Blind guiding walking stick system based on equipment terminal cooperation

Abstract

The invention relates to the technical field of intelligent auxiliary equipment, and provides a blind guiding walking stick system based on equipment terminal collaboration, comprising a blind guiding walking stick which comprises a main control unit and a walking device; the equipment terminal is in communication connection with the blind guiding walking stick; the equipment terminal comprises an image acquisition device and an information processing device, the image acquisition device is used for acquiring an environment image, and the information processing device is used for processing the environment image, generating a walking strategy instruction and sending the walking strategy instruction to the main control unit; and the main control unit receives the walking strategy instruction and controls the walking device to execute corresponding operation according to the walking strategy instruction. Through cooperative work division of the equipment terminal and the blind guiding crutch, the terminal is responsible for environment perception and decision making, and the crutch is responsible for motion execution, so that the key problems that a traditional scheme depends on high-cost special hardware, indoor and outdoor scene adaptive splitting is achieved, and the low obstacle detection capacity is insufficient are fundamentally solved; and active navigation and obstacle avoidance with low cost, high precision and full-scene coverage are realized.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent assistive devices, and in particular to a blind guide cane system based on device terminal collaboration. Background Art

[0002] With the increasing demand for independent travel among the visually impaired, smart guide canes have received widespread attention as an important auxiliary device. Traditional smart guide canes rely on built-in sensors (such as ultrasound and lidar) to achieve navigation and obstacle avoidance functions, but there are significant technical defects in practical applications. First, the hardware cost is high, and second, the scene adaptability is poor. For example, in indoor areas or areas without GPS signals, the GPS positioning function that traditional canes rely on fails and cannot provide continuous navigation. In addition, the built-in processor computing power of traditional canes is limited, making it difficult to run complex visual algorithms (such as SLAM and target detection), resulting in weak dynamic obstacle avoidance capabilities. Therefore, there is an urgent need for a low-cost, high-precision, full-scene coverage smart guide cane solution to address the limitations of traditional technologies and meet users' needs for safe and convenient navigation. Summary of the invention

[0003] The main purpose of this application is to provide a guide cane system based on device terminal collaboration, aiming to provide a low-cost, high-precision, full-scenario coverage intelligent guide cane solution to address the limitations of traditional technology and meet users' needs for safe and convenient navigation.

[0004] In a first aspect, the present application provides a blind guide cane system based on device terminal collaboration, comprising: A guide cane for the blind, comprising a main control unit and a walking device; A device terminal is communicatively connected with the guide crutch; the device terminal comprises an image acquisition device and an information processing device, the image acquisition device is used to acquire an environmental image, the information processing device is used to process the environmental image and generate a walking strategy instruction, and send the walking strategy instruction to the main control unit; The main control unit receives the walking strategy instruction, and controls the walking device to perform corresponding operations according to the walking strategy instruction.

[0005] In one embodiment, the guide crutch also includes a detachably connected fixing structure for fixing the device terminal, and the fixing structure includes a magnetic multi-angle adjustment bracket to adapt to different device terminals.

[0006] In one embodiment, the communication module between the guide crutch and the device terminal includes a Bluetooth module or a WiFi module for transmitting the walking strategy instructions in real time.

[0007] In one embodiment, the walking device includes a motor-driven wheel group, and the motor-driven wheel group includes a stepping motor and a reduction gear, which is used to respond to the walking strategy instructions of the main control unit to achieve speed regulation or direction adjustment.

[0008] In one embodiment, the information processing device processes the environment image by a synchronous positioning and map building algorithm to build an environment map in real time and fuse the environment map with offline map data to generate a navigation path.

[0009] In one embodiment, the simultaneous positioning and mapping algorithm includes: A feature extraction module, the feature extraction module is used to extract feature points from the environmental image; a feature matching module is used to match the feature points and output matching results; a map optimization module is used to optimize the terminal device posture and the environmental map according to the matching results.

[0010] In one embodiment, the information processing device is also used to execute a target detection algorithm to generate a graded obstacle avoidance strategy based on obstacle type and distance: including: generating a deceleration instruction when a static obstacle is detected to enter a first preset distance range; generating a detour path planning instruction when a dynamic obstacle is detected to enter a second preset distance range; generating an emergency braking instruction when an obstacle distance is detected to be less than a third distance range.

[0011] In one embodiment, the target detection algorithm includes a deep learning based target detection model.

[0012] In one embodiment, the device terminal integrates a voice interaction module for switching navigation modes and / or broadcasting navigation instructions through voice commands.

[0013] In one embodiment, the voice interaction module is used to receive and process the voice instructions to switch the navigation mode, and the navigation mode includes an indoor mode and an outdoor mode; the navigation instructions include path guidance, obstacle warning and safety prompts.

[0014] In a second aspect, the present application provides a device terminal for a blind guide cane system, comprising: An image acquisition device, used for acquiring environmental images; An information processing device, used for processing the environment image and generating walking strategy instructions; A communication module, used for sending the walking strategy instruction to the main control unit of the guide crutch; Voice interaction module, used to receive voice commands and broadcast navigation information; A fixed structure is used to detachably connect the device terminal to a guide cane. An embodiment of the present application provides a guide cane system based on device terminal collaboration, including: a guide cane, which includes a main control unit and a walking device; a device terminal, which is communicatively connected to the guide cane; the device terminal includes an image acquisition device and an information processing device, the image acquisition device is used to acquire environmental images, the information processing device is used to process environmental images and generate walking strategy instructions, and send the walking strategy instructions to the main control unit; the main control unit receives the walking strategy instructions, and controls the walking device to perform corresponding operations according to the walking strategy instructions. Through the collaborative division of labor between the device terminal and the guide cane, in which the terminal is responsible for environmental perception and decision-making, and the cane is responsible for motion execution, it fundamentally solves the key problems of traditional solutions relying on high-cost dedicated hardware, the separation of indoor and outdoor scene adaptability, and insufficient low obstacle detection capabilities, and realizes low-cost, high-precision, full-scene coverage active navigation and obstacle avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of the structure of a blind guide crutch system based on device terminal collaboration provided in one embodiment of the present application; Figure 2 A schematic diagram of the structure of a device terminal for a blind guide crutch system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0019] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, the singular forms of "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0020] Currently, existing smart guide canes rely on built-in sensors and processors to achieve navigation or obstacle avoidance functions. For example, they need to integrate special sensors such as ultrasound and lidar, which makes the equipment large, expensive, and poor in scene adaptability. Because GPS cannot work indoors or in areas without signals, ultrasonic sensors tend to ignore low obstacles (such as steps, etc.). In addition, the built-in processor has difficulty running complex visual algorithms due to limited computing power, resulting in weak dynamic obstacle avoidance capabilities.

[0021] To this end, an embodiment of the present application provides a blind guide cane system based on device terminal collaboration. Figure 1 and Figure 2 As shown, a blind guide cane system 100 based on device terminal collaboration includes: a blind guide cane 102, which includes a main control unit (not shown) and a walking device 1021; a device terminal 101, which is connected to the blind guide cane 102 in communication; the device terminal 101 includes an image acquisition device and an information processing device, the image acquisition device is used to acquire environmental images, the information processing device is used to process environmental images and generate walking strategy instructions, and send the walking strategy instructions to the main control unit; the main control unit receives the walking strategy instructions, and controls the walking device to perform corresponding operations according to the walking strategy instructions. Through the collaborative division of labor between the device terminal 101 and the blind guide cane 102, the terminal is responsible for environmental perception and decision-making, and the cane is responsible for motion execution, which fundamentally solves the key problems of the traditional solution relying on high-cost dedicated hardware, the separation of indoor and outdoor scene adaptability, and the insufficient ability to detect low obstacles, and realizes low-cost, high-precision, full-scene coverage active navigation and obstacle avoidance.

[0022] In one embodiment, the device terminal 101 further includes a communication module, which includes a Bluetooth module or a WiFi module, for transmitting the walking strategy instruction to the main control unit in real time.

[0023] In one embodiment, the terminal device 101 includes a mobile phone, and the image acquisition device includes a camera module built into the mobile phone, specifically including at least one of an RGB camera lens, a depth camera lens, and an ultra-wide-angle lens. In one embodiment, the RGB camera lens continuously captures the front environment video stream at 30fps. The depth camera lens includes a TOF depth lens, and the ToF depth lens is only activated when an obstacle enters within 5m to provide a real-time depth map for auxiliary distance measurement. When a complex scene (such as a narrow passage or a crowded area) is detected, the ultra-wide-angle lens can be automatically activated to stitch a panoramic image. It can be seen that the environmental image captured by the image acquisition device includes at least one of an environmental video stream, a depth map, and a panoramic image.

[0024] In one embodiment, the information processing device further includes an image preprocessing unit and a data fusion unit. The image preprocessing unit is used to perform real-time distortion correction, dynamic exposure adjustment and noise reduction on the collected environmental image. The preprocessed environmental image is transmitted to the data fusion unit to generate image fusion data. For example, in one embodiment, the data fusion unit can fuse the ToF depth map with the RGB map to generate RGB-D fusion data. Specifically, the data fusion unit ensures that the ToF depth map and the RGB image are collected at the same time through timestamp synchronization; secondly, the camera intrinsic parameters (focal length, principal point offset) and extrinsic parameters (relative position of ToF and RGB camera) are used for coordinate system registration, and each pixel of the depth map is mapped to the corresponding position of the RGB image; finally, the registered data is interpolated and optimized to fill the holes or missing areas in the depth map to generate dense RGB-D fusion data.

[0025] In one embodiment, the information processing device processes the environment image by a synchronous positioning and map building algorithm to build an environment map in real time and fuse the environment map with offline map data to generate a navigation path.

[0026] In one embodiment, the simultaneous positioning and mapping algorithm includes: a feature extraction module, which is used to extract feature points from the environmental image; a feature matching module, which is used to match the feature points and output matching results; and a map optimization module, which is used to optimize the terminal device posture and the environmental map according to the matching results.

[0027] In one embodiment, the information processing device processes RGB-D fusion data through a simultaneous localization and mapping (SLAM) algorithm to construct an environmental map in real time and generate a navigation path. First, the "feature extraction module" extracts feature points (such as ORB features) from the RGB image of the RGB-D fusion data, and uses the depth map to obtain the three-dimensional coordinates of the feature points; then, the "feature matching module" matches the feature points of the current frame with the feature points in the historical frame or offline map, and outputs the matching results; then, the "map optimization module" optimizes the position (6 degrees of freedom) of the terminal device and the geometric structure of the environmental map based on the matching results and combined with the depth information to ensure the accuracy and consistency of the map; finally, the optimized environmental map is fused with offline map data (such as Amap API) to generate a global navigation path, and the path is dynamically adjusted in combination with real-time RGB-D data to avoid obstacles. This process makes full use of the color and depth information of the RGB-D fusion data, significantly improving the navigation accuracy and scene adaptability.

[0028] The information processing device is also used to execute a target detection algorithm to generate a graded obstacle avoidance strategy based on obstacle type and distance: including: generating a deceleration instruction when a static obstacle is detected to enter a first preset distance range; generating a detour path planning instruction when a dynamic obstacle is detected to enter a second preset distance range; and generating an emergency braking instruction when the obstacle distance is detected to be less than a third distance range.

[0029] In one embodiment, the information processing device identifies the obstacle type (dynamic / static) based on the deep learning target detection model algorithm, and the priority response strategy is: deceleration: reduce the travel speed (0.3m / s→0.1m / s) when a static obstacle (such as a table and chair) is detected within 5m; detour: plan a detour path (path curvature radius ≥1m) when a dynamic obstacle (such as a pedestrian) enters the range of 3m; emergency stop: trigger emergency braking when the obstacle distance is <0.5m.

[0030] It is understandable that for deep learning-based target detection model algorithms, lightweight models (such as YOLOv5, MobileNet-SSD, and NanoDet) can be selected; if the accuracy requirements are high and the computing power is sufficient, models such as Faster R-CNN, Mask R-CNN, or DETR can be selected. Different models can be used to adapt to different terminal devices.

[0031] In one embodiment, the device terminal 101 integrates a voice interaction module for switching navigation modes and / or broadcasting navigation instructions through voice commands. The voice interaction module is used to receive and process the voice commands to switch the navigation mode, which includes an indoor mode and an outdoor mode; the navigation instructions include path guidance, obstacle warnings, and safety prompts.

[0032] It is understandable that the core functions of the voice interaction module include voice command reception and processing, navigation mode switching, and navigation command broadcasting. First, the device terminal collects user voice signals through a microphone array and uses a deep learning-based speech recognition algorithm (such as Transformer or RNN-T) to convert the voice into text instructions. The speech recognition model supports multi-language and dialect adaptation, with a recognition accuracy of over 95%. Then, the command semantics are parsed through natural language processing (NLP) technology, such as "switch to indoor mode" or "what obstacles are ahead", so as to perform the corresponding operations.

[0033] The navigation mode switching function allows users to switch seamlessly between indoor and outdoor modes. In indoor mode, the system prioritizes the use of visual SLAM and RGB-D fusion data for positioning and navigation, while turning off GPS to save power; in outdoor mode, the system enables GPS positioning and combines visual SLAM with offline map data to generate a global path. Users can switch modes in real time with simple voice commands (such as "switch to indoor navigation"), and the system will automatically adjust sensor configuration and algorithm parameters to adapt to different environmental requirements.

[0034] The navigation command broadcast function includes path guidance, obstacle warning and safety tips. For example, the system will broadcast path guidance information such as "turn right in 10 meters ahead" or "go straight for 50 meters to reach the destination"; when an obstacle is detected, it will issue warning information such as "there are pedestrians 3 meters ahead, please pay attention to avoid" or "there are low steps on the left"; in an emergency, the system will prompt "please slow down" or "emergency brake, please stand firm". These instructions are broadcast in real time through the speaker or Bluetooth headset of the device terminal. The speech synthesis (TTS) technology uses a deep learning model (such as Tacotron 2), supports multi-language and emotional broadcasting, and ensures that users can receive information clearly and accurately.

[0035] It is understandable that the voice interaction module relies on the hardware (such as microphone array, speaker and processing chip) and software (such as voice recognition engine, NLP parsing module, TTS engine) of the device terminal 101. Deep learning algorithms (such as Transformer and WaveNet) are used for voice recognition and synthesis, while the rule engine is used for command parsing and mode switching. This combination of hardware and software design enables the voice interaction module to run efficiently and stably.

[0036] Furthermore. Voice interaction realizes the "hands-free" operation mode, which greatly improves the user experience, especially for visually impaired users. Secondly, the seamless switching of indoor and outdoor modes ensures navigation accuracy and continuity, and enhances the system's scene adaptability. In addition, the real-time obstacle warning and safety prompt functions significantly improve user safety and reduce the risk of collision. By quickly switching modes through voice commands, the system can optimize sensor and algorithm resource allocation, thereby reducing power consumption. Finally, the multi-language support function meets the needs of users in different regions and improves the universality of the product.

[0037] From the above content, it can be seen that the voice interaction module realizes efficient and natural voice command processing and navigation command broadcasting through deep learning and NLP technology, which significantly improves the system's usability, safety and scenario adaptability, and provides users with a smarter and more convenient navigation experience.

[0038] like Figure 1 As shown, the guide cane 102 includes a main control unit and a walking device 1021. The main control unit receives a walking strategy instruction and controls the walking device to perform corresponding operations according to the walking strategy instruction. In one embodiment, the walking device includes a motor-driven wheel group, and the motor-driven wheel group includes a stepping motor and a reduction gear, which is used to respond to the walking strategy instruction of the main control unit to achieve speed regulation or direction adjustment.

[0039] like Figure 1 As shown, the guide cane 102 includes a main control unit and a walking device 1021. The main control unit is responsible for receiving walking strategy instructions from the device terminal 101 (such as a smart phone), and controlling the walking device to perform corresponding operations according to the instructions. The core component of the walking device is the motor-driven wheel set, which includes a stepping motor and a reduction gear, and can accurately respond to the instructions of the main control unit to achieve speed regulation and direction adjustment.

[0040] In one embodiment, the main control unit first parses the received walking strategy instructions. For example, when the instruction requires deceleration, the main control unit generates a corresponding PWM (pulse width modulation) signal to control the stepper motor to reduce the speed. The rotation of the stepper motor is transmitted to the drive wheel through the reduction gear, thereby reducing the travel speed of the crutch from the default 0.8 m / s to 0.3 m / s. The design of the reduction gear not only improves the torque output, but also ensures the smoothness of the speed regulation, avoiding the user discomfort that may be caused by sudden deceleration.

[0041] When the command requires a change of direction, the main control unit will control the stepper motors on the left and right sides to run at different speeds according to the detour path generated by the path planning algorithm. For example, when turning right, the speed of the left motor will be slightly higher than that of the right motor, causing the crutch to deflect to the right as a whole. By adjusting the speed difference of the motors on both sides, the system can achieve smooth steering with a curvature radius of ≥1.2 meters, ensuring the user's stability when turning.

[0042] In an emergency, if the distance to an obstacle is less than 0.5 meters, the main control unit will immediately send an emergency stop command. At this time, the stepper motor quickly stops rotating and locks the drive wheel through the electromagnetic brake to ensure that the crutch stops completely within 0.1 seconds. This quick response mechanism effectively avoids the risk of collision and ensures the safety of the user.

[0043] In addition, the main control unit also monitors the speed and position of the stepper motor in real time through the encoder to form a closed-loop control. If a deviation is detected between the actual speed and the target speed (such as slipping due to changes in ground friction), the main control unit will dynamically adjust the PWM signal to ensure that the walking device strictly follows the instructions. This closed-loop control mechanism not only improves the reliability of the system, but also enhances the user experience.

[0044] It can be seen that the motor-driven wheel set can accurately respond to the instructions of the main control unit through the coordinated work of the stepper motor and the reduction gear, and realize functions such as speed regulation, direction adjustment and emergency braking. This design not only ensures the efficient operation of the guide cane, but also provides users with a safe and stable navigation experience.

[0045] In one embodiment, the guide cane 102 further includes a detachably connected fixing structure (not shown) for fixing the device terminal. The fixing structure adopts a "magnetic multi-angle adjustment bracket" to adapt to device terminals of different sizes and models, while providing a flexible angle adjustment function to meet the needs of users in different usage scenarios.

[0046] Specifically, the fixed structure consists of two parts: the "magnetic base" and the "multi-angle adjustment bracket". The magnetic base is firmly connected to the metal frame or special magnetic patch of the device terminal through strong magnets to ensure that the device will not fall off during movement. The multi-angle adjustment bracket adopts a hinge design and supports a pitch angle adjustment range of -30° to 90°. Users can adjust the viewing angle of the device terminal according to their height and usage habits to obtain the best operation and viewing experience. For example, during navigation, users can adjust the device terminal to a slightly tilted angle to more clearly view the real-time path and obstacle markings.

[0047] In addition, the fixed structure is also equipped with a "quick disassembly mechanism". Users only need to gently press the release button on the bracket to remove the device terminal from the crutch, which is convenient for daily use or charging. The bracket is made of lightweight aluminum alloy, which not only ensures the stability of the structure, but also reduces the overall weight and avoids increasing the burden on users. In order to further improve the adaptability, the bracket is also designed with a retractable clamping arm that is compatible with mainstream smartphone sizes from 4.7 inches to 7 inches.

[0048] In actual use, users only need to bring the device terminal close to the magnetic base, and it will be automatically adsorbed and fixed without complicated installation steps. The multi-angle adjustment function allows the device terminal to adapt to different usage scenarios. For example, in outdoor sunlight, users can adjust the screen to the best viewing angle to reduce reflections; in complex indoor environments, users can adjust the angle to ensure that the camera can fully capture the environmental information in front and to the side.

[0049] From the above, we can see that the magnetic multi-angle adjustment bracket not only provides a stable device fixing solution, but also significantly improves the user's convenience and comfort through flexible angle adjustment and quick disassembly design, further enhancing the practicality and scene adaptability of the guide crutch.

[0050] This embodiment provides a device terminal 200 for a guide cane system, including: an image acquisition device 202, used to acquire environmental images; an information processing device 201, used to process the environmental images and generate walking strategy instructions; a communication module 203, used to send the walking strategy instructions to the main control unit of the guide cane; a voice interaction module 204, used to receive voice instructions and broadcast navigation information.

[0051] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0052] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0053] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0054] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0056] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0057] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0058] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A blind guide cane system based on device terminal collaboration, characterized in that: include: A guide crutch for the blind, comprising a main control unit and a walking device; a device terminal, which is communicatively connected to the guide crutch; the device terminal comprises an image acquisition device and an information processing device, the image acquisition device is used to acquire environmental images, the information processing device is used to process the environmental images and generate walking strategy instructions, and send the walking strategy instructions to the main control unit; the main control unit receives the walking strategy instructions, and controls the walking device to perform corresponding operations according to the walking strategy instructions.

2. The blind guide crutch system according to claim 1, characterized in that: The guide crutch also includes a detachably connected fixing structure for fixing the device terminal, and the fixing structure includes a magnetic multi-angle adjustment bracket to adapt to different device terminals.

3. The blind guide crutch system according to claim 1, characterized in that: The communication module between the guide crutch and the device terminal includes a Bluetooth module or a WiFi module for transmitting the walking strategy instructions in real time.

4. The blind guide crutch system according to claim 1, characterized in that: The walking device includes a motor-driven wheel group, and the motor-driven wheel group includes a stepping motor and a reduction gear, which is used to respond to the walking strategy instruction of the main control unit to achieve speed regulation or direction adjustment.

5. The blind guide crutch system according to claim 1, characterized in that: The information processing device processes the environment image by a synchronous positioning and map building algorithm to build an environment map in real time and fuse the environment map with offline map data to generate a navigation path.

6. The blind guide crutch system according to claim 5, characterized in that: The synchronous positioning and mapping algorithm includes: a feature extraction module, which is used to extract feature points from the environmental image; a feature matching module, which is used to match the feature points and output matching results; and a map optimization module, which is used to optimize the terminal device posture and the environmental map according to the matching results.

7. The blind guide crutch system according to claim 1, characterized in that: The information processing device is also used to execute a target detection algorithm to generate a graded obstacle avoidance strategy based on obstacle type and distance: including: generating a deceleration instruction when a static obstacle is detected to enter a first preset distance range; generating a detour path planning instruction when a dynamic obstacle is detected to enter a second preset distance range; and generating an emergency braking instruction when the obstacle distance is detected to be less than a third distance range.

8. The blind guide crutch system according to claim 7, characterized in that: The target detection algorithm includes a target detection model based on deep learning.

9. The blind guide crutch system according to claim 1, characterized in that: The device terminal is integrated with a voice interaction module for switching navigation modes and / or broadcasting navigation instructions through voice commands.

10. The blind guide crutch system according to claim 9, characterized in that: The voice interaction module is used to receive and process the voice instructions to switch the navigation mode, and the navigation mode includes an indoor mode and an outdoor mode; the navigation instructions include path guidance, obstacle warning and safety prompts.

11. A device terminal for a blind guide crutch system, characterized in that: include: An image acquisition device, used for acquiring environmental images; An information processing device, used for processing the environment image and generating walking strategy instructions; A communication module is used to send the walking strategy instruction to the main control unit of the guide cane; a voice interaction module is used to receive voice instructions and broadcast navigation information; and a fixing structure is used to detachably connect the device terminal to the guide cane.

Images