal output at the first pressure detection point changes from weak to strong, the second leg pressure signal output at the second pressure detection point changes from strong to weak. When the human leg is away from the corresponding side mechanical leg at the second pressure detection point, the pressure detection component is exerted with pressure at the second pressure detection point, the second leg pressure signal output at the second pressure detection point changes from weak to strong, the first leg pressure signal output at the first pressure detection point changes from strong to weak. When the relative position between the human leg and the corresponding side mechanical leg remains unchanged, the first leg pressure signal and the second leg pressure signal are both 0 or a specified reference value.

[0110] Table 3

[0111]

[0112]

[0113] As shown in Table 3, the "first" label is used to represent the first leg pressure signal, and the "second" label is used to represent the second leg pressure signal.

[0114] As shown in Table 3, for the case that the same pressure detection assembly can simultaneously detect the first leg pressure signal and the second leg pressure signal, the first leg pressure signal or the second leg pressure signal will present different change trends in different gait states. By comprehensively considering the change trends of the first leg pressure signal and the second leg pressure signal, the gait state can be determined.

[0115] As another aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide a gait determination method based on an exoskeleton. Please refer to Figure 5 The gait determination method based on the exoskeleton comprises:

[0116] S51. Obtain a waist inclination angle, wherein the waist inclination angle is an inclination angle of a waist of a human body relative to a reference direction after the human body wears the exoskeleton.

[0117] In this step, as described above, the exoskeleton comprises a trunk mechanical part and an angle sensor, and the angle sensor is installed at a waist position of the trunk mechanical part. When the human body wears the exoskeleton, the angle sensor abuts against the waist of the human body, and is used to obtain the waist inclination angle.

[0118] As shown in Table 1, generally, when the gait of the human body is a sitting gait, a standing gait, a walking gait, a stair climbing gait or a stair descending gait, the waist inclination angle is 0 to 10. When the gait of the human body is a jogging gait, the waist inclination angle is 10 to 30.

[0119] S52. Determine a direction characteristic value, wherein the direction characteristic value is used to represent a moving direction of a leg of the human body relative to a corresponding side mechanical leg in the exoskeleton.

[0120] In this step, the moving direction between each side leg of the human body and the corresponding side mechanical leg in the exoskeleton is matched with a direction characteristic value. The moving direction between the left side human calf and the left side mechanical calf is matched with a first direction characteristic value, the moving direction between the left side human thigh and the left side mechanical thigh is matched with a second direction characteristic value, the moving direction between the right side human calf and the right side mechanical calf is matched with a third direction characteristic value, and the moving direction between the right side human thigh and the right side mechanical thigh is matched with a fourth direction characteristic value.

[0121] It can also be understood that each direction characteristic value comprises a positive direction characteristic value and a negative direction characteristic value, the positive direction characteristic value is used to represent that the leg of the human body approaches the corresponding side mechanical leg in the exoskeleton, and the negative direction characteristic value is used to represent that the leg of the human body is away from the corresponding side mechanical leg in the exoskeleton.

[0122] In addition to the method of determining the moving direction of the leg of the human body relative to the corresponding side mechanical leg in the exoskeleton to obtain the direction characteristic value by using the pressure detection assembly provided above, the moving direction of the leg of the human body relative to the corresponding side mechanical leg in the exoskeleton can also be determined by other reasonable methods.

[0123] In some embodiments, the first position of the annular accommodating portion is provided with a first Hall detector, and the second position of the annular accommodating portion is provided with a second Hall detector. When the human body wears the exoskeleton, the human leg is bound by the leg band, wherein the first magnet is arranged at a position of the leg band corresponding to the first position, and the second magnet is arranged at a position of the leg band corresponding to the second position.

[0124] Specifically, when the human leg is a left human calf, the left mechanical calf is provided with a left calf band at a position close to the knee joint, the left calf band is provided with a first magnet at a position corresponding to the first position of the first annular accommodating portion, and the left calf band is provided with a second magnet at a position corresponding to the second position of the first annular accommodating portion.

[0125] Similarly, when the human leg is a left human thigh, the left mechanical thigh is provided with a left thigh band at a position close to the knee joint, the left thigh band is provided with another first magnet at a position corresponding to the first position of the second annular accommodating portion, and the left thigh band is provided with another second magnet at a position corresponding to the second position of the second annular accommodating portion, and so on.

[0126] When the human body moves, the leg band is moved by the human leg. When the human leg is close to the mechanical leg, the first magnet is close to the first Hall detector, so that the first Hall signal is detected, and a positive characteristic value is generated according to the first Hall signal. When the human leg is away from the mechanical leg, the second magnet is close to the second Hall detector, so that the second Hall signal is detected, and a negative characteristic value is generated according to the second Hall signal.

[0127] In some embodiments, when the human leg is close to the mechanical leg, the first magnet is close to the first Hall detector, and the second magnet is away from the second Hall detector, so that the first Hall signal is detected from weak to strong, and the second Hall signal is detected from strong to weak. Therefore, when the first Hall signal is from weak to strong, and the second Hall signal is from strong to weak, a positive characteristic value can be generated. When the human leg is away from the mechanical leg, the second magnet is close to the second Hall detector, and the first magnet is away from the first Hall detector, so that the second Hall signal is detected from strong to weak, and the first Hall signal is detected from weak to strong. Therefore, when the second Hall signal is from strong to weak, and the first Hall signal is from weak to strong, a negative characteristic value can be generated.

[0128] S53. Determine the gait according to the waist inclination angle and direction characteristic value.

[0129] The embodiment does not need to process too much gait characteristic data, and the waist inclination angle and direction characteristic value can be used to determine the gait, which is beneficial to improve the recognition efficiency of the gait, so as to efficiently control the exoskeleton to work, thereby improving the coordination between the exoskeleton and the human body.

[0130] In some embodiments, determining the direction feature value, please refer to Figure 6 S52 comprises:

[0131] S521. Acquiring a leg pressure signal.

[0132] S522. Determining a pressure direction according to the leg pressure signal.

[0133] S523. Determining a direction feature value according to the pressure direction.

[0134] In S521, the mechanical leg is provided with a pressure detection component, when the human leg approaches or moves away from the corresponding side mechanical leg, the human leg triggers the pressure detection component to generate different leg pressure signals.

[0135] In some embodiments, the leg pressure signal comprises a first leg pressure signal and / or a second leg pressure signal. The pressure detection component comprises a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on the opposite sides of the human leg. The pressure detection component at the first pressure detection point can detect the first leg pressure signal when the human leg approaches the corresponding side mechanical leg. The pressure detection component at the second pressure detection point can detect the second leg pressure signal when the human leg moves away from the corresponding side mechanical leg.

[0136] In S522, determining the pressure direction according to the leg pressure signal comprises: if the first pressure detection point detects the first leg pressure signal, determining the pressure direction as a positive pressure direction, wherein the positive pressure direction is the pressure direction exerted by the human leg on the pressure detection component when the human leg approaches the mechanical leg. If the second pressure detection point detects the second leg pressure signal, determining the pressure direction as a negative pressure direction, wherein the negative pressure direction is the pressure direction exerted by the human leg on the pressure detection component when the human leg moves away from the mechanical leg. If neither the first pressure detection point nor the second pressure detection point detects the leg pressure signal, determining the pressure direction as a neutral pressure direction, wherein the neutral pressure direction is the pressure direction when the relative position between the human leg and the mechanical leg remains unchanged.

[0137] The difference between the above embodiment and the present embodiment is that, in some embodiments, determining the pressure direction according to the leg pressure signals comprises: determining a pressure change trend according to the first leg pressure signal and the second leg pressure signal, wherein the pressure change trend comprises a change trend of the first leg pressure signal and a change trend of the second leg pressure signal. If the pressure change trend is that the first leg pressure signal changes from weak to strong and the second leg pressure signal changes from strong to weak, it is determined that the pressure direction is a positive pressure direction. If the pressure change trend is that the first leg pressure signal changes from strong to weak and the second leg pressure signal changes from weak to strong, it is determined that the pressure direction is a negative pressure direction. If the pressure change trend is that the first leg pressure signal and the second leg pressure signal remain unchanged, it is determined that the pressure direction is a neutral pressure direction.

[0138] In S523, determining the direction feature value according to the pressure direction comprises: if the pressure direction is a positive pressure direction, determining the direction feature value as a positive direction feature value. If the pressure direction is a negative pressure direction, determining the direction feature value as a negative direction feature value. If the pressure direction is a neutral pressure direction, determining the direction feature value as a neutral direction feature value.

[0139] It can be understood that the positive direction feature value, the negative direction feature value and the neutral direction feature value can be represented by any data, such as 1 representing the positive direction feature value, 0 representing the negative direction feature value,

[0140] As described above, after obtaining the direction feature value, in S53, the present embodiment can directly use the waist inclination angle, the first direction feature value, the second direction feature value, the third direction feature value and the fourth direction feature value to look up a table, and then determine the gait, wherein the gait comprises at least one of a sitting gait, a standing gait, a slow running gait, a walking gait, an up-stair climbing gait and a down-stair climbing gait.

[0141] The difference between the above embodiment and the present embodiment is that, in S53, the present embodiment can input the waist inclination angle, the direction feature value and the leg pressure signals into the SVM classifier to obtain the gait, that is, input the waist inclination angle, the first direction feature value, the second direction feature value, the third direction feature value, the fourth direction feature value and the leg pressure signals corresponding to each side of the human leg into the SVM classifier to obtain the gait. For example:

[0142] The waist inclination angle is θ.

[0143] The first leg pressure signal between the left human calf and the left mechanical calf is zs1, the second leg pressure signal is zs2, and the first direction feature value is p1. Therefore, the data set of the left human calf is [zs1, zs2, p1].

[0144] The first leg pressure signal between the left human thigh and the left mechanical thigh is zb1, the second leg pressure signal is zb2, and the second direction characteristic value is p2. The data set of the left human thigh is [zb1, zb2, p2].

[0145] The first leg pressure signal between the right human calf and the right mechanical calf is ys1, the second leg pressure signal is ys2, and the third direction characteristic value is p3. The data set of the right human calf is [ys1, ys2, p3].

[0146] The first leg pressure signal between the right human thigh and the right mechanical thigh is yb1, the second leg pressure signal is yb2, and the fourth direction characteristic value is p4. The data set of the right human thigh is [yb1, yb2, p4].

[0147] In this embodiment, θ, [zs1, zs2, p1], [zb1, zb2, p2], [ys1, ys2, p3], and [yb1, yb2, p4] are input into the SVM classifier. The SVM classifier outputs a classification result, which is a corresponding gait. The SVM classifier is used to determine the gait. This method has good universality, low computational power consumption, short calculation time, high accuracy, and high universality and scalability.

[0148] In addition, as shown in Table 3, the first leg pressure signal and the second leg pressure signal also have different change trends under different gaits. In this embodiment, the first leg pressure signal and the second leg pressure signal with different change trends are combined under the addition of the direction characteristic value, and the SVM classifier is used. Compared with the table lookup method, this embodiment can more accurately and reliably identify each gait.

[0149] In some embodiments, the SVM classifier can be trained in advance. In this embodiment, a gait database of six activities, such as “sitting gait”, “standing gait”, “going upstairs gait”, “going downstairs gait”, “walking gait”, and “jogging gait”, is established according to the waist inclination angle, the direction characteristic value, and the leg pressure signal of each side of the human leg obtained by the subject under each motion scene, and the SVM algorithm is used for training to generate an SVM multi-classifier.

[0150] It should be noted that in the above various embodiments, the above steps do not necessarily have a certain sequence. Those skilled in the art can understand from the description of the embodiments of the present disclosure that the above steps can have different execution sequences in different embodiments, that is, they can be executed in parallel, or they can be executed in exchange, and the like.

[0151] As another aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide a gait determination device based on an exoskeleton. The gait determination device based on the exoskeleton can be a software module including a plurality of instructions stored in a memory accessible by a processor to invoke the instructions for execution to complete the gait determination method based on the exoskeleton described in the various embodiments.

[0152] In some embodiments, the gait determination device based on the exoskeleton can also be built by hardware devices, for example, the gait determination device based on the exoskeleton can be built by one or more chips, and each chip can work in coordination with each other to complete the gait determination method based on the exoskeleton described in the various embodiments. For another example, the gait determination device based on the exoskeleton can also be built by various logic devices, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine), or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination of these components.

[0153] Referring to Figure 6 , the gait determination device 600 based on the exoskeleton includes an angle acquisition module 61, a direction determination module 62, and a gait determination module 63.

[0154] The angle acquisition module 61 is configured to acquire a waist inclination angle. The waist inclination angle is an inclination angle of a waist of a human body relative to a reference direction when the human body wears an exoskeleton. The direction determination module 62 is configured to determine a direction feature value. The direction feature value is used to represent a moving direction of a leg of the human body relative to a corresponding side mechanical leg in the exoskeleton. The gait determination module 63 is configured to determine a gait according to the waist inclination angle and the direction feature value.

[0155] The embodiments do not need to process too much gait feature data, and the waist inclination angle and the direction feature value can be used to determine the gait, which is beneficial to improve the recognition efficiency of the gait, so as to efficiently control the exoskeleton to work, thereby improving the coordination between the exoskeleton and the human body.

[0156] In some embodiments, the exoskeleton includes a trunk mechanical part and an angle sensor. The angle sensor is installed at a waist position of the trunk mechanical part, and abuts against a waist of a human body when the human body wears the exoskeleton, and is configured to collect a waist inclination angle.

[0157] In some embodiments, the direction determining module 62 is specifically configured to: acquire a leg pressure signal, wherein the mechanical leg is provided with a pressure detection component, when the human leg approaches or moves away from the corresponding side mechanical leg, the human leg triggers the pressure detection component to generate different leg pressure signals, determine a pressure direction according to the leg pressure signal, and determine the direction feature value according to the pressure direction.

[0158] In some embodiments, the leg pressure signal includes a first leg pressure signal and / or a second leg pressure signal. The pressure detection component includes a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on opposite sides of the human leg. The pressure detection component at the first pressure detection point can detect the first leg pressure signal when the human leg approaches the corresponding side mechanical leg. The pressure detection component at the second pressure detection point can detect the second leg pressure signal when the human leg moves away from the corresponding side mechanical leg.

[0159] In some embodiments, the direction determining module 62 is specifically further configured to: if the first pressure detection point detects the first leg pressure signal, determine that the pressure direction is a positive pressure direction. If the second pressure detection point detects the second leg pressure signal, determine that the pressure direction is a negative pressure direction. If neither the first pressure detection point nor the second pressure detection point detects the leg pressure signal, determine that the pressure direction is a neutral pressure direction.

[0160] In some embodiments, the direction determining module 62 is specifically further configured to: determine a pressure change trend according to the first leg pressure signal and the second leg pressure signal. If the pressure change trend is that the first leg pressure signal changes from weak to strong and the second leg pressure signal changes from strong to weak, determine that the pressure direction is a positive pressure direction. If the pressure change trend is that the first leg pressure signal changes from strong to weak and the second leg pressure signal changes from weak to strong, determine that the pressure direction is a negative pressure direction. If the pressure change trend is that the first leg pressure signal and the second leg pressure signal remain unchanged, determine that the pressure direction is a neutral pressure direction.

[0161] In some embodiments, the direction determining module 62 is specifically further configured to: if the pressure direction is a positive pressure direction, determine that the direction feature value is a positive feature value, wherein the positive feature value is used to indicate that the human leg approaches the corresponding side mechanical leg in the exoskeleton. If the pressure direction is a negative pressure direction, determine that the direction feature value is a negative feature value, wherein the negative feature value is used to indicate that the human leg moves away from the corresponding side mechanical leg in the exoskeleton. If the pressure direction is a neutral pressure direction, determine that the direction feature value is a neutral feature value, wherein the neutral feature value is used to indicate that the relative position between the human leg and the corresponding side mechanical leg in the exoskeleton remains unchanged.

[0162] In some embodiments, the gait includes at least one of a sitting gait, a standing gait, a jogging gait, a walking gait, an ascending stairs gait, and a descending stairs gait, and the gait determination module 63 is specifically configured to: input the waist inclination angle, the direction feature value, and the leg pressure signal into an SVM classifier to obtain the gait.

[0163] It should be noted that the above-mentioned exoskeleton-based gait determination device can execute the exoskeleton-based gait determination method provided by the embodiments of the present disclosure, and has the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the exoskeleton-based gait determination device embodiments can be referred to the exoskeleton-based gait determination method provided by the embodiments of the present disclosure.

[0164] Please refer to Figure 7 , Figure 7 A circuit structure schematic diagram of an electronic device is provided for the embodiments of the present disclosure. As shown in Figure 7 , the electronic device 700 includes one or more processors 71 and a memory 72. Among them, Figure 7 take one processor 71 as an example.

[0165] The processor 71 and the memory 72 can be connected by a bus or other means, Figure 7 take the connection by the bus as an example.

[0166] The memory 72 as a kind of storage medium, it 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 gait determination method in the embodiments of the present disclosure. The processor 71 executes the non-volatile software program, instruction and module stored in the memory 72, thereby performing various functional applications and data processing of the exoskeleton-based gait determination device, that is, realizing the functions of the exoskeleton-based gait determination method provided by the method embodiments and each module or unit of the above-mentioned device embodiments.

[0167] The memory 72 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 72 can optionally include a memory remotely arranged relative to the processor 71, and these remote memories can be connected to the processor 71 through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0168] The program instructions / modules are stored in the memory 72, and when executed by the one or more processors 71, the exoskeleton-based gait determination method in any of the above-mentioned method embodiments is executed.

[0169] The embodiment of the present disclosure further provides a storage medium, which stores computer executable instructions, and the computer executable instructions are executed by one or more processors, for example, one processor 71 in the computer device, so that the one or more processors can execute the exoskeleton-based gait determination method in any method embodiment. Figure 7 The embodiment of the present disclosure further provides a computer program product, which comprises a computer program stored on a non-volatile computer readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by an electronic device, the electronic device executes the exoskeleton-based gait determination method.

[0170] The embodiment of the present disclosure further provides a computer program product, which comprises a computer program stored on a non-volatile computer readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by an electronic device, the electronic device executes the exoskeleton-based gait determination method.

[0171] The above-mentioned device or equipment embodiments are only illustrative, wherein the unit modules illustrated as separate components can or can not be physically separated, and the components illustrated as module units can or can not be physical units, that is, can be located in one place, or can be distributed on multiple network module units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0172] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus a general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0173] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present disclosure, and not to limit them; under the idea of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the present disclosure as described above. In order to be brief, they are not provided in detail; although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. An exoskeleton-based gait determination method, characterized by, The method comprises the following steps: obtaining a waist inclination angle, wherein the waist inclination angle is an inclination angle of a waist of a human body relative to a reference direction when the human body wears the exoskeleton; determining a direction characteristic value, wherein the direction characteristic value is used to represent a moving direction of a leg of the human body relative to a corresponding mechanical leg in the exoskeleton; the determination of the direction characteristic value comprises: obtaining a leg pressure signal, wherein the mechanical leg is provided with a pressure detection assembly, and when the leg of the human body approaches or moves away from the corresponding mechanical leg, the leg of the human body triggers the pressure detection assembly to generate different leg pressure signals; the leg pressure signal comprises a first leg pressure signal and / or a second leg pressure signal; the pressure detection assembly comprises a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on opposite sides of the front and back of the leg of the human body; the pressure detection assembly at the first pressure detection point can detect the first leg pressure signal when the leg of the human body approaches the corresponding mechanical leg; the pressure detection assembly at the second pressure detection point can detect the second leg pressure signal when the leg of the human body moves away from the corresponding mechanical leg; determining a pressure direction according to the leg pressure signal; determining the direction characteristic value according to the pressure direction; determining a gait according to the waist inclination angle and the direction characteristic value.

2. The method of claim 1, wherein, The exoskeleton comprises a trunk mechanical part and an angle sensor, wherein the angle sensor is installed on a waist position of the trunk mechanical part, and when the human body wears the exoskeleton, the angle sensor abuts against the waist of the human body, and is used to collect the waist inclination angle.

3. The method of claim 1, wherein, The determination of the pressure direction according to the leg pressure signal comprises: if the first pressure detection point detects the first leg pressure signal, then determining that the pressure direction is a positive pressure direction; if the second pressure detection point detects the second leg pressure signal, then determining that the pressure direction is a negative pressure direction; if neither the first pressure detection point nor the second pressure detection point detects a leg pressure signal, then determining that the pressure direction is a neutral pressure direction.

4. The method of claim 1, wherein, The determination of the pressure direction according to the leg pressure signal comprises: determining a pressure change trend according to the first leg pressure signal and the second leg pressure signal; if the pressure change trend is that the first leg pressure signal changes from weak to strong, and the second leg pressure signal changes from strong to weak, then determining that the pressure direction is a positive pressure direction; if the pressure change trend is that the first leg pressure signal changes from strong to weak, and the second leg pressure signal changes from weak to strong, then determining that the pressure direction is a negative pressure direction; if the pressure change trend is that the first leg pressure signal and the second leg pressure signal remain unchanged, then determining that the pressure direction is a neutral pressure direction.

5. The method of claim 1, wherein, The determination of the direction characteristic value according to the pressure direction comprises: if the pressure direction is a positive pressure direction, then determining that the direction characteristic value is a positive characteristic value, wherein the positive characteristic value is used to represent that the leg of the human body approaches the corresponding mechanical leg in the exoskeleton. If the pressure direction is a negative pressure direction, the direction feature value is determined as a negative feature value, wherein the negative feature value is used to represent that the human leg is away from the corresponding mechanical leg in the exoskeleton; If the pressure direction is a neutral pressure direction, the direction feature value is determined as a neutral feature value, wherein the neutral feature value is used to represent that the relative position between the human leg and the corresponding mechanical leg in the exoskeleton remains unchanged.

6. The method of claim 1, wherein, The gait includes at least one of a sitting gait, a standing gait, a slow running gait, a walking gait, an up-stair gait and a down-stair gait, and the determining the gait according to the waist inclination angle and the direction feature value includes: inputting the waist inclination angle, the direction feature value and the leg pressure signal into an SVM classifier to obtain the gait.

7. An exoskeleton characterized by, comprise: a trunk mechanical part; an angle sensor installed at a waist position of the trunk mechanical part, abutting against the human waist when the human wears the exoskeleton, used to detect the inclination angle of the human waist relative to a reference direction to obtain a waist inclination angle; a mechanical leg connected with the trunk mechanical part; a sensor module installed on the mechanical leg, used to detect the moving direction of the human leg relative to the corresponding mechanical leg in the exoskeleton to obtain a direction feature value; a power assembly installed on the trunk mechanical part and connected with the mechanical leg; a controller installed on the trunk mechanical part and electrically connected with the angle sensor, the sensor module and the power assembly, used to execute the exoskeleton-based gait determination method according to any one of claims 1 to 6, and control the power assembly to drive the mechanical leg to work according to the gait.

8. The exoskeleton of claim 7, wherein, The sensor module comprises a pressure detection assembly installed on the corresponding mechanical leg, which is triggered by the human leg to generate a leg pressure signal when the human leg approaches or moves away from the corresponding mechanical leg.

9. The exoskeleton of claim 8, wherein, The leg pressure signal comprises a first leg pressure signal and / or a second leg pressure signal; The pressure detection assembly comprises a first pressure detection point and a second pressure detection point, wherein the first pressure detection point and the second pressure detection point are respectively located on opposite sides of the human leg; The pressure detection assembly at the first pressure detection point can detect the first leg pressure signal when the human leg approaches the corresponding mechanical leg; The pressure detection assembly at the second pressure detection point can detect the second leg pressure signal when the human leg moves away from the corresponding mechanical leg.

10. A storage medium, characterized by The computer executable instructions stored in the memory are used to make the electronic device execute the exoskeleton-based gait determination method according to any one of claims 1 to 6.

11. An electronic device, comprising: comprise: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the exoskeleton-based gait determination method according to any one of claims 1 to 6.

Images