A control method for an intelligent walking aid

Abstract

This invention relates to the field of walking aid technology, and more particularly to a control method for an intelligent walking aid, comprising: controlling the walking aid to sequentially traverse an obstacle test surface with progressively increasing obstacle heights; calculating the rate of change of blurriness in the obstacle test surface image; determining the data acquisition parameters of the walking aid's inertial measurement module and obtaining the walking aid's direction of travel based on the rate of change of blurriness in the obstacle test surface image, with the data marker time corrected according to the time difference in data transmission between the inertial measurement module and the camera; determining the walking aid's body height and the relative angle between the front and rear wheels; establishing a mapping relationship; and controlling the walking aid to operate according to the mapping relationship. This invention improves driving efficiency and visual stability, enabling the walking aid to more accurately control its speed and stopping position, thus enhancing the safety and controllability during use.

Description

Technical Field

[0001] This invention relates to the field of walking aid technology, and more particularly to a control method for an intelligent walking aid. Background Technology

[0002] The sensing system of an intelligent walking aid is the core of its intelligence. Its vision-based sensing system acquires environmental information through attached visual sensors, identifies and judges obstacles in the walking environment, and plans the correct movement path to guide the user. Its motion signal-based sensing system mainly judges the movement trend and state of the user and the walking aid by detecting signals such as the movement angle, speed, position, and force of the user's limbs and the walking aid. Its physiological electrical signal-based sensing system collects the user's physiological electrical signals through various invasive and non-invasive physiological electrical signal acquisition devices, such as MEMS microneedle array dry electrodes. This sensing method is generally used in cases where the extremities are missing or the strength is insufficient to express the intention to move, or when the user has completely lost the ability to move.

[0003] Chinese Patent Publication No. CN113545929B discloses a control method and device for an intelligent walking aid, an intelligent walking aid, and a controller. The method includes the following steps: acquiring the moving speed of the intelligent walking aid; acquiring the posture of the intelligent walking aid; when the posture indicates that the front end of the intelligent walking aid is tilted upwards, and the moving speed of the intelligent walking aid is less than a first threshold, reducing the torque output value of the motor; when the upward tilt angle of the intelligent walking aid is greater than a preset maximum threshold, reducing or stopping the increase of the torque output value of the motor. Therefore, the control method and device for the intelligent walking aid, the intelligent walking aid, and the controller have problems such as: in complex terrain, obstacles of inconsistent heights cause blurred images captured by the walking aid during manual obstacle-crossing, leading to decreased visual accuracy; obstacle-crossing causes center shift and torque imbalance in the walking aid; and the direction of the shift causes excessive time for correction, resulting in decreased driving efficiency. Summary of the Invention

[0004] To address these issues, the present invention provides a control method for an intelligent walking aid, which overcomes the problems in the prior art where the visual images captured by the walking aid are blurry during the manual obstacle-crossing process due to obstacles of inconsistent heights in complex terrain, leading to a decrease in the visual accuracy of the walking aid; the obstacle-crossing causing the walking aid to shift its center and lose torque balance; and the direction of the shift causing the walking aid to take too long to correct its direction, thus reducing the walking aid's driving efficiency.

[0005] To achieve the above objectives, the present invention provides a control method for an intelligent walking aid, comprising:

[0006] The walking aid was controlled to pass through a test surface with progressively increasing obstacle heights.

[0007] The camera of the walking aid captures images of the obstacle test surface as it passes over the obstacle test surface, and the rate of change of the blur level of the obstacle test surface image is calculated.

[0008] The data acquisition parameters of the inertial measurement module of the walking aid are determined based on the rate of change of the blur level of the obstacle test road surface image, and the direction of travel of the walking aid is obtained. The data acquisition parameters include the acquisition frequency and the data marking time.

[0009] The data marking time is corrected based on the time difference between the data transmission between the inertial measurement module and the camera;

[0010] The vehicle height and the relative angle between the front and rear wheels of the walker are determined based on the offset angle between the direction of travel and the predetermined route after the walker passes through a single height gradient in sequence.

[0011] Establish a mapping relationship between the blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid;

[0012] The walking aid is controlled to operate according to the mapping relationship.

[0013] Furthermore, the process of calculating the rate of change of blurriness in the obstacle test road surface image includes:

[0014] Convert the obstacle test road surface image into a grayscale image;

[0015] The grayscale image is convolved sequentially using the Laplacian operator.

[0016] The variance of the computation results of the Laplacian operator is obtained to characterize the blurriness of the obstacle test road surface image;

[0017] The rate of change of blur level is calculated based on the blur level of three consecutive frames of the obstacle test road surface image.

[0018] Furthermore, the rate of change of blur level is the ratio of the change of blur level between any two consecutive frames in three adjacent consecutive frames, and the change of blur level between two consecutive frames is the difference between the blur level of the obstacle test road surface image in the current frame and the blur level of the previous frame.

[0019] Furthermore, the process of determining the data acquisition parameters of the inertial measurement module of the walking aid and obtaining the walking aid's direction of travel includes:

[0020] The rate of change of the ambiguity is compared with a preset rate of change;

[0021] If the rate of change of the blur level is greater than or equal to the preset rate of change, then the image acquisition stability of the camera is determined to be unsatisfactory.

[0022] The inertial measurement module is controlled to record data when the rate of change of the blur level of the acquired obstacle test surface image is equal to the preset rate of change, and the acquisition frequency of the inertial measurement module is reduced.

[0023] The direction of travel of the walking aid is obtained based on the data recorded by the inertial measurement module.

[0024] Furthermore, the process of correcting the data marker time based on the time difference between the data transmission between the inertial measurement module and the camera includes:

[0025] The times when the data collected by the inertial measurement module arrives at the data receiving end and the times when the obstacle test road surface image collected by the camera arrives at the data receiving end are respectively obtained;

[0026] Calculate the time difference between data transmission between the inertial measurement module and the camera;

[0027] If the time difference is greater than the preset time difference, the data marker time is reduced and corrected according to the walking speed of the walker when the camera captures the obstacle test road surface image.

[0028] Furthermore, the time difference is the absolute value of the difference between the time when the data collected by the inertial measurement module arrives at the data receiving end and the time when the obstacle test road surface image collected by the camera arrives at the data receiving end.

[0029] Furthermore, the reduced data marker time is the difference between the original data marker time and the reduced correction magnitude.

[0030] The reduction correction magnitude is the product of the time difference and the ratio of the walking aid's speed to the preset speed of the walking vehicle when the obstacle test road surface image is displayed.

[0031] Furthermore, the process of determining the vehicle height and front and rear wheel camber angles of the walking aid includes:

[0032] The direction of travel and the predetermined route of the walking aid after passing through a single altitude gradient are obtained respectively, and the offset angle is calculated.

[0033] Compare the offset angle with the preset angle;

[0034] If the offset angle is greater than or equal to the preset angle, it is determined that the operational stability of the mobility aid does not meet the requirements, and the vehicle height is reduced and the relative angle between the front and rear wheels is increased.

[0035] The vehicle height and the relative angle between the front and rear wheels are positively correlated with the offset angle.

[0036] Furthermore, the relative angle between the front and rear wheels is the acute angle between the horizontal diameter axis of the front wheel and the horizontal diameter axis of the rear wheel of the walking aid.

[0037] Furthermore, the process of establishing the mapping relationship between the blur level of the obstacle test surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid includes:

[0038] The blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid are combined into a quaternion data set;

[0039] The historical data of the quadruple data are classified and trained according to the obstacle height gradient;

[0040] The mapping relationship is generated based on the training results.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: The method of the present invention, by setting an obstacle test surface and calculating the blurriness of the obstacle test surface image, addresses the issue that in complex terrain, obstacles of inconsistent heights cause blurry images to be captured by the walker's vision during manual obstacle-crossing, leading to a decrease in the walker's visual accuracy. Furthermore, because vehicle body adjustments lag behind terrain changes, such as only compensating after the fact on bumpy roads, blurred images cause a disconnect between environmental perception and motion state data. By determining the data acquisition parameters of the walker's inertial measurement module, the stability and accuracy of data acquisition are improved; according to... By adjusting the angle of deviation between the walking aid's direction of travel and the predetermined route, and by adjusting the height of the walking aid and the relative angles of the front and rear wheels, problems such as center shift and torque imbalance caused by obstacles are avoided. This shortens the time for the walking aid to correct its direction and improves its driving efficiency. By establishing a mapping relationship between the blurriness of the obstacle test road image, the data acquisition parameters of the inertial measurement module, and the height of the walking aid and the tilt angles of the front and rear wheels, the stability and safety of the walking aid are improved. This allows the walking aid to more accurately control its speed and stopping position, enhancing the safety and controllability during use.

[0042] Furthermore, the method of the present invention calculates the rate of change of the blur degree of the obstacle test road surface image, and accurately reflects the road surface complexity and the stability of the walking aid during the driving process based on the changing trend of the blur degree of the obstacle test road surface image between two consecutive frames. Since the walking aid faces large bumps or obstacles, it will cause nonlinear distortion in the continuous images collected by the walking aid's vision system, resulting in edge blurring. The blur degree of the obstacle test road surface image is characterized by the Laplacian variance, thereby realizing the monitoring of the driving status of the walking aid during driving.

[0043] Furthermore, the method of the present invention, by setting a preset rate of change, addresses the issue that the visual sensitivity of the walking aid decreases when the camera's acquisition of the surrounding environment is unable to adapt to bumpy road surfaces. By marking data and reducing the acquisition frequency of the inertial measurement module, data is forced to be recorded at moments of ambiguity, thereby reducing misjudgment and data redundancy caused by road bumps, improving data processing efficiency and the walking aid's response speed, enhancing the algorithm's ability to extract useful information from images, and reducing noise in the inertial measurement module, thus improving the clarity of information visually.

[0044] Furthermore, the method described in this invention, by setting a preset time difference, addresses the asynchronous nature of data transmission between the inertial measurement module and the camera due to factors such as wear, uncleanliness, aging of the inertial measurement module, strong electromagnetic fields encountered by the walking aid, and changes in ambient temperature. This leads to a mismatch in the time of the data collected by the two devices. By correcting the data marking time, the consistency between the data from the inertial measurement module and the image data from the camera is increased, thereby improving the accuracy and response speed of the walking aid control. By reducing the data marking time according to the walking aid's travel speed to compensate for the impact of the time difference, the stability and efficiency of the walking aid in complex terrain are improved.

[0045] Furthermore, the method of the present invention, by setting a preset angle, addresses the issue that the walking aid's direction of travel may deviate due to the varying heights of the obstacle environment. Since blurred images cannot accurately determine the walking aid's driving status, the method may misjudge its direction of travel. Simultaneously with the visual blurring of the walking aid, the method collects the angle between its direction of travel and the predetermined direction. By lowering the vehicle's height to stabilize its center of gravity and increasing the relative angle between the front and rear wheels to generate a resisting torque on the driving direction, the method reduces response lag caused by mechanical gaps. This enhances the walking aid's ability to correct its course when crossing three-dimensional obstacles such as steps and slopes, thereby improving the spatial continuity and attitude stability of the walking aid's motion control.

[0046] Furthermore, the method described in this invention, by setting a mapping relationship, can predict and control the operating state of the walking aid based on the blurriness of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and multiple information such as the height of the walking aid and the tilt angles of the front and rear wheels. By analyzing the current environment, the stability of the walking aid in driving paths with different obstacle heights is improved. Attached Figure Description

[0047] Figure 1 This is an overall flowchart of the control method for the intelligent walking aid according to an embodiment of the present invention;

[0048] Figure 2 This is a flowchart illustrating the rate of change of blurriness in an obstacle test road surface image, representing the control method of the intelligent walking aid according to an embodiment of the present invention.

[0049] Figure 3 The flowchart below shows the data acquisition parameters of the inertial measurement module of the intelligent walking aid, which is used to determine the control method of the intelligent walking aid according to an embodiment of the present invention.

[0050] Figure 4 This is a flowchart illustrating the data marker timing correction process for the control method of the intelligent walking aid according to an embodiment of the present invention. Detailed Implementation

[0051] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0052] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0053] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0054] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] Please see Figure 1 , Figure 2 , Figure 3 as well as Figure 4 The diagrams shown are, respectively, an overall flowchart, a flowchart of the rate of change of ambiguity, a flowchart of the data acquisition parameters of the inertial measurement module, and a flowchart of the data marker time correction flowchart for the control method of the intelligent walking aid according to an embodiment of the present invention. An embodiment of the present invention provides a control method for an intelligent walking aid, comprising:

[0056] Step S1: Control the walking aid to pass through the obstacle test surface with progressively increasing obstacle heights;

[0057] Step S2: Obtain an image of the obstacle test surface captured by the camera of the walking aid when it passes through the obstacle test surface, and calculate the rate of change of the blur degree of the obstacle test surface image;

[0058] Step S3: Determine the data acquisition parameters of the inertial measurement module of the walking aid based on the rate of change of the blur degree of the obstacle test road surface image and obtain the walking aid's direction of travel. The data acquisition parameters include the acquisition frequency and the data marking time.

[0059] The data marking time is corrected based on the time difference between the data transmission between the inertial measurement module and the camera;

[0060] Step S4: Determine the vehicle height and the relative angle between the front and rear wheels of the walking aid based on the offset angle between the direction of travel and the predetermined route direction after the walking aid has passed through a single height gradient.

[0061] Step S5: Establish the mapping relationship between the blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid;

[0062] Step S6: Control the walking aid to operate according to the mapping relationship.

[0063] Specifically, provided that the small diameter wheels of the walker are not less than 5 inches, the general range of the gradient value for the increasing obstacle height gradient is [1mm, 5mm], and the preferred embodiment of the gradient value for the increasing obstacle height gradient is 3mm.

[0064] Those skilled in the art will understand that the selectable range of gradient values ​​for the increasing obstacle height gradient provided in this embodiment, as well as the preferred embodiment, are the values ​​that best address the technical problem solved by the present invention, under the condition that the small diameter wheels of the walker are not less than 5 inches. In actual applications or experiments, those skilled in the art can adaptively adjust the gradient values ​​for the increasing obstacle height gradient according to the actual application environment and application scenario.

[0065] Specifically, the inertial measurement module includes a gyroscope and an accelerometer.

[0066] Specifically, the method of using an inertial measurement module to obtain the direction of travel of the walking aid is a well-known technique and will not be elaborated here.

[0067] In practice, the method described in this invention addresses the issue of visual inaccuracies caused by obstacles of varying heights in complex terrain. These inaccuracies result in blurred images captured by the walker during manual obstacle-crossing maneuvers, leading to decreased visual accuracy. Furthermore, the method addresses the problem of the walker's vehicle body adjusting lags behind terrain changes (e.g., only post-event compensation on bumpy roads), causing a disconnect between environmental perception and motion data. By determining the data acquisition parameters of the walker's inertial measurement module, the stability and accuracy of data acquisition are improved. Based on the offset angle between the walker's direction of travel and the predetermined route, the method adjusts the walker's height and the relative angles of the front and rear wheels, preventing center shift and torque imbalance caused by obstacle crossings. This shortens the time required for direction correction and improves the walker's efficiency. Finally, by establishing a mapping relationship between the blurriness of the obstacle test surface image, the data acquisition parameters of the inertial measurement module, and the walker's height and wheel camber angles, the stability and safety of the walker are enhanced. This allows for more precise control of speed and stopping position, improving safety and controllability during use.

[0068] Specifically, the process of calculating the rate of change of blurriness in the obstacle test surface image includes:

[0069] Convert the obstacle test road surface image into a grayscale image;

[0070] The grayscale image is convolved sequentially using the Laplacian operator.

[0071] The variance of the computation results of the Laplacian operator is obtained to characterize the blurriness of the obstacle test road surface image;

[0072] The rate of change of blur level is calculated based on the blur level of three consecutive frames of the obstacle test road surface image.

[0073] Specifically, the process of obtaining the variance of the computation results of the Laplacian operator includes:

[0074] Divide the grayscale image into n×n pixel blocks;

[0075] The Laplacian operator is used to perform convolution operations on each pixel block, and the variance of the high-frequency components of several pixel blocks is calculated.

[0076] Specifically, the rate of change of blur level is the ratio of the change of blur level between any two consecutive frames in three adjacent consecutive frames, and the change of blur level between any two consecutive frames is the difference between the blur level of the obstacle test road surface image in the current frame and the blur level of the previous frame.

[0077] In practice, the method of the present invention calculates the rate of change of the blur degree of the obstacle test road surface image. Based on the trend of the change of the blur degree of the obstacle test road surface image between two consecutive frames, it accurately reflects the complexity of the road surface and the stability of the walking aid during the driving process. Since the walking aid faces large bumps or obstacles, it will cause nonlinear distortion in the continuous images collected by the walking aid's vision system, resulting in edge blurring. The blur degree of the obstacle test road surface image is characterized by the Laplacian variance, thereby realizing the monitoring of the driving status of the walking aid during driving.

[0078] Specifically, the process of determining the data acquisition parameters of the inertial measurement module of the walking aid and obtaining the walking aid's direction of travel includes:

[0079] The rate of change of the ambiguity is compared with a preset rate of change;

[0080] If the rate of change of the blur level is greater than or equal to the preset rate of change, then the image acquisition stability of the camera is determined to be unsatisfactory.

[0081] The inertial measurement module is controlled to mark data and obtain the direction of travel when the rate of change of the blur level of the acquired obstacle test road surface image is equal to the preset rate of change, thereby reducing the acquisition frequency of the inertial measurement module.

[0082] Specifically, when the camera is an RGB camera and the frame rate is 50fps, the general range of the preset change rate is [6%, 20%], and the preferred embodiment of the preset change rate is 12%.

[0083] Those skilled in the art will understand that the range of preset change rates and the preferred embodiments provided in this embodiment are the values ​​that best address the technical problem solved by the present invention under the condition that the camera is an RGB camera and the frame rate is 50fps. In actual applications or experiments, those skilled in the art can make adaptive adjustments to the preset change rates according to the actual application environment and application scenario.

[0084] In practice, if the difference between the rate of change of ambiguity and the preset rate of change is within 1%, the acquisition frequency of the inertial measurement module is reduced by 14Hz. If the difference between the rate of change of ambiguity and the preset rate of change exceeds 1%, the acquisition frequency of the inertial measurement module is reduced by 6Hz for every 1% increase. For example, if the difference between the rate of change of ambiguity and the preset rate of change is 4%, and the current acquisition frequency of the inertial measurement module is 140Hz, the acquisition frequency is reduced to 140Hz-14Hz-6Hz×3=108Hz.

[0085] In practice, the method of the present invention sets a preset rate of change. Since the camera's ability to capture the surrounding environment cannot adapt to bumpy roads, the visual sensitivity of the walking aid will decrease. By marking data and reducing the acquisition frequency of the inertial measurement module, data is forced to be recorded at moments of ambiguity, thereby reducing misjudgment and data redundancy caused by road bumps, improving data processing efficiency and the walking aid's response speed, enhancing the algorithm's ability to extract useful information from images, and reducing noise in the inertial measurement module, thus improving the clarity of information visually.

[0086] Specifically, the process of correcting the data marker time based on the time difference between the data transmission between the inertial measurement module and the camera includes:

[0087] The times when the data collected by the inertial measurement module arrives at the data receiving end and the times when the obstacle test road surface image collected by the camera arrives at the data receiving end are respectively obtained;

[0088] Calculate the time difference between data transmission between the inertial measurement module and the camera;

[0089] If the time difference is greater than the preset time difference, the data marker time is reduced and corrected according to the walking speed of the walker when the camera captures the obstacle test road surface image.

[0090] Specifically, the time difference is the absolute value of the difference between the time when the data collected by the inertial measurement module arrives at the data receiving end and the time when the obstacle test road surface image collected by the camera arrives at the data receiving end.

[0091] Specifically, the reduced data marker time is the difference between the original data marker time and the reduced correction magnitude;

[0092] The reduction correction magnitude is the product of the time difference and the ratio of the walking aid's speed to the preset speed of the walking vehicle when the obstacle test road surface image is displayed.

[0093] Specifically, when the camera is an RGB camera and the frame rate is 50fps, the general range of the preset time difference is [0.06ms, 0.1ms], and the preferred embodiment of the preset time difference is 0.08ms.

[0094] Those skilled in the art will understand that the range of preset time differences and preferred embodiments provided in this embodiment are the values ​​that best address the technical problem solved by the present invention under the condition that the camera is an RGB camera and the frame rate is 50fps. In actual applications or experiments, those skilled in the art can make adaptive adjustments to the preset time difference according to the actual application environment and application scenario.

[0095] In practice, the method of this invention sets a preset time difference. Due to wear, uncleanliness, aging of the inertial measurement module, strong electromagnetic fields encountered by the walking aid, and changes in the ambient temperature of the walking aid, the data transmission between the inertial measurement module and the camera is asynchronous, resulting in a time mismatch between the data collected by the two. By correcting the data marking time, the consistency between the data from the inertial measurement module and the image data from the camera is increased in time, thereby improving the accuracy and response speed of the walking aid control. By reducing the data marking time according to the walking aid's travel speed to compensate for the impact of the time difference, the stability and efficiency of the walking aid in complex terrain are improved.

[0096] Specifically, the process of determining the height of the walking aid and the camber angles of the front and rear wheels includes:

[0097] The direction of travel and the predetermined route of the walking aid are obtained respectively, and the offset angle is calculated;

[0098] Compare the offset angle with the preset angle;

[0099] If the offset angle is greater than or equal to the preset angle, it is determined that the operational stability of the mobility aid does not meet the requirements, and the vehicle height is reduced and the relative angle between the front and rear wheels is increased.

[0100] The vehicle height and the relative angle between the front and rear wheels are positively correlated with the offset angle.

[0101] Specifically, the relative angle between the front and rear wheels is the acute angle between the horizontal diameter axis of the front wheel and the horizontal diameter axis of the rear wheel of the mobility aid, and the front and rear wheels turn in opposite directions as the relative angle between the front and rear wheels increases.

[0102] Specifically, the vehicle height is adjusted via hydraulic rods, and the relative angle between the front and rear wheels is adjusted via steering rods.

[0103] Specifically, under the condition that the small diameter wheel of the walker is not less than 5 inches and the large diameter wheel is not less than 24 inches, the general range of the preset angle is [0.8°, 2.4°], and the preferred embodiment of the preset angle is 1.2°.

[0104] Those skilled in the art will understand that the range of preset angles and preferred embodiments provided in this embodiment are the values ​​that best address the technical problem solved by the present invention, under the condition that the small diameter wheel of the walker in this embodiment is not less than 5 inches and the large diameter wheel is not less than 24 inches. In actual applications or experiments, those skilled in the art can make adaptive adjustments to the preset angles according to the actual application environment and application scenario.

[0105] In practice, the method of the present invention sets a preset angle. Due to the influence of different heights of the walking aid in obstacle environments, the direction of travel may deviate. Because the blurred image cannot accurately determine the driving status of the walking aid, the walking aid may misjudge the direction of travel. At the same time as the visual blur of the walking aid, the angle between the direction of travel and the predetermined direction is collected. By reducing the height of the vehicle body to stabilize the center of gravity, and by increasing the relative angle between the front and rear wheels to generate a resisting torque on the driving direction, the response lag caused by mechanical structure gaps is reduced. This improves the heading correction ability of the walking aid when crossing three-dimensional obstacles such as steps and slopes, and improves the spatial continuity and attitude stability of the walking aid motion control.

[0106] Specifically, the process of establishing the mapping relationship between the blur level of the obstacle test surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid includes:

[0107] The blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid are combined into a quaternion data set;

[0108] The historical data of the quadruple data are classified and trained according to the obstacle height gradient;

[0109] The mapping relationship is generated based on the training results.

[0110] In practice, the method described in this invention, by setting a mapping relationship, can predict and control the operating state of the walking aid based on the blurriness of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and multiple information such as the height of the walking aid and the tilt angles of the front and rear wheels. By analyzing the current environment, the stability of the walking aid is improved in driving paths with different obstacle heights.

[0111] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A control method for an intelligent walking aid, characterized in that, include: The walking aid was controlled to pass through a test surface with progressively increasing obstacle heights. The camera of the walking aid captures images of the obstacle test surface as it passes over the obstacle test surface, and the rate of change of the blur level of the obstacle test surface image is calculated. The data acquisition parameters of the inertial measurement module of the walking aid are determined based on the rate of change of the blur level of the obstacle test road surface image, and the direction of travel of the walking aid is obtained. The data acquisition parameters include the acquisition frequency and the data marking time. The data marking time is corrected based on the time difference between the data transmission between the inertial measurement module and the camera; The height of the walking aid and the relative angle between the front and rear wheels are determined based on the offset angle between the walking aid's direction of travel and the predetermined route direction; wherein, the process of determining the height of the walking aid and the camber angle of the front and rear wheels includes: The direction of travel and the predetermined route of the walking aid are obtained respectively, and the offset angle is calculated; Compare the offset angle with the preset angle; If the offset angle is greater than or equal to the preset angle, it is determined that the operational stability of the mobility aid does not meet the requirements, and the vehicle height is reduced and the relative angle between the front and rear wheels is increased. Wherein, the vehicle height and the relative angle between the front and rear wheels are positively correlated with the offset angle; The relative angle between the front and rear wheels is the acute angle between the horizontal diameter axis of the front wheel and the horizontal diameter axis of the rear wheel of the walking aid, and the front and rear wheels turn in opposite directions as the relative angle between the front and rear wheels increases; Establish a mapping relationship between the blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid; The walking aid is controlled to operate according to the mapping relationship, wherein... The process of establishing the mapping relationship between the blur level of the obstacle test surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid includes: The blur level of the obstacle test road surface image, the data acquisition parameters of the inertial measurement module, and the vehicle height and front and rear wheel camber angles of the walking aid are combined into a quaternion data set. The historical data of the quadruple data are classified and trained according to the obstacle height gradient; The mapping relationship is generated based on the training results.

2. The control method for the intelligent walking aid according to claim 1, characterized in that, The process of calculating the rate of change of blur in the obstacle test road surface image includes: Convert the obstacle test road surface image into a grayscale image; The grayscale image is convolved sequentially using the Laplacian operator. The variance of the computation results of the Laplacian operator is obtained to characterize the blurriness of the obstacle test road surface image; The rate of change of blur level is calculated based on the blur level of three consecutive frames of the obstacle test road surface image.

3. The control method for the intelligent walking aid according to claim 2, characterized in that, The rate of change of blur level is the ratio of the change of blur level between any two consecutive frames in three adjacent consecutive frames, and the change of blur level between any two consecutive frames is the difference between the blur level of the obstacle test road surface image in the current frame and the blur level of the previous frame.

4. The control method for the intelligent walking aid according to claim 3, characterized in that, The process of determining the data acquisition parameters of the inertial measurement module of the walking aid and obtaining the walking aid's direction of travel includes: The rate of change of the ambiguity is compared with a preset rate of change; If the rate of change of the blur level is greater than or equal to the preset rate of change, then the image acquisition stability of the camera is determined to be unsatisfactory. The inertial measurement module is controlled to mark data and obtain the direction of travel when the rate of change of the blur level of the acquired obstacle test road surface image is equal to the preset rate of change, thereby reducing the acquisition frequency of the inertial measurement module.

5. The control method for the intelligent walking aid according to claim 4, characterized in that, The process of correcting the data marker time based on the time difference between the data transmission between the inertial measurement module and the camera includes: The times when the data collected by the inertial measurement module arrives at the data receiving end and the times when the obstacle test road surface image collected by the camera arrives at the data receiving end are respectively obtained; Calculate the time difference between data transmission between the inertial measurement module and the camera; If the time difference is greater than the preset time difference, the data marker time is reduced and corrected according to the walking speed of the walker when the camera captures the obstacle test road surface image.

6. The control method for the intelligent walking aid according to claim 5, characterized in that, The time difference is the absolute value of the difference between the time when the data collected by the inertial measurement module arrives at the data receiving end and the time when the obstacle test road surface image collected by the camera arrives at the data receiving end.

7. The control method for the intelligent walking aid according to claim 6, characterized in that, The reduced correction data marker time is the difference between the original data marker time and the reduction correction magnitude; The reduction correction magnitude is the product of the time difference and the ratio of the walking aid's speed to the preset speed of the walking vehicle when the obstacle test road surface image is displayed.

Images