Blind stick, safety path navigation method thereof, electronic device and storage medium

Abstract

The application discloses a blind stick, a safety path navigation method thereof, an electronic device and a storage medium, and is applied to the technical field of blind navigation. The method comprises the following steps: planning a path according to a current position and a target position of a user, and generating an initial path; guiding the user to travel along the initial path; establishing a path width model, and obtaining a safety path width through the path width model; and monitoring the position of the user in real time during the travel process, and ensuring that the user is always within the safety path width range. The blind stick is organically combined with a visual camera to form a cooperative working system, the position relationship between the user and the safety path width is monitored in real time, the user is reminded to immediately adjust the travel direction of the user through different levels of vibration feedback, and it is ensured that the user always travels within the safety path width range of the path. The safety and independence of the visually impaired person are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of blind navigation, in particular to a blind stick, a path navigation method thereof, an electronic device and a storage medium.

[0002] Currently, there are more than 250 million people worldwide with visual impairment, and visually impaired people often face various challenges in travel, including various obstacles, unfriendly traffic environment and imperfect traffic facilities, which limit their independent travel. But with the progress of science and technology, more and more blind people's auxiliary devices have emerged, such as blind sticks with sensors, blind people's glasses with cameras, machine guide dogs, etc., and artificial intelligence technology is introduced to provide voice prompts to help visually impaired people detect obstacles and traffic signs and guide the blind forward. Blind sticks give the visually impaired greater independence because they are easy to use, do not require special training, and can be used in various environments. Therefore, compared with other blind people's auxiliary devices, blind sticks are more popular among the visually impaired.

[0003] The existing blind stick guides the visually impaired by adding various devices to the blind stick to guide the visually impaired to travel, which can provide path planning and obstacle avoidance for the visually impaired, but the guidance information provided by these methods is usually rough and requires users to react based on their senses without providing active guidance. The real environment is complex and variable, and users lack a sense of security when traveling based on voice guidance alone.

[0004] Therefore, there is a need for a new technical solution. SUMMARY

[0005] The first object of the present application is to provide a safe path navigation method for a blind stick, which specifically comprises the following steps:

[0006] Planning a path according to the current position and the target position of the user to generate an initial path;

[0007] Guiding the user to travel along the initial path;

[0008] Establishing a path width model to obtain a safe path width through the path width model;

[0009] Real-time monitoring of the user's position during travel to ensure that the user is always within the safe path width range.

[0010] Further, the planning of the path according to the current position and the target position of the user specifically comprises:

[0011] Obtaining the current position through a positioning device and obtaining the target position through voice recognition;

[0012] Integrating the current position and the target position into map data and obtaining an initial path through a path planning algorithm.

[0013] Further, the establishing the path width model specifically comprises:

[0014] scanning the surrounding environment to determine whether there is an obstacle;

[0015] if there is no obstacle, setting a reasonable safety path width according to the user state on the basis of the initial path.

[0016] Optionally, the establishing the path width model further comprises:

[0017] if there is an obstacle, obtaining an obstacle image;

[0018] obtaining information of the obstacle according to the obstacle image; the obstacle information comprises an obstacle position and an obstacle shape;

[0019] determining a minimum safety distance around the obstacle according to the obstacle information and a pedestrian passing standard;

[0020] updating the path based on the minimum safety distance and the obstacle information to obtain a new path;

[0021] on the basis of the new path, setting a reasonable safety path width in combination with the environmental condition and the user state;

[0022] wherein the obtaining the information of the obstacle according to the obstacle image specifically comprises:

[0023] obtaining a depth image of the obstacle, and establishing a three-dimensional point cloud model according to the depth image;

[0024] obtaining the obstacle information based on the three-dimensional point cloud model.

[0025] Further, the ensuring that the user is always within the safety path width range specifically comprises:

[0026] determining a center position according to the safety path width;

[0027] obtaining a distance between the blind stick and the center position, denoted as a center distance;

[0028] starting a hierarchical vibration feedback according to the center distance to remind the user to be always within the safety path width range.

[0029] Further, the starting the hierarchical vibration feedback according to the distance specifically comprises:

[0030] comparing the center distance with a first preset threshold value;

[0031] if the center distance is greater than the first preset threshold value, indicating that the blind stick is not within the safety path width range, the blind stick vibrates strongly.

[0032] If the center distance is less than or equal to a first preset threshold, indicating that the blind stick is within the safe path width range, the position relationship between the blind stick and the path edge is compared.

[0033] Further, the comparison of the position relationship between the blind stick and the path edge specifically includes:

[0034] determining the position of the path edge according to the safe path width;

[0035] obtaining the distance between the blind stick and the closer path edge, denoted as an edge distance;

[0036] comparing the edge distance with a second preset threshold;

[0037] If the edge distance is greater than or equal to the second preset threshold, indicating that the blind stick approaches the path edge but does not reach the path edge, the blind stick is slightly vibrated;

[0038] If the edge distance is less than the second preset threshold, indicating that the blind stick has reached the path edge, the blind stick is moderately vibrated.

[0039] Further, the reminding the user to be within the safe path width range specifically includes:

[0040] guiding the user to adjust the advancing direction according to the vibration feedback through voice prompt:

[0041] obtaining the position of the blind stick after starting the hierarchical vibration feedback, and determining the position relationship between the blind stick and the center position;

[0042] If the blind stick is on the left of the center position, guiding the user to move right;

[0043] If the blind stick is on the right of the center position, guiding the user to move left.

[0044] A second object of the present application is to provide a blind stick applying the safe path navigation method of the blind stick according to any one of the embodiments of the present application.

[0045] A third object of the present application is to provide an electronic device, comprising: a memory having program code stored thereon; a processor connected with the memory, and when the program code is executed by the processor, the safe path navigation method of the blind stick according to any one of the embodiments of the present application is realized.

[0046] A fourth object of the present application is to provide a computer readable storage medium having program instructions stored thereon, and the program instructions are executed to realize the safe path navigation method of the blind stick according to any one of the embodiments.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] The application provides a safety path navigation method for a blind stick, which forms a cooperative working system through the organic combination of the blind stick and a visual camera, and monitors the positional relationship between the user and the safety path width in real time; through different levels of vibration feedback, the user is reminded to adjust the travel direction in real time, so as to ensure that the user always travels within the safety path width of the path, and the safety and independence of the visually impaired person are greatly improved.

[0049] Through the fusion of multiple optimization algorithms for specific tasks, the blind stick can provide a highly intelligent and adaptive navigation experience, ensuring that the blind user can safely and independently move in a complex and variable environment. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0051] Figure 1 is a safety path navigation method flowchart of the blind stick provided by the first embodiment of the application;

[0052] Figure 2 is a safety path navigation method flowchart of the blind stick provided by the first embodiment of the application;

[0053] Figure 3 is a blind stick position judgment flowchart of the safety path navigation method provided by the first embodiment of the application;

[0054] Figure 4 is an electronic device schematic diagram provided by the third embodiment of the application;

[0055] Figure 5 is a storage medium schematic diagram provided by the fourth embodiment of the application. DETAILED DESCRIPTION

[0056] The embodiments of the application will be described in detail below with reference to the drawings.

[0057] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0059] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0060] Example 1

[0061] Figure 1 This is a flowchart illustrating a safe path navigation method using a white cane provided in an embodiment of the present invention. This embodiment is applicable to situations where visually impaired individuals navigate using a white cane. Figure 1 As shown, a safe path navigation method using a white cane specifically includes the following steps:

[0062] S1: Plan a route based on the user's current location and target location, and generate an initial route;

[0063] It should be noted that route planning based on the user's current location and target location specifically includes:

[0064] The current location is obtained through a positioning device, and the target location is obtained through a voice device;

[0065] The current position and the target position are integrated into the map data, and an initial path is obtained through a path planning algorithm.

[0066] In this embodiment, the positioning device is located in the blind stick. The positioning device can be a global positioning navigation system, a Beidou satellite navigation system, an inertial navigation system, etc. The global positioning navigation system has good long-term accuracy, but poor short-term accuracy, low data output frequency, and is greatly affected by the environment. The inertial navigation system has high short-term measurement accuracy and high update frequency, but the inertial navigation system data drifts, and the long-term navigation error is large.

[0067] In this embodiment, the global positioning navigation system and the inertial navigation system are combined, and the data measured by the two systems is fused through a Kalman filtering algorithm to obtain data with high stability and accuracy in long and short terms, so as to realize accurate positioning of the user.

[0068] In another preferred embodiment, Wi-Fi positioning or Bluetooth beacon technology positioning can be supplemented in indoor or poor signal areas.

[0069] In another preferred embodiment, an easily identifiable marker point is added to the blind stick, and the marker point is tracked in real time by using computer vision technology to facilitate determination of the position and direction of the blind stick, so as to obtain the current position of the user.

[0070] The map data is detailed map data provided by a professional surveying and mapping institution, which contains road width, pedestrian crossing, building outline, etc. The map data is updated regularly to keep it up to date.

[0071] The voice device uses a new natural language processing technology to recognize the user's language. The natural language processing technology converts the user's voice into executable instructions, and provides feedback to the user through voice synthesis technology. The user can interact with the blind stick through voice commands, ask for the current position, set the target position, etc.

[0072] The path planning algorithm can be an improved A* algorithm or a D* series algorithm. These algorithms consider path cost and obstacle information, and can quickly generate an efficient path. Among them, the improved A* algorithm effectively improves the shortcomings of the traditional A* algorithm through operations such as expanding adjacent points, removing redundant points and path smoothing. Experimental results show that the improved A* algorithm can reduce the number of expanded nodes when generating an initial path, and reduce system memory occupancy.

[0073] The D* algorithm estimates the path consumption to reach the target position through an estimation function and a fast retrieval function, and reduces unnecessary calculations. In the search process, all grids are marked as known or unknown, and they are sorted according to the values of the estimation function and the fast retrieval function.

[0074] In practical applications, appropriate algorithms can be selected according to specific needs. For example, if it is necessary to quickly find the shortest path, the A* algorithm can be selected; if the environment changes frequently, the D* algorithm can be selected.

[0075] S2: guiding the user to travel along the initial path;

[0076] In this embodiment, the blind stick integrates multiple sensors and intelligent technologies, combined with a voice device, to generate relevant voice prompts by considering the current position and travel direction of the user, guiding the user to travel along the initial path. For example, the blind stick uses GPS and cameras for accurate positioning and environment detection, combined with voice navigation functions, to help visually impaired people independently travel to the destination. The integration of these technologies ensures that visually impaired people can safely and effectively navigate in complex environments.

[0077] S3: establishing a path width model to obtain the safe path width through the path width model;

[0078] It should be noted that, as Figure 2 establishing a path width model specifically includes:

[0079] S301: scanning the surrounding environment to determine whether there are obstacles;

[0080] Specifically, if there are no obstacles, S302 is executed;

[0081] If there are obstacles, S303-S307 are executed.

[0082] In this embodiment, scanning the surrounding environment is achieved by installing multiple sensors on the blind stick. Alternatively, scanning the surrounding environment uses a high-resolution camera located on the blind stick with sufficient frame rate to track the blind stick movement in real time. For example, a binocular camera, a ToF camera, or a stereo vision system uses depth perception technology to scan the surrounding environment to obtain surrounding environment images, and determines whether there are obstacles through image recognition algorithms. In order to adapt to different lighting conditions, the camera may also be equipped with automatic exposure and automatic focusing functions.

[0083] In another preferred embodiment, an ultrasonic sensor can be used to emit ultrasonic waves to the surroundings, and the time and intensity of the ultrasonic wave reflection are used to determine whether there are obstacles and the approximate distance of the obstacles. The formula for detecting the distance of obstacles by the ultrasonic sensor is: distance = ultrasonic propagation speed x ultrasonic round-trip time / 2. The propagation speed of ultrasonic waves in air is usually 340 m / s. For example, if the ultrasonic round-trip time is 0.01 s, the distance is 340 x 0.01 / 2 = 1.7 m.

[0084] At the same time, an infrared sensor can be combined to detect the heat radiation of the surrounding objects, further assisting in judging the existence of obstacles. When the sensor detects an obstacle, a miniature camera on the blind stick will automatically start to directly obtain the image of the obstacle. The camera can use a high-resolution image sensor to ensure that a clear obstacle image can be captured.

[0085] Alternatively, the judgment of whether there is an obstacle can also be realized by a target detection algorithm. A target detection model is established according to the target detection algorithm, and the target detection model is trained by a training data set to obtain a target detection model that meets the detection requirements. The training data set can be images containing vehicles, pedestrians, fixed objects and other obstacles, and the labels of the data in the training set represent whether the environment contains obstacles.

[0086] The target detection algorithm can use traditional target detection methods, such as Haar features, HOG features, LBP features, combined with machine learning methods such as AdaBoost, SVM, DPM, etc. to realize the identification and judgment of obstacles.

[0087] The target detection algorithm can also use a target detection algorithm based on deep learning (CNN), including RCNN series, SSD, YOLO series algorithm, etc. The RCNN series algorithm can use R-CNN, Fast R-CNN, etc.

[0088] Taking the Fast R-CNN algorithm as an example, the camera continuously captures the images of the surrounding environment, the images are subjected to feature extraction by a feature extractor to obtain a feature map, a selective search algorithm is run on the original image, and the regions of interest are mapped to the feature map. Each region of interest is subjected to a region of interest pooling operation to obtain an equal-length feature vector. The obtained feature vectors are sorted into positive and negative samples, and are batched into parallel R-CNN subnetworks for classification and regression, and the losses of the two are unified. Through training, a target detection model is obtained, and the images of the surrounding environment actually collected are input into the target detection model to identify the target region containing obstacles, which can realize high-speed and accurate target detection.

[0089] The region of interest pooling operation is a key operation for preparing data input into the R-CNN subnetwork. Since the obtained regions of interest usually have different sizes, after being mapped to the feature map, feature tensors of different sizes are obtained. The region of interest pooling operation first divides the region of interest into a target number of grids, and then performs a maximum pooling operation on each grid to obtain an equal-length region of interest feature vector.

[0090] S302: On the basis of the initial path, set a reasonable safety path width according to the user state.

[0091] In the present embodiment, the safety path width is the width of the safety travel area planned for the user by the white cane, to ensure that the user has enough space to adjust when walking. Generally, the safety path width needs to be wide enough to accommodate a person walking normally, and to leave room for unexpected situations.

[0092] The user state includes the walking speed and walking habits of the user, etc. If the user walks faster, a relatively narrow safety path width may be needed to ensure the efficiency of navigation; while if the user is slower or requires higher safety, the system will accordingly expand the safety path width. For example, for an elderly and disabled blind user, the safety path width can be set wider, so that they have enough time and space to deal with possible unexpected situations. When setting the safety path width, the body measurement size also needs to be considered, and a certain margin is left according to the activity comfort and safety requirements.

[0093] S303: Obtain an obstacle image;

[0094] S304: Obtain information of the obstacle according to the obstacle image; the obstacle information includes the position of the obstacle and the shape of the obstacle;

[0095] Specifically, by analyzing the pixels in the obstacle image, the coordinate position of the obstacle in the obstacle image can be determined, and then combined with the parameters of the camera and the position information of the white cane, the position of the obstacle in the actual space can be calculated.

[0096] For example, assuming that the imaging plane coordinate system of the camera is (x, y), the coordinate of the image center point is (x0, y0), and the pixel size is dx and dy (unit: meter / pixel). For the obstacle pixel coordinate (x1, y1) detected in the image, the position coordinate (X, Y) of the obstacle in the actual space can be calculated by the following formula:

[0097] X = (x1-x0) x dx

[0098] Y = (y1-y2) x dy

[0099] It should be noted that obtaining the information of the obstacle according to the obstacle image specifically includes:

[0100] Obtaining a depth image of the obstacle, and establishing a three-dimensional point cloud model according to the depth image;

[0101] Obtaining the obstacle information based on the three-dimensional point cloud model.

[0102] Optionally, the technical route for collecting the depth image includes ToF (Time-of-Flight), binocular vision, structured light, etc.

[0103] In order to accurately detect objects in a short time, and not be affected by humidity, air pressure and temperature, make it suitable for use on a white cane, detect close-range and long-range obstacles of various shapes and sizes. In some preferred embodiments, a ToF camera is used which is accurate, fast, long-range, and low-cost.

[0104] The ToF camera uses a tiny emitter to emit infrared light or laser, where the generated light will bounce off any object and return to the ToF camera. According to the time difference between the emission of light and the reflection of light by the object returning to the ToF camera, the sensor can measure the distance between the object and the ToF camera.

[0105] The ToF camera can provide depth information, combined with the camera, a depth image can be obtained, so that the distance between the user and the obstacle and the position of the obstacle can be obtained. Then convert the depth image into a three-dimensional point cloud model to obtain the shape of the obstacle.

[0106] Through the depth information obtained by stereo vision or ToF camera, a three-dimensional point cloud model is constructed, which realizes more accurate obstacle positioning and shape recognition, and facilitates subsequent generation of a new path that avoids the obstacle according to the obstacle position and obstacle shape.

[0107] S305: Determine the minimum safety distance around the obstacle according to the obstacle information and the pedestrian traffic standard;

[0108] For example, the shape of the obstacle can be circular, square, irregular, etc.

[0109] If the obstacle is a circular obstacle, assuming the radius of the circular obstacle is r, then the minimum safety distance D min_circle is:

[0110] D min_circle =r+k1×w

[0111] where k1 is a safety distance coefficient, which can be valued according to the actual situation, generally between 1.2-1.5; w is the average width of the human body.

[0112] If the obstacle is a square obstacle, the side length is a and b, then the minimum safety distance D min_aquare is:

[0113] D min_aquare =max(a,b) / 2+k2×w

[0114] where k2 is a safety distance coefficient, similar to k1; w is the average width of the human body.

[0115] If the obstacle is an irregularly shaped obstacle, the size of the minimum circumscribed rectangle of the irregularly shaped obstacle can be calculated, and then the minimum safety distance is determined in the manner of a square obstacle.

[0116] In another preferred embodiment, the minimum safety distance can also be set according to factors such as the average reaction time and walking speed of the user. The minimum safety distance can be a threshold value. The motion state of the user is monitored by the built-in accelerometer and gyroscope, and the data is fused by the Kalman filter to accurately estimate the instantaneous speed of the user. The minimum safety distance is dynamically updated according to the instantaneous speed. For example, when the user walks at a speed of 5 km / h, the safety distance is set to 0.8 meters; if the speed increases to 7 km / h, it is adjusted to 1 meter accordingly.

[0117] S306: Update the path based on the minimum safety distance and the obstacle information to obtain a new path;

[0118] Specifically, the new path avoids the obstacle and has a minimum safety distance from the obstacle, ensuring that the user will not collide with the obstacle.

[0119] In this embodiment, the method can update the path in real time to respond to changes in the environment, such as newly appearing obstacles or moving objects.

[0120] S307: Based on the new path, set a reasonable safety path width in combination with the environmental conditions and the user's state.

[0121] Specifically, the environmental conditions include obstacle information; the user's state includes the user's walking speed and walking habits.

[0122] The safety path width is the width of the safe travel area planned by the white cane for the user. The safety path width is set according to the environmental conditions and the user's walking speed and habits to ensure that the user can avoid obstacles and have enough space to adjust when walking. Under normal circumstances, the safety path width needs to be wide enough to accommodate a person walking normally, and there is a margin to deal with unexpected situations.

[0123] S4: Monitor the user's position in real time during the travel process to ensure that the user is always within the safety path width range.

[0124] It should be noted that, as Figure 3 ensuring that the user is always within the safety path width range specifically includes:

[0125] S401: Determine the center position according to the safety path width;

[0126] S402: Obtain the distance between the white cane and the center position, denoted as the center distance;

[0127] S403: Start a hierarchical vibration feedback according to the center distance to remind the user that he is always in the safe path width range.

[0128] Specifically, the step of starting a hierarchical vibration feedback according to the center distance comprises:

[0129] S4031: Determine whether the center distance is greater than a first preset threshold value;

[0130] Specifically, if the center distance is greater than the first preset threshold value, execute S4032;

[0131] If the center distance is less than or equal to the first preset threshold value, execute S4033;

[0132] S4032: Indicate that the blind stick is out of the safe path width range, and the blind stick vibrates strongly;

[0133] S4033: Indicate that the blind stick is in the safe path width range, and compare the position relationship between the blind stick and the path edge.

[0134] Specifically, the first preset threshold value is half of the safe path width value.

[0135] S4034: Determine the position of the path edge according to the safe path width;

[0136] S4035: Obtain the distance between the blind stick and the closer path edge, denoted as edge distance;

[0137] S4036: Determine whether the edge distance is greater than or equal to a second preset threshold value;

[0138] If the edge distance is greater than or equal to the second preset threshold value, execute S4037:

[0139] If the edge distance is less than the second preset threshold value, execute S4038:

[0140] S4037: Indicate that the blind stick is close to the path edge but has not reached the path edge, and the blind stick vibrates slightly;

[0141] S4038: Indicate that the blind stick has reached the path edge, and the blind stick vibrates moderately.

[0142] Specifically, the second preset threshold value represents a safe distance between the blind stick and the path edge, and the second preset threshold value can also be set as needed.

[0143] In the embodiment, the user is given a haptic feedback of vibration through the vibration device built in the blind stick to start the graded vibration feedback, and the user is informed of the position relationship with the safe path width at the moment according to the vibration prompt of different levels, so as to adjust the position of the user immediately and keep the user in the safe path width range. The graded vibration feedback greatly enhances the perception ability of the visually impaired by providing additional sensory information, and helps them to move and interact in the environment more safely and more confidently.

[0144] It should be noted that the user is reminded to be in the safe path width range all the time, which specifically includes:

[0145] The user is guided to adjust the walking direction according to the vibration feedback through voice prompts:

[0146] After starting the graded vibration feedback, the position of the blind stick is acquired, and the position relationship between the blind stick and the center position is judged.

[0147] If the blind stick is on the left of the center position, the user is guided to move to the right.

[0148] If the blind stick is on the right of the center position, the user is guided to move to the left.

[0149] For example, in the walking process, the blind stick vibrates moderately, and it is judged that the blind stick is located on the left of the center position at the moment, indicating that the user reaches the path edge on the left of the safe path width, and needs to walk to the right to correct the walking direction. Therefore, the user is reminded to adjust the walking direction to the right through voice prompts.

[0150] In the embodiment, through the organic combination of the blind stick and the visual camera, a cooperative working system is formed to monitor the position relationship between the user and the safe path width in real time. Through the vibration feedback of different levels, the user is reminded to adjust the walking direction immediately to ensure that the user always walks in the safe path width range of the path. The method has the characteristics that the user does not need to know whether there is an obstacle in front of him or what kind of obstacle it is. The user only needs to detect left and right through the blind stick to keep himself in the safe path width range of the planned path and walk until reaching the destination, which greatly improves the safety and independence of the visually impaired.

[0151] Embodiment Two

[0152] A blind stick applies the safe path navigation method of the blind stick according to any one of the embodiments of the application. For detailed description of the method, reference can be made to the corresponding description in the above method embodiments, which will not be described here again.

[0153] Embodiment Three

[0154] An electronic device 300, such as Figure 4As shown, it includes: a memory 301 storing program code; and a processor 302 connected to the memory, which, when the program code is executed by the processor, implements a safe path navigation method for a white cane. For a detailed description of the method, please refer to the corresponding description in the above method embodiments, which will not be repeated here.

[0155] Example 4

[0156] A computer-readable storage medium 400, such as Figure 5 As shown, it stores program instructions 401, which, when executed, implement a safe path navigation method for a white cane. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here.

[0157] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A safe path navigation method of a blind stick, characterized by, Specifically comprising the following steps: Planning a path according to the current position and the target position of the user, generating an initial path; Guiding the user to travel along the initial path; establishing a path width model to obtain a safe path width through the path width model; Monitoring the position of the user in real time during the travel to ensure that the user is always within the safe path width range; The establishment of the path width model specifically comprises: scanning the surrounding environment to determine whether there are obstacles; if there are no obstacles, set a reasonable safe path width according to the user's state on the basis of the initial path; the establishment of the path width model also comprises: if there are obstacles, obtain an obstacle image; obtain the information of the obstacle according to the obstacle image; the obstacle information includes the position of the obstacle and the shape of the obstacle; determine the minimum safe distance around the obstacle according to the obstacle information and the pedestrian traffic standard; update the path based on the minimum safe distance and the obstacle information to obtain a new path; set a reasonable safe path width based on the new path, combined with the environmental conditions and the user's state; wherein obtaining the information of the obstacle according to the obstacle image specifically comprises: obtaining a depth image of the obstacle, and establishing a three-dimensional point cloud model according to the depth image; obtaining the obstacle information based on the three-dimensional point cloud model; The user's state includes the user's walking speed and walking habit. If the user's walking speed is fast, a relatively narrow safe path width may be needed to ensure the efficiency of navigation; if the user's action is more sluggish or the user requires higher safety, the system will accordingly expand the safe path width; when setting the safe path width, the body measurement size also needs to be considered, and a certain amount of allowance is required according to the activity comfort and safety requirements.

2. The method of claim 1, wherein, The planning of the path according to the current position and the target position of the user specifically comprises: obtaining the current position through a positioning device, and obtaining the target position through voice recognition; integrating the current position and the target position into map data, and obtaining an initial path through a path planning algorithm.

3. The safe path navigation method of a blind stick according to claim 2, characterized by, The ensuring that the user is always within the safe path width range specifically comprises: determining a center position according to the safe path width; obtaining the distance between the blind stick and the center position, denoted as the center distance; starting a hierarchical vibration feedback according to the center distance to remind the user to always be within the safe path width range.

4. The safe path navigation method of a blind stick according to claim 3, characterized by, Starting a hierarchical vibration feedback according to the distance specifically comprises: comparing the center distance with a first preset threshold; if the center distance is greater than the first preset threshold, indicating that the blind stick is not within the safe path width range, the blind stick vibrates strongly; if the center distance is less than or equal to the first preset threshold, indicating that the blind stick is within the safe path width range, then compare the positional relationship between the blind stick and the path edge.

5. The safe path navigation method of a blind stick according to claim 4, wherein, The comparison of the position relationship between the blind stick and the path edge specifically includes: determining the position of the path edge according to the safety path width; obtaining the distance between the blind stick and the closer path edge, denoted as edge distance; comparing the edge distance with a second preset threshold; if the edge distance is greater than or equal to the second preset threshold, it indicates that the blind stick approaches the path edge but does not reach the path edge, and the blind stick slightly vibrates; if the edge distance is less than the second preset threshold, it indicates that the blind stick has reached the path edge, and the blind stick moderately vibrates.

6. The safe path navigation method of a blind stick according to claim 5, wherein, The reminding the user to always be within the safety path width specifically includes: guiding the user to adjust the marching direction according to the vibration feedback through voice prompt: obtaining the position of the blind stick after starting the hierarchical vibration feedback, and judging the position relationship between the blind stick and the center position; if the blind stick is on the left of the center position, guiding the user to move right; if the blind stick is on the right of the center position, guiding the user to move left.

7. A white cane, characterized by The method of any one of claims 1-6 is applied.

8. An electronic device, comprising: comprising: a memory having program code stored thereon; a processor connected with the memory, and when the program code is executed by the processor, the method of any one of claims 1-6 is implemented.

9. A computer-readable storage medium, characterized in that, having program instructions stored thereon, the program instructions being executed to implement the method of any one of claims 1-6.

Images