Self-adaptive control system and method applied to walking assisting robot

Abstract

The invention belongs to the field of medical rehabilitation equipment and robot control, and particularly relates to a self-adaptive control system and method applied to a walking assisting robot, and the system comprises a sensor information collection module which is used for collecting sensor information at each position of the walking assisting robot in real time, the intention identification and environment identification module and the self-adaptive control module are used for identifying the environment; the intention recognition and environment recognition module is used for recognizing and analyzing a user walking intention including the walking direction and speed, selecting different walking modes according to feedback signals and sending the different walking modes to the self-adaptive control module; meanwhile, ground gradient changes when the user assists in walking are recognized, different assistance or resistance modes are selected according to feedback signals, and the modes are sent to the self-adaptive control module; and the adaptive control module dynamically adjusts the magnitude and the direction of the speed command of the motion control module, and dynamically adjusts according to modes for providing different assistance or resistance.

Description

Technical Field

[0001] The invention belongs to the field of medical rehabilitation equipment and robot control, and in particular to an adaptive control system and method applied to a walking assist robot. Background Art

[0002] As a rehabilitation aid, walking assistance robots have been developing continuously in recent years and have become one of the key research areas of robots. Walking assistance robots can solve the difficulty of walking for the elderly, weak and sick groups and reduce the burden of walking.

[0003] Existing walking assistance robot products have relatively simple functions, cannot effectively identify the user's movement intention, are not easy to use in different terrains and scenarios, and lack effective protection in active safety. If we want walking assistance robots to better help users walk easily and freely, we must consider the user's experience and ensure the user's walking safety. A complete and reliable adaptive control method is the key to ensuring the safety, practicality and stability of walking assistance robots. Summary of the invention

[0004] The purpose of the present invention is to provide an adaptive control method for a walking assistance robot. This method can improve the usability, reliability, completeness and safety of the walking assistance robot, better ensure that the user can walk easily and freely, effectively reduce the user's walking fatigue, improve the user's walking safety, and improve and optimize the user's experience.

[0005] The technical solution adopted by the present invention to achieve the above-mentioned purpose is: an adaptive control system applied to a walking assistance robot, comprising: a sensor information acquisition module, an intention recognition and environment recognition module, an adaptive control module and a motion control module;

[0006] The sensor information acquisition module is used to collect sensor information located at various positions of the walking assistance robot in real time and send it to the intention recognition and environment recognition module and the adaptive control module;

[0007] The intention recognition and environment recognition module is used to recognize and analyze the user's walking intention including the walking direction and speed according to the sensor information received at various positions of the walking assistance robot, select different walking modes according to the feedback signal, and send it to the adaptive control module; at the same time, it also recognizes the change of ground slope during user assisted walking, selects different modes of providing assistance or resistance according to the feedback signal, and sends it to the adaptive control module;

[0008] The adaptive control module is used to dynamically adjust the speed instruction size and direction of the motion control module according to the user's walking intention including the walking direction and speed, and dynamically adjust according to the mode of providing different assistance or resistance, and transmit it to the motion control module; at the same time, it also provides safety protection for the user according to the sensor data collected by the sensor information collection module, and transmits it to the motion control module;

[0009] The motion control module is used to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking.

[0010] The sensor information acquisition module includes: a capacitive contact sensor, a gyroscope sensor, a motor parameter acquisition unit, a force sensor and an obstacle avoidance sensor;

[0011] The capacitive contact sensor is arranged on the device handle of the walking assistance robot, and is used to collect the capacitive contact sensor information for grip detection, and send it to the intention recognition and environment recognition module and the adaptive control module respectively;

[0012] The gyroscope sensor is installed in the controller of the walking assistance robot, and is used to collect the angular velocity or angular displacement of the walking assistance robot in space, so as to obtain the posture of the walking assistance robot in real time and send it to the intention recognition and environment recognition module;

[0013] The motor parameter acquisition unit is used to collect the motor current and speed information fed back by the motor, and send them to the intention recognition and environment recognition module and the adaptive control module respectively;

[0014] The force sensor is arranged on the device handle of the walking assistance robot, and is used to collect the force generated when the user uses the left and right handles of the device handle, and send the magnitude of the force to the intention recognition and environment recognition module and the adaptive control module;

[0015] The obstacle avoidance sensor is a sonar sensor or a laser sensor, which is installed at the front end of the walking assistance robot in the forward direction. It is used to collect sonar data and laser data, and then obtain the distance of obstacles in front of the walking assistance robot, and send them to the intention recognition and environment recognition module and the adaptive control module respectively.

[0016] The intention recognition and environment recognition module includes: an intention recognition and behavior analysis unit and an environment recognition unit respectively connected to the adaptive control module;

[0017] The intention recognition and behavior analysis unit is connected to the capacitive contact sensor and the force sensor respectively, and is used to receive the magnitude of the force generated when the user uses the left and right handles, judge the user's walking intention intensity, quantify the intention intensity, and send the predicted user walking speed and direction to the adaptive control module;

[0018] The environment recognition unit is connected to the gyro sensor and is used to obtain the change of ground slope when the user walks according to the sent walking assistance robot posture, select different assistance or resistance size modes according to the change of ground slope, and send it to the adaptive control module.

[0019] The adaptive control module includes: a speed adaptive control unit, a human-machine interaction force control unit and a user protection unit;

[0020] The speed adaptive control unit is connected to the intention recognition and behavior analysis unit and the motor parameter acquisition unit respectively, and is used to dynamically adjust the motor current and speed information according to different power assistance or resistance size modes and motor current and speed information sent by the intention recognition and behavior analysis unit;

[0021] The human-machine interaction force control unit is connected to the environment recognition unit and the motor parameter acquisition unit respectively, and is used to control the travel speed of the walking assistance robot according to the interaction force between the human and the walking assistance robot as the control object, so as to assist the user in walking;

[0022] The user protection unit is connected to the capacitive contact sensor, the force sensor and the obstacle avoidance sensor respectively, and is used to judge whether the user has disengaged the handles based on the information from the capacitive contact sensor, and to start and stop the walking assistance robot; at the same time, based on the changes in the force generated when the user uses the left and right handles, it is judged whether the user is in danger of falling, and the walking assistance robot is controlled to start the anti-reversing function; it also detects obstacles in front of the walking assistance robot, and slows down or stops when the obstacle reaches a set distance while the user is walking, to prevent the user from being tripped or hit by the obstacle.

[0023] A control method for an adaptive control system applied to a walking assistance robot comprises the following steps:

[0024] 1) The sensor information collected by the sensor information acquisition module is directly transmitted to the adaptive control module on the one hand, and to the intention recognition and environment recognition module on the other hand;

[0025] 2) The intention recognition and environment recognition module recognizes and analyzes the intensity of a person's walking intention, including the direction and speed of walking, through the capacitive contact sensor information and the force sensor information, and sends it to the adaptive control module;

[0026] 3) At the same time, the intention recognition and environment recognition module recognizes the change in ground slope when the user is walking with assistance, and selects different assistance or resistance modes according to the feedback signal, and sends it to the adaptive control module;

[0027] 4) The adaptive control module dynamically adjusts the speed command size and direction, and the resistance / assistance size of the motion control according to the user's walking intention including the walking direction and speed, and transmits them to the motion control module to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking. At the same time, the adaptive control module provides safety protection for the user based on the sensor data collected by the sensor information acquisition module.

[0028] The step 2) is specifically:

[0029] 2-1) The intention recognition and behavior analysis unit obtains the data information of the capacitive contact sensors and force sensors on the left and right handles of the walking assistance robot, identifies the user's walking intention including the walking direction and speed, and quantifies the intensity of the user's walking intention according to the size of the force sensor data to obtain the user's target walking speed, that is:

[0030] v i =f v (F r ,F l )

[0031] Among them, v i is the user's target walking speed; F r F is the actual force applied by the user to the right handle of the walking assistance robot; l The actual force applied by the user to the left handle of the walking assistance robot;

[0032] 2-2) Select different walking modes according to the feedback signal: turning movement, forward / backward movement, stationary and starting;

[0033] 2-3) The user's target walking direction is obtained based on the difference in the force between the left and right hands;

[0034] 2-4) When the force of one side handle is reduced or there is a pulling force on one side handle, and the force of the other side handle is increased, the speed of the two wheels of the car is controlled according to the user's target walking direction, and the motion differential adjusts the deflection angle of the car to reach the turning position. The direction angle is:

[0035] α i =f d (F r -F l )

[0036] Among them, α i F is the user's target rotation angle; r F is the actual force applied by the user to the right handle of the walking assistance robot; l It is the actual force applied by the user to the left handle of the walking assistance robot.

[0037] In step 3), the intention recognition and environment recognition module recognizes the change in ground slope when the user assists walking, specifically:

[0038] The environment recognition unit obtains the change of the ground slope when the user walks according to the change of the posture of the walking assistance robot obtained by the gyroscope sensor;

[0039] Among them, the walking assistance robot detects ground slope changes ranging from 5° to 15°;

[0040] When the ground slope is less than 5°, the walking assistance robot works in flat ground mode; when the ground slope is greater than 5°, the walking assistance robot works in slope mode, providing continuous assistance during the uphill process and continuous resistance during the downhill process; when the ground slope is greater than 15°, the walking assistance robot works in slope mode with a slope of 15°.

[0041] The adaptive control module dynamically adjusts the speed command size and direction of motion control, specifically:

[0042] When the user pushes the walking assistance robot to a speed greater than the set speed limit, the walking assistance robot will provide protective resistance, the resistance size of which is the set value of the current resistance gear;

[0043] When the user pushes the walking assistance robot to walk at a speed lower than the speed limit, the walking assistance robot provides continuous assistance in the direction of travel, and the magnitude of the assistance is the setting value of the current assistance gear;

[0044] The speed of the walking assistance robot is dynamically adjusted through different modes and different user travel speeds to achieve speed adaptive control.

[0045] The adaptive control module performs security protection on the user according to the sensor data collected by the sensor information collection module, specifically:

[0046] a. The user protection unit determines whether the user has disengaged the handle according to the capacitive contact sensor information, and starts and stops the walking assistance robot;

[0047] b. The user protection unit determines whether the user is in danger of falling according to the change in the force generated when the user uses the left and right handles, and controls the walking assistance robot to start the anti-reversing function;

[0048] c. The user protection unit detects obstacles in front of the walking assistance robot and slows down or stops when the obstacle reaches a set distance while the user is walking, preventing the user from being tripped or hit by the obstacle.

[0049] The present invention has the following beneficial effects and advantages:

[0050] 1. The present invention performs modular division through the adaptive control method of the walking assistance robot. The functions of each module are clearly distinguished, and the information transmission between modules is clear and intuitive, which greatly improves the overall stability and reliability of the walking assistance robot.

[0051] 2. The present invention can analyze and determine the user's walking intention, including the walking direction and speed, through intention recognition and behavior analysis, and select different walking modes according to feedback signals to improve the usability of the product.

[0052] 3. The present invention can analyze and identify the change in ground slope when the user is walking with assistance through environmental recognition, and select walking modes with different assistance or resistance according to the feedback status, thereby improving the perfection of the product.

[0053] 4. The human-machine interactive force control in the present invention takes the interaction force between the user and the walking assistance robot as the object of control, controls the walking assistance robot's travel speed and different resistance / assistance modes, and plays a function of assisting the user in walking.

[0054] 5. The present invention realizes effective protection of the walking assistance robot against dangers encountered by users through multiple protection mechanisms such as grip detection, anti-fall detection, speed limit, obstacle detection and parking protection, thereby improving the safety and reliability of the product and making users feel more assured when using it. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of the structure of the walking assistance robot system provided by the present invention;

[0056] Figure 2 A schematic diagram of the control flow of the walking assistance robot system provided by the present invention;

[0057] Figure 3 A principle block diagram of an adaptive control method applied to a walking assistance robot provided by the present invention;

[0058] Figure 4 A principle block diagram of human-machine interactive force control and speed control of an adaptive control method for a walking assist robot provided by the present invention;

[0059] In the figure: 1 is a backrest strap, 2 is a device handle, 3 is a device body, 4 is a device seat, 5 is an obstacle avoidance sensor, 6 is a controller, 7 is a device driven wheel, and 8 is a device driving wheel. DETAILED DESCRIPTION

[0060] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0061] like Figure 3As shown, it is a principle block diagram of an adaptive control method applied to a walking assistance robot of the present invention. As can be seen from the figure, an adaptive control system applied to a walking assistance robot of the present invention comprises: a sensor information acquisition module, an intention recognition and environment recognition module, an adaptive control module and a motion control module;

[0062] The sensor information acquisition module is used to collect sensor information located at various positions of the walking assistance robot in real time and send it to the intention recognition and environment recognition module and the adaptive control module;

[0063] The intention recognition and environment recognition module is used to recognize and analyze the user's walking intention including the walking direction and speed according to the sensor information received at various positions of the walking assistance robot, select different walking modes according to the feedback signal, and send it to the adaptive control module; at the same time, it also recognizes the change of ground slope during user assisted walking, selects different modes of providing assistance or resistance according to the feedback signal, and sends it to the adaptive control module;

[0064] The adaptive control module is used to dynamically adjust the speed instruction size and direction of the motion control module according to the user's walking intention including the walking direction and speed, and dynamically adjust according to the mode of providing different assistance or resistance, and transmit it to the motion control module; at the same time, it also provides safety protection for the user according to the sensor data collected by the sensor information collection module, and transmits it to the motion control module;

[0065] The motion control module is used to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking.

[0066] The system structure of the walking assist robot is as follows Figure 1 As shown, Figure 1 As shown, the walking assistance robot of the present invention is a prior art, and the walking assistance robot includes: a backrest strap 1, a device handle 2, a device body 3, a device seat 4, an obstacle avoidance sensor 5, a controller 6, a device driven wheel 7, and a device driving wheel 8. Its structural design can be in a variety of ways, and the sensor information acquisition module in the present invention can be applied to this type of robot; the walking assistance robot is a human-computer interactive walking assistance device, and the human serves as the input signal source for operating the device, and is also the control object of the walking assistance robot. The walking assistance robot system control process is as follows: Figure 2 As shown, the thrust of the person on the walking assistance robot serves as a signal input to control the movement of the walking assistance robot. On the other hand, the movement of the walking assistance robot will also exert force on the person to assist the user in walking.

[0067] exist Figure 1The sensor information acquisition module in the present invention includes: a capacitive contact sensor, a gyroscope sensor, a motor parameter acquisition unit, a force sensor and an obstacle avoidance sensor;

[0068] The capacitive contact sensor is provided on the device handle 2 of the walking assistance robot, and is used to collect capacitive contact sensor information for grip detection, and send it to the intention recognition and environment recognition module and the adaptive control module respectively;

[0069] The gyroscope sensor is arranged in the controller 6 of the walking assistance robot, and is used to collect the angular velocity or angular displacement of the walking assistance robot in space, so as to obtain the posture of the walking assistance robot in real time, and send it to the intention recognition and environment recognition module;

[0070] The motor parameter acquisition unit is used to collect the motor current and speed information fed back by the motor, and send them to the intention recognition and environment recognition module and the adaptive control module respectively;

[0071] The force sensor is provided on the device handle 2 of the walking assistance robot, and is used to collect the force generated when the user uses the left and right handles of the device handle 2, and send the magnitude of the force to the intention recognition and environment recognition module and the adaptive control module;

[0072] The obstacle avoidance sensor 5 is a sonar sensor or a laser sensor, which is installed at the front end of the vehicle body in the forward direction of the walking assistance robot. It is used to collect sonar data and laser data, and then obtain the distance of obstacles in front of the walking assistance robot, and send them to the intention recognition and environment recognition module and the adaptive control module respectively.

[0073] like Figures 2-3 As shown, the present invention provides an adaptive control method for a walking assistance robot, comprising the following steps:

[0074] 1) The sensor information collected by the sensor information acquisition module is directly transmitted to the adaptive control module on the one hand, and to the intention recognition and environment recognition module on the other hand;

[0075] 2) The intention recognition and environment recognition module recognizes and analyzes the intensity of a person's walking intention, including the direction and speed of walking, through the capacitive contact sensor information and the force sensor information, and sends it to the adaptive control module;

[0076] 3) At the same time, the intention recognition and environment recognition module recognizes the change in ground slope when the user is walking with assistance, and selects different assistance or resistance modes according to the feedback signal, and sends it to the adaptive control module;

[0077] 4) The adaptive control module dynamically adjusts the speed command size and direction, and the resistance / assistance size of the motion control according to the user's walking intention including the walking direction and speed, and transmits them to the motion control module to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking. At the same time, the adaptive control module unit provides safety protection for the user based on the sensor data collected by the sensor information acquisition module.

[0078] like Figure 3 As shown in the figure, the intention recognition and environment recognition module includes: an intention recognition and behavior analysis unit and an environment recognition unit respectively connected to the adaptive control module;

[0079] The intention recognition and behavior analysis unit is connected to the capacitive contact sensor and the force sensor respectively, and is used to receive the magnitude of the force generated when the user uses the left and right handles, judge the user's walking intention intensity, quantify the intention intensity, and send the predicted user walking speed and direction to the adaptive control module;

[0080] The environment recognition unit is connected to the gyroscope sensor and is used to obtain the change of ground slope when the user walks according to the posture of the walking assistance robot sent, and select different assistance or resistance size modes according to the change of ground slope, and send it to the adaptive control module.

[0081] like Figure 2-3 As shown, regarding step 2), it mainly involves the functions of the intention recognition and environment recognition modules, and specifically performs the following steps:

[0082] 2-1) The force sensor embedded in the handlebar is used to determine the strength of the user's intention to walk. According to the size of the force sensor data, the strength of the user's intention to walk can be quantified, and the speed at which the user wants to walk can be given.

[0083] v i =f v (F r ,F l )

[0084] Among them, v i is the user's target walking speed; F r F is the actual force applied by the user to the right handle of the walking assistance robot; l The actual force applied by the user to the left handle of the walking assistance robot;

[0085] The difference in strength between the left and right hands can indicate the direction the user wants to walk. For example, when the user turns left, the strength of the left handlebar must be weakened or the left hand has the strength to pull the handlebar backwards, while the right hand will increase the strength to push the car. Based on this, the speed of the two wheels of the car is controlled, and the motion differential adjusts the deflection angle of the car to achieve the steering function.

[0086] α i =f d (F r -F l )

[0087] Among them, α i F is the user's target rotation angle; r F is the actual force applied by the user to the right handle of the walking assistance robot; l It is the actual force applied by the user to the left handle of the walking assistance robot.

[0088] 2-2) Environmental recognition The posture of the walking assistance robot is calculated by obtaining data from the gyroscope sensor. The change in posture is used to determine the change in ground slope when the user is walking. The walking assistance robot detects ground slope changes in the range of 5° to 15°. When the ground slope is less than 5°, the robot works in flat ground mode; when the ground slope is greater than 5°, the robot works in slope mode, providing continuous assistance during the uphill process and continuous resistance during the downhill process; when the ground slope is greater than 15°, the robot works on a slope with a slope of 15°.

[0089] like Figure 2-3 As shown in the figure, human-machine interaction force control is to control the interaction force between people and walking assistance robots as the object of control, control the walking assistance robot's travel speed, and play the role of assisting users in walking. For example, when the user's lower limbs are not fully functional, the robot needs to provide an auxiliary force during walking to prevent the user from falling forward due to unstable center of gravity; when the user uses the walking assistance robot in slope mode, continuous assistance needs to be provided during the uphill process to ensure that the user walks smoothly.

[0090] like Figure 3 As shown, the adaptive control module includes: a speed adaptive control unit, a human-machine interaction force control unit and a user protection unit;

[0091] The speed adaptive control unit is connected to the intention recognition and behavior analysis unit and the motor parameter acquisition unit respectively, and is used to dynamically adjust the motor current and speed information according to different power assistance or resistance size modes and motor current and speed information sent by the intention recognition and behavior analysis unit;

[0092] The human-machine interaction force control unit is connected to the environment recognition unit and the motor parameter acquisition unit respectively, and is used to control the travel speed of the walking assistance robot according to the interaction force between the human and the walking assistance robot as the control object, so as to assist the user in walking;

[0093] The user protection unit is connected to the capacitive contact sensor, the force sensor and the obstacle avoidance sensor respectively, and is used to judge whether the user has disengaged the handles based on the information from the capacitive contact sensor, and to start and stop the walking assistance robot; at the same time, based on the changes in the force generated when the user uses the left and right handles, it is judged whether the user is in danger of falling, and the walking assistance robot is controlled to start the anti-reversing function; it also detects obstacles in front of the walking assistance robot, and slows down or stops when the obstacle reaches a set distance while the user is walking, to prevent the user from being tripped or hit by the obstacle.

[0094] Regarding step 4), it mainly involves the functions of the adaptive control module, and specifically performs the following steps:

[0095] 3-1) Speed ​​adaptive control, the speed limit of the walking assistance robot can be set to "1-5", and the corresponding speeds are approximately 0.6m / s, 0.8m / s, 1.0m / s, 1.2m / s, and 1.4m / s. When the user pushes the walking assistance robot to walk at a speed greater than the set speed limit, the walking assistance robot will provide protective resistance, and the resistance size is the setting value of the current "resistance" gear; when the user pushes the walking assistance robot to walk at a speed less than the speed limit, the walking assistance robot provides continuous assistance in the direction of travel, and the assistance size is the setting value of the current "assistance" gear. The speed of the walking assistance robot is dynamically adjusted through different modes and different user travel speeds to achieve speed adaptive control.

[0096] 3-2) Handle detection: After the walking assistance robot is powered on, the user holds the handlebars with both hands to push the walking assistance robot forward, and the speed changes with the user's walking speed. If the user leaves the handlebars with either hand, the walking assistance robot will stop immediately.

[0097] 3-3) The force sensor detects the change in thrust before the user falls, and determines the trend and risk of falling. When the robot detects the fall signal, it adopts the best anti-fall strategy to prevent the user from falling or minimize the damage caused by the fall. When the user is tripped by an obstacle and the body falls forward rapidly, the change in human-machine interaction force can be detected to determine whether there is a risk of falling, and the anti-fall function is activated.

[0098] 3-4) The distance of obstacles in front of the walking assistance robot is detected by sonar sensors and laser sensors. When the obstacle reaches the set distance while the user is walking, the robot slows down or stops to prevent the user from being tripped or hit by the obstacle.

[0099] like Figure 4As shown in the figure, the motion control module adopts PID control method to perform closed-loop control on the motor speed of the walking assistance robot. By measuring the error between the actual motor speed of the walking assistance robot and the target speed of the desired control output, combined with the set maximum movement speed, and according to the three pre-calibrated parameters of proportion, integration and differentiation, the motor speed control amount of the walking assistance robot is output, and the current input of the motor drive control in the motion control module is adjusted to make the motor speed of the walking assistance robot as close as possible to the speed control instruction requirements that meet the user's intentions.

[0100] In summary, the present invention takes the interaction force between a person and a walking assistance robot as the object of control, and can assist the user to walk easily and freely according to the user's movement intention, such as turning assistance walking, forward assistance walking, parking, etc. The walking speed of the walking assistance robot can be dynamically adjusted according to the walking speed of the user.

[0101] At the same time, the walking assistance robot in the present invention can provide different assistance / resistance modes according to the change of the slope of the ground on which the user walks (flat ground, uphill or downhill) to adapt to the walking needs of the user in different environments. When the user leaves the handle, a low obstacle suddenly appears in front, or the user is walking at an excessive speed, the parking brake is applied to provide safety protection. The falling tendency can also be detected and judged according to the magnitude of the interaction force between the user and the walking assistance robot, and effective protection can be provided to improve the safety protection capability.

[0102] Those skilled in the art will appreciate that the above are only preferred embodiments of the present invention, and the various embodiments of the present disclosure and / or the features described in the claims may be combined or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. It is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or perform equivalent substitutions on some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

[0103] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An adaptive control system for a walking assistance robot, characterized in that: include: Sensor information acquisition module, intention recognition and environment recognition module, adaptive control module and motion control module; The sensor information acquisition module is used to collect sensor information located at various positions of the walking assistance robot in real time and send it to the intention recognition and environment recognition module and the adaptive control module; The intention recognition and environment recognition module is used to recognize and analyze the user's walking intention including the walking direction and speed according to the sensor information received at various positions of the walking assistance robot, select different walking modes according to the feedback signal, and send it to the adaptive control module; at the same time, it also recognizes the change of ground slope during user assisted walking, selects different modes of providing assistance or resistance according to the feedback signal, and sends it to the adaptive control module; The adaptive control module is used to dynamically adjust the speed instruction size and direction of the motion control module according to the user's walking intention including the walking direction and speed, and dynamically adjust according to the mode of providing different assistance or resistance, and transmit it to the motion control module; at the same time, it also provides safety protection for the user according to the sensor data collected by the sensor information collection module, and transmits it to the motion control module; The motion control module is used to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking.

2. The adaptive control system for a walking assistance robot according to claim 1, characterized in that: The sensor information acquisition module includes: a capacitive contact sensor, a gyroscope sensor, a motor parameter acquisition unit, a force sensor and an obstacle avoidance sensor; The capacitive contact sensor is arranged on the device handle (2) of the walking assistance robot, and is used to collect capacitive contact sensor information for grip detection, and send it to the intention recognition and environment recognition module and the adaptive control module respectively; The gyroscope sensor is arranged in the controller (6) of the walking assistance robot, and is used to collect the angular velocity or angular displacement of the walking assistance robot in space, so as to obtain the posture of the walking assistance robot in real time, and send it to the intention recognition and environment recognition module; The motor parameter acquisition unit is used to collect the motor current and speed information fed back by the motor, and send them to the intention recognition and environment recognition module and the adaptive control module respectively; The force sensor is arranged on the device handle (2) of the walking assistance robot, and is used to collect the force generated when the user uses the left and right handles of the device handle (2), and send the magnitude of the force to the intention recognition and environment recognition module and the adaptive control module; The obstacle avoidance sensor (5) is a sonar sensor or a laser sensor, which is arranged at the front end of the vehicle body in the forward direction of the walking assistance robot, and is used to collect sonar data and laser data, thereby obtaining the distance of obstacles in front of the walking assistance robot, and sending them to the intention recognition and environment recognition module and the adaptive control module respectively.

3. The adaptive control system for a walking assistance robot according to claim 1, characterized in that: The intention recognition and environment recognition module includes: an intention recognition and behavior analysis unit and an environment recognition unit respectively connected to the adaptive control module; The intention recognition and behavior analysis unit is connected to the capacitive contact sensor and the force sensor respectively, and is used to receive the magnitude of the force generated when the user uses the left and right handles, judge the user's walking intention intensity, quantify the intention intensity, and send the predicted user walking speed and direction to the adaptive control module; The environment recognition unit is connected to the gyro sensor and is used to obtain the change of ground slope when the user walks according to the sent walking assistance robot posture, select different assistance or resistance size modes according to the change of ground slope, and send it to the adaptive control module.

4. The adaptive control system for a walking assistance robot according to claim 1, characterized in that: The adaptive control module includes: a speed adaptive control unit, a human-machine interaction force control unit and a user protection unit; The speed adaptive control unit is connected to the intention recognition and behavior analysis unit and the motor parameter acquisition unit respectively, and is used to dynamically adjust the motor current and speed information according to different power assistance or resistance size modes and motor current and speed information sent by the intention recognition and behavior analysis unit; The human-machine interaction force control unit is connected to the environment recognition unit and the motor parameter acquisition unit respectively, and is used to control the travel speed of the walking assistance robot according to the interaction force between the human and the walking assistance robot as the control object, so as to assist the user in walking; The user protection unit is connected to the capacitive contact sensor, the force sensor and the obstacle avoidance sensor respectively, and is used to judge whether the user has disengaged the handles based on the information from the capacitive contact sensor, and to start and stop the walking assistance robot; at the same time, based on the changes in the force generated when the user uses the left and right handles, it is judged whether the user is in danger of falling, and the walking assistance robot is controlled to start the anti-reversing function; it also detects obstacles in front of the walking assistance robot, and slows down or stops when the obstacle reaches a set distance while the user is walking, to prevent the user from being tripped or hit by the obstacle.

5. The control method of the adaptive control system applied to a walking assist robot according to claim 1, characterized in that: The following steps are involved: 1) The sensor information collected by the sensor information acquisition module is directly transmitted to the adaptive control module on the one hand, and to the intention recognition and environment recognition module on the other hand; 2) The intention recognition and environment recognition module recognizes and analyzes the intensity of a person's walking intention, including the direction and speed of walking, through the capacitive contact sensor information and the force sensor information, and sends it to the adaptive control module; 3) At the same time, the intention recognition and environment recognition module recognizes the change in ground slope when the user is walking with assistance, and selects different assistance or resistance modes according to the feedback signal, and sends it to the adaptive control module; 4) The adaptive control module dynamically adjusts the speed command size and direction, and the resistance / assistance size of the motion control according to the user's walking intention including the walking direction and speed, and transmits them to the motion control module to realize the motion control of the left and right wheel motors of the walking assistance robot to assist the user in walking. At the same time, the adaptive control module provides safety protection for the user based on the sensor data collected by the sensor information acquisition module.

6. The adaptive control method for a walking assistance robot according to claim 5, characterized in that: The step 2) is specifically: 2-1) The intention recognition and behavior analysis unit obtains the data information of the capacitive contact sensors and force sensors on the left and right handles of the walking assistance robot, identifies the user's walking intention including the walking direction and speed, and quantifies the intensity of the user's walking intention according to the size of the force sensor data to obtain the user's target walking speed, that is: v i =f v (F r ,F l ) Among them, v i is the user's target walking speed; F r F is the actual force applied by the user to the right handle of the walking assistance robot; l The actual force applied by the user to the left handle of the walking assistance robot; 2-2) Select different walking modes according to the feedback signal: turning movement, forward / backward movement, stationary and starting; 2-3) The user's target walking direction is obtained based on the difference in the force between the left and right hands; 2-4) When the force of one side handle is reduced or there is a pulling force on one side handle, and the force of the other side handle is increased, the speed of the two wheels of the car is controlled according to the user's target walking direction, and the motion differential adjusts the deflection angle of the car to reach the turning position. The direction angle is: α i =f d (F r -F l ) Among them, α i F is the user's target rotation angle; r F is the actual force applied by the user to the right handle of the walking assistance robot; l It is the actual force applied by the user to the left handle of the walking assistance robot.

7. The adaptive control method for a walking assistance robot according to claim 5, characterized in that: In step 3), the intention recognition and environment recognition module recognizes the change in ground slope when the user assists walking, specifically: The environment recognition unit obtains the change of the ground slope when the user walks according to the change of the posture of the walking assistance robot obtained by the gyroscope sensor; Among them, the walking assistance robot detects ground slope changes ranging from 5° to 15°; When the ground slope is less than 5°, the walking assistance robot works in flat ground mode; when the ground slope is greater than 5°, the walking assistance robot works in slope mode, providing continuous assistance during the uphill process and continuous resistance during the downhill process; when the ground slope is greater than 15°, the walking assistance robot works in slope mode with a slope of 15°.

8. The adaptive control method for a walking assistance robot according to claim 5, characterized in that: The adaptive control module dynamically adjusts the speed command size and direction of motion control, specifically: When the user pushes the walking assistance robot to a speed greater than the set speed limit, the walking assistance robot will provide protective resistance, the resistance size of which is the set value of the current resistance gear; When the user pushes the walking assistance robot to walk at a speed lower than the speed limit, the walking assistance robot provides continuous assistance in the direction of travel, and the magnitude of the assistance is the setting value of the current assistance gear; The speed of the walking assistance robot is dynamically adjusted through different modes and different user travel speeds to achieve speed adaptive control.

9. The adaptive control method for a walking assistance robot according to claim 5, characterized in that: The adaptive control module performs security protection on the user according to the sensor data collected by the sensor information collection module, specifically: a. The user protection unit determines whether the user has disengaged the handle according to the capacitive contact sensor information, and starts and stops the walking assistance robot; b. The user protection unit determines whether the user is in danger of falling according to the change in the force generated when the user uses the left and right handles, and controls the walking assistance robot to start the anti-reversing function; c. The user protection unit detects obstacles in front of the walking assistance robot and slows down or stops when the obstacle reaches a set distance while the user is walking, preventing the user from being tripped or hit by the obstacle.

Images