An intelligent wheelchair automatic navigation system and method

Abstract

This invention pertains to wheelchairs, specifically an intelligent wheelchair automatic navigation system and method, comprising the following steps: Step 1: After system startup, the visual sensor module begins operation, monitoring the user's posture and position information. The camera captures the user's body posture and relative position to the wheelchair, and the data is transmitted to the control and execution module for analysis and processing. Step 2: The user can send a summoning signal via voice command or a mobile application, informing the system of their needs. Step 3: After receiving the user's signal and sensor data, the motion control and wheelchair navigation module formulates the optimal navigation route based on the user's requirements. Step 4: Once the navigation route is determined, the wheelchair body will activate its motor according to the instructions of the motion control and wheelchair navigation module, and the wheelchair will avoid obstacles based on the environmental map. Step 5: When the wheelchair reaches the target location, the user can easily get in and out, and the system can automatically stop based on the user's instructions or gestures.

Description

Technical Field

[0001] This invention relates to wheelchairs, specifically to an intelligent wheelchair automatic navigation system and method. Background Technology

[0002] Traditional wheelchairs require family members or staff to move them to a designated parking location when not in use. When the user needs to use them again, someone else must move the wheelchair from its parking location to the user's side. This process cannot be completed by the user independently and requires assistance, causing inconvenience. Therefore, an intelligent wheelchair system capable of dynamically monitoring user needs and navigating autonomously is needed.

[0003] To address the aforementioned technical shortcomings, a solution for an intelligent wheelchair automatic navigation system and method is proposed. Summary of the Invention

[0004] To address the above problems, the present invention provides the following technical solution:

[0005] An intelligent wheelchair automatic navigation system and method includes a visual sensor component module, a control and execution module, a motion control and wheelchair navigation module, a user feedback and system optimization module, a trajectory analysis and preference learning module, and a user interface module;

[0006] The visual sensor component module includes a high-resolution camera, a lidar, and a depth sensor. These sensors are responsible for monitoring the environment around the wheelchair in real time, capturing the user's posture information and position data, and transmitting the captured data to the control execution module.

[0007] The control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The control and execution module receives sensor data information from the vision sensor component module and processes the information through the data processing and fusion unit. The processed information is then transmitted to the path planning and navigation unit. Based on user needs, environmental information, and historical trajectory analysis and preferences, the path planning and navigation unit determines the optimal path for the wheelchair and transmits the path information to the motion control and wheelchair navigation module.

[0008] The motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The wheelchair body is the physical part of the smart wheelchair, consisting of an electric wheelchair chassis, a seat, and a battery. These components work together and, based on the path planning data of the path planning and navigation unit in the control and execution module, enable the wheelchair to move along the path of the control and execution module according to the instructions of the PID controller. During the movement, the wheelchair body dynamically adjusts the path through the obstacle avoidance and dynamic adjustment unit, and this data information is transmitted to the user feedback and system optimization module in real time.

[0009] The user feedback and system optimization module collects real-time user feedback through voice recognition, touchscreen, and buttons, and uploads this feedback information to the motion control and wheelchair navigation module in real time. The motion control and wheelchair navigation module processes the received information and combines it with the real-time trajectory analysis and preference learning module to control the redesign of the route until the wheelchair journey is completed.

[0010] The user interface module is the way for users to interact with the system. It typically includes voice recognition, buttons, and mobile applications. Users can use the user interface module to control the movement of the wheelchair in real time, view the walking trajectory, and promptly provide feedback and save data from the historical trajectory analysis and preference learning module, user feedback, and system optimization module.

[0011] Furthermore, the visual sensor component module includes a high-resolution camera, a LiDAR, and a depth sensor;

[0012] The camera is used to capture the user's visual information, including facial expressions, gestures, and head posture, so that the system can better understand the user's needs.

[0013] The lidar measures the distance and shape of the surrounding environment by reflecting a laser beam in order to create a map and detect obstacles.

[0014] The depth sensor is used to obtain the distance and relative position between the user and the wheelchair to ensure safe entry and exit from the vehicle.

[0015] Furthermore, the control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The data processing and analysis of the data processing and fusion unit are as follows:

[0016] The data processing and fusion unit includes user location coordinate data processing and user sitting posture angle data processing: the user location coordinate data refers to the environmental images of the user and wheelchair captured by the depth camera or LiDAR, and the user coordinates are recorded as follows: This represents the user's coordinates on the ground; attitude angle data can be obtained from sensor data and is denoted as... The coordinate system of the wheelchair is The relative position of the user and the wheelchair can be calculated through rotation and translation, using the rotation matrix. Used to represent changes in attitude angle: if If the coordinates are the user's coordinates relative to the wheelchair, then... .

[0017] Furthermore, the data processing and fusion unit also includes a Kalman filter algorithm. Based on dynamic environment and changing posture and user position coordinate data, as well as user sitting angle data, the data processing and fusion unit uses the Kalman filter algorithm to continuously update and optimize the user's position and posture. The Kalman filter formula is as follows: in The estimated state at the current moment. This represents the observed sensor data. This represents the observation matrix; This indicates the Kalman gain;

[0018] This algorithm can dynamically adjust the user's location estimate based on sensor data and system model, thereby improving positioning accuracy.

[0019] Furthermore, the path planning and navigation unit calculates the optimal path based on the data information sent by the control and execution module and the historical trajectory information from the historical trajectory analysis and preference learning module, according to the user's current location and target location. During the planning process, the system continuously optimizes the path, avoiding obstacles and congested areas in real time. The path planning and navigation unit includes environmental modeling and obstacle detection, path planning algorithms, and path optimization. The environmental modeling and obstacle detection uses LiDAR, ultrasonic sensors, or cameras. The system can detect surrounding obstacles and record the obstacle set as follows: Each obstacle Each has its place The path planning algorithm is based on obstacle data and data information from the data processing and fusion unit, and employs... The algorithm, the The algorithm finds the starting point through heuristic search. To the target point The shortest path, The cost function of the algorithm is: in This represents the actual cost from the starting point to the current node n. This is a heuristic estimate of the cost from the current node n to the target point, typically using Euclidean distance: The path optimization involves dynamically adjusting the path when obstacles or user posture change. The dynamic programming or online optimization algorithm is used to perform this path adjustment as follows: in They are adjacent nodes on the path. It is the Euclidean distance between two points.

[0020] Furthermore, the motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The PID controller, based on data controlled by the control and execution module, determines the current position of the wheelchair. The target location is The error is: Output control signal of PID controller for: in It is a proportionality coefficient used to adjust for errors. These are integral coefficients used to eliminate long-term errors. , is the differential coefficient, used to predict changes in error;

[0021] The system uses a PID controller to dynamically adjust the speed and direction of the wheelchair based on real-time errors, ensuring that the wheelchair moves along the planned path.

[0022] Furthermore, in the obstacle avoidance and dynamic adjustment unit, obstacles may suddenly appear during wheelchair movement. To avoid collisions, the wheelchair needs to monitor the surrounding environment and adjust its path in real time. The obstacle avoidance and dynamic adjustment unit includes a dynamic window method, which comprises a wheelchair body state space, a wheelchair body speed window, obstacle detection and evaluation, an evaluation function, and selection of the optimal speed. The dynamic window method calculates the currently available speed window of the wheelchair body in real time, then selects a suitable speed combination to avoid obstacles, and plans the optimal motion trajectory based on this. The specific analysis of the obstacle avoidance and dynamic adjustment unit is as follows:

[0023] The wheelchair body state space, the current speed of the wheelchair body is: ,in It is linear velocity. It is angular velocity;

[0024] The wheelchair body velocity window is based on data from the wheelchair body state space, according to the maximum linear velocity of the wheelchair body. and maximum angular velocity Dynamic windows define a selectable speed range, and the window boundaries are typically:

[0025] Linear velocity: Angular velocity: The obstacle detection and assessment uses sensors to detect the distance to surrounding obstacles in real time and calculates the collision risk for each speed combination based on the position of the obstacles.

[0026] The evaluation function is for each candidate velocity combination Calculate the following function To measure its quality: in Evaluating whether the current combination of speeds is helpful in moving toward the target point is usually a function related to the distance or direction to the target point; Whether a speed combination avoids obstacles is typically calculated based on the shortest distance to the obstacle. Considering the dynamic constraints of the wheelchair itself, ensure that the speed combination does not exceed the dynamic limits of the wheelchair itself. These are weighting coefficients used to balance the various evaluation factors;

[0027] The selection of the optimal speed is based on all candidate speed combinations. Select evaluation value The maximum speed is used as the final selected speed and as the control input for the wheelchair.

[0028] Furthermore, based on the final data from the motion control and wheelchair navigation module, the PID controller transmits the path data to the historical trajectory analysis and preference learning module. The system periodically collects the user's historical travel trajectory data and uses machine learning algorithms to identify the user's travel patterns. The system can predict the user's future travel needs and recommend routes that are more in line with their habits.

[0029] The user interface module, which serves as the means for users to interact with the system, typically includes voice recognition, buttons, and mobile applications. Users can interact with the wheelchair in the following ways: Buttons and touchscreen: Buttons or touchscreens on the wheelchair allow users to send summoning signals, initiate navigation, and provide feedback; Voice commands: Users can use voice commands to inform the wheelchair of their needs, such as "forward" or "stop"; Mobile application: The wheelchair can connect to the user's smartphone application, allowing the user to monitor the wheelchair's location and status in real time and send commands.

[0030] Furthermore, according to claim 9, the method based on an intelligent wheelchair automatic navigation system is characterized by employing an intelligent wheelchair automatic navigation system as described in any one of claims 1-9, and the steps are as follows:

[0031] Step 1: First, after the system starts up, the vision sensor module begins to work, monitoring the user's posture and position information. The camera captures the user's body posture and relative position information with the wheelchair. At the same time, the lidar and depth sensor detect the distance and relative position between the user and the wheelchair. This data is transmitted to the control and execution module for analysis and processing.

[0032] Step 2: Users can send a summoning signal via voice command or mobile application, which informs the system of the user's needs, such as getting on or off the vehicle, or moving to a certain location;

[0033] Step 3: After receiving the user's signals and sensor data, the motion control and wheelchair navigation module will formulate the best navigation route based on the user's needs and environmental conditions. Taking into account obstacles in the environment, the navigation algorithm will determine a safe path to ensure that the wheelchair can reach the target location smoothly.

[0034] Step 4: Once the navigation route is determined, the wheelchair will start its motor according to the instructions of the motion control and wheelchair navigation module to begin autonomous navigation. The wheelchair will avoid obstacles and adjust its speed and direction according to the environmental map to ensure safe navigation.

[0035] Step 5: When the wheelchair reaches the target location, the user can easily get on and off the vehicle. The system can automatically stop according to the user's instructions or gestures, and assist the user in getting on and off the vehicle as needed.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] 1. In the intelligent wheelchair automatic navigation system and method of the present invention, the path planning method based on the A* algorithm is adopted by the present invention, which can accurately calculate the shortest path from the starting position to the target position, avoiding the problems of long paths or inability to avoid obstacles that may occur in traditional navigation systems. By combining real-time environmental perception data, the wheelchair can automatically select the best path in complex indoor environments, ensuring that it reaches the destination quickly and safely.

[0038] 2. In the intelligent wheelchair automatic navigation system and method of the present invention, the present invention uses lidar and depth sensors to scan the surrounding environment in real time, which can accurately detect obstacles in front of and around the wheelchair and take timely avoidance measures. Compared with the traditional static obstacle detection method, the system can adjust the path in real time according to environmental changes, thereby avoiding collisions and falls, and improving the safety and reliability of the wheelchair.

[0039] 3. In the intelligent wheelchair automatic navigation system and method of the present invention, the PID controller can adjust the speed and steering angle of the wheelchair in real time according to the error between the wheelchair and the target position, so as to ensure that the wheelchair drives smoothly and accurately in complex environments. This not only improves the user's comfort, but also maintains good driving performance under different ground conditions, avoiding the instability problems that may occur when traditional wheelchairs turn or accelerate.

[0040] 4. In the intelligent wheelchair automatic navigation system and method of the present invention, not only can automatic navigation be realized, but also the user can be assisted in getting on and off the vehicle. Through the coordinated work of depth perception and vision sensors, the system can determine whether the user has safely completed the operation of getting on and off the vehicle, and adjust the position of the wheelchair as needed, thereby avoiding falls or injuries caused by improper operation. This intelligent assistance function greatly improves the quality of life and autonomy of the elderly, disabled people and people with mobility difficulties.

[0041] 5. In the intelligent wheelchair automatic navigation system and method of the present invention, the system can adjust the navigation strategy in real time according to changes in the environment and user needs. For example, when encountering sudden obstacles or narrow passages, the system can replan the path and quickly avoid obstacles to ensure the safety of the user. This high level of intelligent processing capability enables the wheelchair to exhibit good adaptability and autonomy in dynamic environments, avoiding the limitations of traditional manually controlled wheelchairs in complex environments.

[0042] 6. In the intelligent wheelchair automatic navigation system and method of the present invention, a modular design is adopted to integrate multiple sensors (such as lidar and depth camera), making the hardware structure of the system simpler and more compact, and easier to maintain and upgrade. The user operation is simple. The automatic navigation system can be started by simple voice commands or manual input of target location, avoiding cumbersome operation steps and making it easier for users to use the intelligent wheelchair. Attached Figure Description

[0043] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0044] Figure 1 This is a schematic diagram of the overall steps of an intelligent wheelchair automatic navigation system and method according to the present invention;

[0045] Figure 2 This is a schematic diagram of the overall structure of an intelligent wheelchair automatic navigation system and method according to the present invention;

[0046] Figure 3 The present invention provides a control and execution module for an intelligent wheelchair automatic navigation system and method, comprising the following figures;

[0047] Figure 4 The present invention provides an intelligent wheelchair automatic navigation system and method, comprising a motion control and wheelchair navigation module. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] like Figures 1-4 As shown, an intelligent wheelchair automatic navigation system and method includes a visual sensor component module, a control and execution module, a motion control and wheelchair navigation module, a user feedback and system optimization module, a trajectory analysis and preference learning module, and a user interface module.

[0050] The visual sensor component module includes a high-resolution camera, LiDAR, and depth sensor. These sensors are responsible for monitoring the environment around the wheelchair in real time, capturing the user's posture information and position data, and transmitting the captured data to the control execution module.

[0051] The system scans the surrounding environment in real time using lidar, depth sensors, and vision sensors, collecting information on the location, size, and dynamic changes of surrounding obstacles. Through data fusion from the sensors, the system can build an accurate environmental model and update it in real time.

[0052] The control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The control and execution module receives sensor data from the vision sensor component module and processes the information through the data processing and fusion unit. The processed information is then transmitted to the path planning and navigation unit. Based on user needs, environmental information, historical trajectory analysis and preferences, the path planning and navigation unit determines the optimal path for the wheelchair and transmits the path information to the motion control and wheelchair navigation module.

[0053] Path planning: Based on the target location input by the user and environmental perception data, the system calculates the shortest and safest driving path. If a sudden obstacle is encountered, the system will adjust the path in real time to avoid the obstacle and keep the target location unchanged.

[0054] The motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The wheelchair body is the physical part of the smart wheelchair, consisting of an electric wheelchair chassis, a seat, and a battery. These components work together and, based on the path planning data from the path planning and navigation unit in the control and execution module, enable the wheelchair to move along the path of the control and execution module according to the instructions of the PID controller. During the movement, the wheelchair body dynamically adjusts the path through the obstacle avoidance and dynamic adjustment unit, and this data information is transmitted to the user feedback and system optimization module in real time.

[0055] Based on the path planning results, the system adjusts the speed and direction of the electric drive system using a PID control algorithm to precisely control the wheelchair's movement. The PID controller dynamically adjusts the direction and speed based on the error between the wheelchair and the target position, as well as actual deviations during movement, ensuring the wheelchair can navigate smoothly and accurately.

[0056] When an obstacle is detected in front of or to the side of the wheelchair, the lidar and depth sensor will report the location of the obstacle. The system will then determine the size and type of the obstacle. If it is a static obstacle, the system will calculate a detour path. If it is a dynamic obstacle (such as a pedestrian or other object), the system will adjust its speed and direction in real time to avoid a collision.

[0057] The user feedback and system optimization module collects real-time user feedback through voice recognition, touchscreen, and buttons, and uploads this feedback information to the motion control and wheelchair navigation module in real time. The motion control and wheelchair navigation module processes the received information and combines it with the real-time trajectory analysis and preference learning module to control the replanning and design of the route until the wheelchair journey is completed.

[0058] Based on the final data from the motion control and wheelchair navigation modules, the PID controller transmits the path data to the historical trajectory analysis and preference learning module. The system regularly collects the user's historical travel trajectory data and uses machine learning algorithms to identify the user's travel patterns. The system can predict the user's future travel needs and recommend routes that are more in line with their habits.

[0059] The user interface module is the way for users to interact with the system. It usually includes voice recognition, buttons, and mobile applications. Users can use the user interface module to control the movement status of the wheelchair in real time, view the walking trajectory, and promptly provide feedback and save data information from the historical trajectory analysis and preference learning module, user feedback and system optimization module.

[0060] Specifically, the visual sensor component module includes a high-resolution camera, LiDAR, and a depth sensor;

[0061] Camera: Used to capture the user's visual information, including facial expressions, gestures, and head posture, so that the system can better understand the user's needs;

[0062] LiDAR: It measures the distance and shape of the surrounding environment by reflecting laser beams in order to create a map and detect obstacles;

[0063] Depth sensor: Used to obtain the distance and relative position between the user and the wheelchair to ensure safe entry and exit;

[0064] The wheelchair scans for obstacles ahead using LiDAR and acquires ground information using a depth sensor. When the user inputs the destination, the system plans the shortest path using the A* algorithm and controls the wheelchair to travel along the path using a PID controller. When it encounters obstacles (such as furniture), the system adjusts the path in real time to bypass the obstacles and continue to the target location.

[0065] Specifically, the control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The data processing and analysis of the data processing and fusion unit are as follows:

[0066] The data processing and fusion unit includes user location coordinate data processing and user sitting posture angle data processing: the user location coordinate data refers to the environmental images of the user and wheelchair captured by the depth camera or LiDAR, and the user coordinates are recorded as follows: This represents the user's coordinates on the ground; attitude angle data can be obtained from sensor data and is denoted as... The coordinate system of the wheelchair is The relative position of the user and the wheelchair can be calculated through rotation and translation, using the rotation matrix. Used to represent changes in attitude angle: if If the coordinates are the user's coordinates relative to the wheelchair, then... .

[0067] Specifically, the data processing and fusion unit also includes a Kalman filter algorithm. Based on dynamic environment and changing posture and user position coordinate data, as well as user sitting angle data, the data processing and fusion unit uses the Kalman filter algorithm to continuously update and optimize the user's position and posture. The Kalman filter formula is as follows: in The estimated state at the current moment. This represents the observed sensor data. This represents the observation matrix; This indicates the Kalman gain;

[0068] This algorithm can dynamically adjust the user's location estimate based on sensor data and system model, thereby improving positioning accuracy.

[0069] Specifically, the path planning and navigation unit calculates the optimal path based on the data sent by the control and execution module and the historical trajectory information from the historical trajectory analysis and preference learning module, taking into account the user's current location and target location. During the planning process, the system continuously optimizes the path, avoiding obstacles and congested areas in real time. The path planning and navigation unit includes environmental modeling and obstacle detection, path planning algorithms, and path optimization. Environmental modeling and obstacle detection utilizes LiDAR, ultrasonic sensors, or cameras to detect surrounding obstacles and record the obstacle set as follows: Each obstacle Each has its place The path planning algorithm is based on obstacle data and data information from the data processing and fusion unit, and employs... The algorithm, the The algorithm finds the starting point through heuristic search. To the target point The shortest path, The cost function of the algorithm is: in This represents the actual cost from the starting point to the current node n. This is a heuristic estimate of the cost from the current node n to the target point, typically using Euclidean distance: The path optimization involves dynamically adjusting the path when obstacles or user posture change. The dynamic programming or online optimization algorithm is used to perform this path adjustment as follows: in They are adjacent nodes on the path. It is the Euclidean distance between two points.

[0070] Specifically, the motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The PID controller, based on data controlled by the control and execution module, determines the wheelchair's current position. The target location is The error is: Output control signal of PID controller for: in It is a proportionality coefficient used to adjust for errors. These are integral coefficients used to eliminate long-term errors. , is the differential coefficient, used to predict changes in error;

[0071] The system uses a PID controller to dynamically adjust the speed and direction of the wheelchair based on real-time errors, ensuring that the wheelchair moves along the planned path.

[0072] Specifically, the obstacle avoidance and dynamic adjustment unit addresses the issue that obstacles may suddenly appear during wheelchair operation. To avoid collisions, the wheelchair needs to monitor its surroundings and adjust its path in real time. This unit utilizes a dynamic window method, which includes the wheelchair's state space, speed window, obstacle detection and evaluation, evaluation function, and selection of the optimal speed. The dynamic window method calculates the wheelchair's currently available speed window in real time, selects a suitable speed combination to avoid obstacles, and plans the optimal motion trajectory based on this. The specific analysis of the obstacle avoidance and dynamic adjustment unit is as follows:

[0073] The wheelchair body state space, the current speed of the wheelchair body is: ,in It is linear velocity. It is angular velocity;

[0074] The wheelchair body velocity window is based on data from the wheelchair body state space, according to the maximum linear velocity of the wheelchair body. and maximum angular velocity Dynamic windows define a selectable speed range, and the window boundaries are typically:

[0075] Linear velocity: Angular velocity: The obstacle detection and assessment uses sensors (such as lidar and ultrasonic sensors) to detect the distance to surrounding obstacles in real time, and calculates the collision risk for each speed combination based on the position of the obstacles.

[0076] The evaluation function is for each candidate velocity combination. Calculate the following function To measure its quality: in Evaluating whether the current combination of speeds is helpful in moving toward the target point is usually a function related to the distance or direction to the target point; Whether a speed combination avoids obstacles is typically calculated based on the shortest distance to the obstacle. Considering the dynamic constraints of the wheelchair itself, ensure that the speed combination does not exceed the dynamic limits of the wheelchair itself. These are weighting coefficients used to balance the various evaluation factors;

[0077] The selection of the optimal speed is based on all candidate speed combinations. Select evaluation value The maximum speed is used as the final selected speed and as the control input for the wheelchair.

[0078] Specifically, the trajectory analysis and preference learning module uses the final data from the motion control and wheelchair navigation module to transmit the path data to the historical trajectory analysis and preference learning module. The system will periodically collect the user's historical travel trajectory data and use machine learning algorithms to identify the user's travel patterns. The system can predict the user's future travel needs and recommend routes that are more in line with their habits.

[0079] The user interface module is the way users interact with the system. It typically includes voice recognition, buttons, and mobile applications. Users can interact with the wheelchair in the following ways: Buttons and touchscreens: Buttons or touchscreens on the wheelchair allow users to send call signals, start navigation, and provide feedback; Voice commands: Users can use voice commands to tell the wheelchair their needs, such as "forward" or "stop"; Mobile applications: The wheelchair can connect to the user's smartphone application, allowing the user to monitor the wheelchair's position and status in real time and send commands.

[0080] Specifically, according to claim 9, the method based on an intelligent wheelchair automatic navigation system is characterized by employing an intelligent wheelchair automatic navigation system according to any one of claims 1-9, and the steps are as follows:

[0081] Step 1: First, after the system starts up, the vision sensor module begins to work, monitoring the user's posture and position information. The camera captures the user's body posture and relative position information with the wheelchair. At the same time, the lidar and depth sensor detect the distance and relative position between the user and the wheelchair. This data is transmitted to the control and execution module for analysis and processing.

[0082] Step 2: Users can send a summoning signal via voice command or mobile application, which informs the system of the user's needs, such as getting on or off the vehicle, or moving to a certain location;

[0083] Step 3: After receiving the user's signals and sensor data, the motion control and wheelchair navigation module will formulate the best navigation route based on the user's needs and environmental conditions. Taking into account obstacles in the environment, the navigation algorithm will determine a safe path to ensure that the wheelchair can reach the target location smoothly.

[0084] Step 4: Once the navigation route is determined, the wheelchair will start its motor according to the instructions of the motion control and wheelchair navigation module to begin autonomous navigation. The wheelchair will avoid obstacles and adjust its speed and direction according to the environmental map to ensure safe navigation.

[0085] Step 5: When the wheelchair reaches the target location, the user can easily get on and off. The system can automatically stop based on the user's instructions or gestures, and assist the user with getting on and off as needed.

[0086] Working Principle: First, after the system starts, the vision sensor module begins to work, monitoring the user's posture and position information. The camera captures the user's body posture and relative position with the wheelchair. At the same time, the lidar and depth sensor detect the distance and relative position between the user and the wheelchair. This data is transmitted to the control and execution module for analysis and processing. The user can send a call signal via voice command or mobile application, informing the system of their needs, such as getting on or off the wheelchair or moving to a certain location. After receiving the user's signal and sensor data, the motion control and wheelchair navigation module will formulate the optimal navigation route based on the user's needs and environmental conditions. Taking into account obstacles in the environment, the navigation algorithm will determine a safe path to ensure that the wheelchair can reach the target location smoothly. Once the navigation route is determined, the wheelchair will start its motor according to the instructions of the motion control and wheelchair navigation module and begin autonomous navigation. The wheelchair will avoid obstacles according to the environmental map and adjust its speed and direction to ensure safe navigation. When the wheelchair reaches the target location, the user can easily get on or off the wheelchair. The system can automatically stop according to the user's instructions or gestures and assist the user with getting on and off the wheelchair as needed.

[0087] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and effects.

Claims

1. An intelligent wheelchair automatic navigation system, characterized in that, It includes a vision sensor component module, a control and execution module, a motion control and wheelchair navigation module, a user feedback and system optimization module, a trajectory analysis and preference learning module, and a user interface module; The visual sensor component module includes a high-resolution camera, LiDAR, and depth sensor. These sensors are responsible for monitoring the environment around the wheelchair in real time, capturing the user's posture information and position data, and transmitting the captured data to the control execution module. The control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The control and execution module receives sensor data information from the vision sensor component module and processes the information through the data processing and fusion unit. The processed information is then transmitted to the path planning and navigation unit. Based on user needs, environmental information, and historical trajectory analysis and preferences, the path planning and navigation unit determines the optimal path for the wheelchair and transmits the path information to the motion control and wheelchair navigation module. The motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The wheelchair body is the physical part of the smart wheelchair, consisting of an electric wheelchair chassis, a seat, and a battery. These components work together and, based on the path planning data of the path planning and navigation unit in the control and execution module, enable the wheelchair to move along the path of the control and execution module according to the instructions of the PID controller. During the movement, the wheelchair body dynamically adjusts the path through the obstacle avoidance and dynamic adjustment unit, and this data information is transmitted to the user feedback and system optimization module in real time. The user feedback and system optimization module collects real-time user feedback through voice recognition, touch screen, and buttons, and uploads the feedback information to the motion control and wheelchair navigation module in real time. The motion control and wheelchair navigation module processes the received information and combines it with the real-time trajectory analysis and preference learning module to control the replanning and design of the route until the wheelchair journey is completed. Based on the final data from the motion control and wheelchair navigation modules, the PID controller transmits the path data to the historical trajectory analysis and preference learning module. The system regularly collects the user's historical travel trajectory data and uses machine learning algorithms to identify the user's travel patterns. The system can predict the user's future travel needs and recommend routes that are more in line with their habits. The user interface module is the way for users to interact with the system. It typically includes voice recognition, buttons, and mobile applications. Users can use the user interface module to control the movement of the wheelchair in real time, view the walking trajectory, and promptly provide feedback and save data from the historical trajectory analysis and preference learning module, user feedback, and system optimization module.

2. The intelligent wheelchair automatic navigation system according to claim 1, characterized in that, The visual sensor component module includes a high-resolution camera, a lidar, and a depth sensor; The camera is used to capture the user's visual information, including facial expressions, gestures, and head posture, so that the system can better understand the user's needs. The lidar measures the distance and shape of the surrounding environment by reflecting a laser beam in order to create a map and detect obstacles. The depth sensor is used to obtain the distance and relative position between the user and the wheelchair to ensure safe entry and exit.

3. The intelligent wheelchair automatic navigation system according to claim 2, characterized in that, The control and execution module includes a data processing and fusion unit and a path planning and navigation unit. The data processing and analysis of the data processing and fusion unit are as follows: The data processing and fusion unit includes user location coordinate data processing and user sitting posture angle data processing: the user location coordinate data refers to the environmental images of the user and wheelchair captured by the depth camera or LiDAR, and the user coordinates are recorded as follows: This represents the user's coordinates on the ground; attitude angle data can be obtained from sensor data and is denoted as... The coordinate system of the wheelchair is The relative position of the user and the wheelchair can be calculated through rotation and translation, using the rotation matrix. Used to represent changes in attitude angle: if If the coordinates are the user's coordinates relative to the wheelchair, then... .

4. The intelligent wheelchair automatic navigation system according to claim 3, characterized in that, The data processing and fusion unit also includes a Kalman filter algorithm. Based on dynamic environment and changing posture and user position coordinate data, as well as user sitting posture angle data, the data processing and fusion unit uses the Kalman filter algorithm to continuously update and optimize the user's position and posture. The Kalman filter algorithm is as follows: in The estimated state at the current moment. This represents the observed sensor data. This represents the observation matrix; This indicates the Kalman gain.

5. The intelligent wheelchair automatic navigation system according to claim 2, characterized in that, The path planning and navigation unit calculates the optimal path based on data sent by the control and execution module, historical trajectory information from the historical trajectory analysis and preference learning module, and the user's current and target locations. During the planning process, the system continuously optimizes the path, avoiding obstacles and congested areas in real time. The path planning and navigation unit includes environmental modeling and obstacle detection, path planning algorithms, and path optimization. Environmental modeling and obstacle detection utilizes LiDAR, ultrasonic sensors, or cameras; the system can detect surrounding obstacles and record the obstacle set as follows: Each obstacle Each has its place The path planning algorithm is based on obstacle data and data information from the data processing and fusion unit, and employs... The algorithm, the The algorithm finds the starting point through heuristic search. To the target point The shortest path, The cost function of the algorithm is: in This represents the actual cost from the starting point to the current node n. This is a heuristic estimate of the cost from the current node n to the target point, typically using Euclidean distance: The path optimization involves dynamically adjusting the path when obstacles or user posture change. Dynamic programming or online optimization algorithms are used for path adjustment as follows: in They are adjacent nodes on the path. It is the Euclidean distance between two points.

6. The intelligent wheelchair automatic navigation system according to claim 1, characterized in that, The motion control and wheelchair navigation module includes a PID controller, a wheelchair body, and an obstacle avoidance and dynamic adjustment unit. The PID controller, based on data controlled by the control and execution module, determines the wheelchair's current position. The target location is The error is: Output control signal of PID controller for: in It is a proportionality coefficient, used to adjust for errors. These are integral coefficients used to eliminate long-term errors. , is the differential coefficient, used to predict changes in error.

7. The intelligent wheelchair automatic navigation system according to claim 6, characterized in that, The obstacle avoidance and dynamic adjustment unit addresses the issue that obstacles may suddenly appear during wheelchair movement. To avoid collisions, the wheelchair needs to monitor its surroundings and adjust its path in real time. This unit employs a dynamic window method, which includes a wheelchair state space, a wheelchair speed window, obstacle detection and evaluation, an evaluation function, and the selection of the optimal speed. The dynamic window method calculates the wheelchair's currently available speed window in real time, selects a suitable speed combination to avoid obstacles, and plans the optimal motion trajectory based on this. The obstacle avoidance and dynamic adjustment unit analysis is as follows: The wheelchair's current speed is in the state space of the wheelchair itself. ,in It is linear velocity. It is angular velocity; The wheelchair body velocity window is based on data from the wheelchair body state space, according to the maximum linear velocity of the wheelchair body. and maximum angular velocity Dynamic windows define a selectable speed range, and the window boundaries are typically: Linear velocity: Angular velocity: The obstacle detection and assessment method utilizes sensors to detect the distance to surrounding obstacles in real time and calculates the collision risk for each speed combination based on the position of the obstacles. The evaluation function evaluates each candidate velocity combination. Calculate the following function To measure its quality: in Evaluating whether the current combination of speeds is helpful in moving toward the target point is usually a function related to the distance or direction to the target point; Whether a speed combination avoids obstacles is typically assessed based on the shortest distance to the obstacle. Considering the dynamic constraints of the wheelchair itself, ensure that the speed combination does not exceed the dynamic limits of the wheelchair itself. These are weighting coefficients used to balance the various evaluation factors; The selection of the optimal speed is based on all candidate speed combinations. Select evaluation value The maximum speed is used as the final selected speed and as the control input for the wheelchair.

8. The intelligent wheelchair automatic navigation system according to claim 7, characterized in that, The user interface module is the way for users to interact with the system. It typically includes voice recognition, buttons, and mobile applications. Users can interact with the wheelchair in the following ways: Buttons and touchscreens: Buttons or touchscreens on the wheelchair allow users to send summoning signals, start navigation, and provide feedback; Voice commands: Users can use voice commands to inform the wheelchair of their needs; Mobile applications: The wheelchair can connect to the user's smartphone application, allowing the user to monitor the wheelchair's location and status in real time and send commands.

9. An intelligent wheelchair automatic navigation method, based on the intelligent wheelchair automatic navigation system according to any one of claims 1 to 8, characterized in that: include, It monitors the environment around the wheelchair in real time, captures the user's posture information and position data, and transmits the captured data to the control execution module; The system receives sensor data from the vision sensor module and processes the information through the data processing and fusion unit. The processed information is then transmitted to the path planning and navigation unit. Based on user needs, environmental information, historical trajectory analysis, and preferences, the path planning and navigation unit determines the optimal path for the wheelchair and transmits this path information to the motion control and wheelchair navigation module. Based on the path planning data of the path planning and navigation unit in the control and execution module, the wheelchair can be controlled to move along the path of the control and execution module according to the instructions of the PID controller. During the movement, the wheelchair dynamically adjusts the path through the obstacle avoidance and dynamic adjustment unit, and the data information is transmitted to the user feedback and system optimization module in real time. The system collects real-time user feedback through voice recognition, touchscreen, and buttons, and uploads this feedback information to the motion control and wheelchair navigation module in real time. The motion control and wheelchair navigation module processes the received information and combines it with the real-time trajectory analysis and preference learning module to control the replanning and design of the route until the wheelchair journey is completed. The user interface module allows for real-time control of the wheelchair's movement and viewing of its trajectory, as well as timely feedback and saving of data from the historical trajectory analysis and preference learning modules, user feedback, and system optimization modules.

Images