A robot behavior control method with human-computer interaction function

Abstract

This invention provides a robot behavior control method with human-computer interaction capabilities, relating to the field of robotics. It allows the robot to interact with the user, identifying non-standard movements through a robot terminal, and assisting the user in correcting those movements. It is applicable to various movement calibration scenarios, such as dance movement calibration, fitness movement calibration, and rehabilitation movement calibration. This can improve the accuracy and efficiency of training.

Description

Technical Field

[0001] This invention relates to robotics technology, and more particularly to a method for controlling robot behavior with human-computer interaction capabilities. Background Technology

[0002] In modern life, people are paying increasing attention to their health and skill improvement. Whether it's for rehabilitation to restore physical function, building a good physique through fitness, or pursuing exquisite performance in dance, precise movement calibration is a crucial element.

[0003] However, traditional motion calibration methods have many limitations. Most rely on one-on-one human guidance, which not only consumes a lot of manpower and time, but also the level of the instructors varies, making it difficult to guarantee the accuracy and consistency of the calibration.

[0004] Therefore, a solution is urgently needed to overcome this bottleneck. Summary of the Invention

[0005] This invention provides a robot behavior control method with human-computer interaction function, which can improve the efficiency and accuracy of action calibration.

[0006] A first aspect of the present invention provides a robot behavior control method with human-computer interaction function, comprising a robot body and an interaction device carrier, wherein the robot body is provided with a plurality of electrode plates, and the interaction device carrier is provided with metal components corresponding to the electrode plates, comprising:

[0007] The robot's camera module identifies the user's current actions and records any non-compliant actions by comparing the current actions with standard actions.

[0008] Identify the calibration area corresponding to the non-compliant action, activate the electrode plate corresponding to the calibration area, and make it fit with the corresponding metal component of the interactive device carrier;

[0009] Control the robot to perform standard actions and generate reminder messages.

[0010] Optionally, in one possible implementation of the first aspect, the user's current action is identified by the robot's camera module, and non-compliant actions of the user are recorded based on a comparison between the current action and a standard action, including:

[0011] Acquire image data captured by the camera module and extract key points of the human body from the image data;

[0012] Determine the user's current action based on the relative position and current angle of each key point;

[0013] Retrieve the standard position and standard angle of the preset point corresponding to the standard action, compare the standard position and standard angle with the relative position and the current angle respectively, and determine the current action with a similarity of less than the threshold as a non-compliant action.

[0014] Optionally, in one possible implementation of the first aspect, before identifying the user's current action based on the robot's imaging module and recording the user's non-compliant action by combining the comparison result of the current action and the standard action, the method further includes:

[0015] The camera module identifies the user's actual height and obtains the ratio between the user's hands and height.

[0016] Based on the initial limb length and height of the robot body, combined with the aforementioned proportional relationship and height value, the adjustment parameters of the robot body's limb parts are calculated, including the hands and legs.

[0017] Adjust the robot's limbs according to the adjustment parameters to make the robot's height match the user's height.

[0018] Optionally, in one possible implementation of the first aspect, the process of identifying the user's current action based on the robot's imaging module and recording the user's non-compliant action by combining the comparison result of the current action and the standard action further includes:

[0019] Identify key points of the human body in multiple frames of images captured by the shooting module, and calculate the displacement values ​​of the same key points in adjacent frames;

[0020] Calculate the average value of multiple displacement values ​​to determine the preset standard displacement value of the robot body, and obtain the adjustment coefficient based on the ratio of the average value and the standard displacement value.

[0021] The standard speed of the robot body is offset and adjusted based on the product of the adjustment factor and the standard speed of the robot body.

[0022] Optionally, in one possible implementation of the first aspect, the process of identifying the user's current action based on the robot's imaging module and recording the user's non-compliant action by combining the comparison result of the current action and the standard action further includes:

[0023] Obtain the user's input proficiency level and control the robot's movements according to the preset speed corresponding to the proficiency level;

[0024] The system collects the user's current speed in real time, obtains the speed difference between the preset speed and the current speed, and controls the robot's movements according to the preset speed that is one level lower than the current proficiency level when the speed difference is greater than the threshold.

[0025] Optionally, in one possible implementation of the first aspect, determining the calibration location corresponding to the non-compliant action, activating the electrode plate corresponding to the calibration location, and making it fit against the corresponding metal component of the interactive device carrier includes:

[0026] The actual position of the metal component corresponding to the electrode is identified based on the image data collected by the imaging module;

[0027] A preferred path is generated, starting from the current position of the electrode plate at the calibration site and ending at the actual position of the metal component.

[0028] The robot body's calibration section is moved according to the preferred path, and the corresponding electrode plates are activated to perform a bonding operation between the electrode plates and metal parts at the calibration section.

[0029] Optionally, in one possible implementation of the first aspect, controlling the movement of the calibration section of the robot body according to the preferred path includes:

[0030] Obtain the distance values ​​between the corresponding electrode plates and metal components in the calibration area during the movement;

[0031] When the distance value exceeds the distance threshold, the calibration part is moved according to the preset speed.

[0032] When the distance value is less than or equal to the distance threshold, the preset speed is offset according to the product of the ratio of the distance value and the distance threshold and the preset speed, and the movement of the calibration part is controlled according to the offset speed.

[0033] Optionally, in one possible implementation of the first aspect, the robot body is controlled to perform standard actions and generate reminder information, including:

[0034] The robot body is controlled to perform standard actions, and the force feedback module collects the force applied by the user at the corresponding position of each electrode plate.

[0035] A warning message is generated when the applied force value is outside the standard applied force value range.

[0036] Optionally, in one possible implementation of the first aspect, the process of generating a reminder message when the applied force value is not within the standard applied force value range further includes:

[0037] When the applied force value is less than the minimum value of the interval, obtain the first adjustment value corresponding to the difference between the minimum value of the interval and the applied force value, and add the first adjustment value to the current value of the corresponding electrode plate;

[0038] When the applied force value is greater than the maximum value of the interval, obtain the second adjustment value corresponding to the difference between the applied force value and the maximum value of the interval, and subtract the second adjustment value from the current value of the corresponding electrode.

[0039] Optionally, in one possible implementation of the first aspect, the average adjustment value of the first adjustment value and / or the second adjustment value after each electrode plate has finished calibration is obtained, and the position corresponding to the electrode plate whose average adjustment value is greater than a preset threshold is determined as a position prone to error.

[0040] Calculate the average historical current value of error-prone locations, and set the current value of the corresponding electrode plate to this average value during the next interactive operation.

[0041] A second aspect of the present invention provides a robot behavior control system with human-computer interaction function, comprising a robot body and an interaction device carrier, wherein the robot body is provided with a plurality of electrode plates, and the interaction device carrier is provided with metal components corresponding to the electrode plates, including:

[0042] The recognition module is used to identify the user's current action based on the robot's camera module, and record the user's non-compliant actions by combining the comparison results of the current action and the standard action.

[0043] The bonding module is used to identify the calibration area corresponding to the non-compliant action, activate the electrode plate corresponding to the calibration area, and bond it with the corresponding metal part of the interactive device carrier.

[0044] The calibration module is used to control the robot body to perform standard actions and generate reminder messages.

[0045] The beneficial effects of this invention are as follows:

[0046] By installing cameras at multiple locations on the robot, image fusion technology is used to acquire complete user motion information. The detected real-time motion postures are compared with a pre-built standard motion library, and the similarity is precisely calculated to accurately identify non-compliant user movements. This precise motion recognition and recording method provides a reliable basis for subsequent motion calibration, greatly improving the targeting and effectiveness of the calibration. For example, in dance motion calibration, it can accurately capture subtle deviations in each joint of the dancer, helping them quickly improve their movements and enhance their dance performance; in fitness scenarios, it can promptly identify incorrect movements by fitness enthusiasts, reducing the risk of sports injuries; for rehabilitation patients, it can record their motion recovery status in detail, providing strong data support for adjusting rehabilitation treatment plans.

[0047] Based on the user's height and hand-to-body ratio obtained from the camera module, combined with the robot's initial limb length and height, the adjustment parameters for the robot's limbs (hands and legs) are precisely calculated. This achieves accurate matching between the robot's height and the user's height, greatly improving the convenience and comfort of human-computer interaction. Simultaneously, the robot's movement speed is adjusted in multiple ways. It can be adjusted by calculating the ratio of the average displacement value to the standard displacement value based on the displacement values ​​of key human body points in multiple frames captured by the camera module, obtaining an adjustment coefficient to offset the robot's standard speed. Alternatively, it can be adjusted flexibly based on the preset speed corresponding to the user's input proficiency level, combined with the real-time collected user speed; when the speed difference exceeds a threshold, the robot's movement speed is adjusted. This personalized speed adaptation mechanism allows the robot to closely follow the user's movement rhythm, providing customized services for users with different proficiency levels and movement speeds.

[0048] After identifying the calibration points corresponding to the user's non-compliant actions, the robot precisely controls the corresponding electrode pads to adhere to the metal components on the interactive device carrier. During the adhesion process, the distance between the electrode pads and the metal components is monitored in real time, and the movement speed of the calibration points is dynamically adjusted to ensure efficient and accurate adhesion. When the user follows the robot to perform standard actions, the force feedback module collects the user's applied force values ​​at the corresponding positions of each electrode pad in real time. When the applied force value deviates from the standard applied force value range, the electrode pad current is automatically adjusted. If the applied force is insufficient, the current is increased to enhance the adhesion and assist the user in applying force; if the applied force is excessive, the current is decreased to reduce the user's applied force, thereby helping the user to better complete the standard actions, improving training effectiveness, and ensuring training safety. In addition, by calculating the average adjustment value of each electrode pad after calibration, error-prone high-risk locations are identified, and the electrode pad current value is pre-set for the next interactive operation based on the historical average current value of that location, further optimizing the calibration effect for error-prone areas. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present invention;

[0050] Figure 2 This is a flowchart illustrating a robot behavior control method with human-computer interaction function provided in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the structure of a robot behavior control system with human-computer interaction function provided in an embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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.

[0053] See Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of the present invention. Specifically, this embodiment allows interaction between a robot and a user. The robot terminal identifies the user's movements, identifies non-standard movements, and assists the user in calibrating their movements. It is applicable to various movement calibration scenarios, such as dance movement calibration, fitness movement calibration, and rehabilitation movement calibration.

[0054] This embodiment includes a robot body and an interactive device carrier. The robot body is equipped with multiple electrode pads, and the interactive device carrier is equipped with metal components corresponding to the electrode pads. The interactive device carrier can be clothing with metal components. Thin, highly magnetically conductive metal patches can be sewn or embedded in key joint areas such as the shoulder, elbow, wrist, hip, knee, and ankle. The shape and size of these metal patches are optimized to ensure sufficient adhesion area with the robot's electrode pads without hindering the user's normal activities. For example, the metal patch on the wrist is designed to be small and flexible, not impeding wrist rotation. When the user wears the interactive device carrier, the electrode pads in the robot body and the metal components in the interactive device carrier adhere to each other, allowing the user to control the robot body to assist in calibrating their movements.

[0055] See Figure 2 This is a flowchart illustrating a robot behavior control method with human-computer interaction function provided in an embodiment of the present invention. Figure 2 The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S101 to S103 are detailed as follows:

[0056] S101 identifies the user's current action based on the robot's camera module and records the user's non-compliant actions by comparing the current action with the standard action.

[0057] In practical applications, the imaging module can be a camera, which can be installed at multiple locations on the robot body, such as the chest, arms, back, and head, forming a distributed viewing system. Cameras in different locations can capture user actions from different angles, and through image fusion technology, complete user action information can be obtained.

[0058] During user training, the robot can demonstrate a set of movements, which the user follows. The robot identifies and records any non-standard movements, which deviate from the standard movements. The standard movements are the correct actions the user is currently performing. The robot obtains the corresponding movement instructions through several methods: First, it can connect to external devices (such as smart speakers or mobile apps), allowing users to send preset movement sequences (such as fitness routines or dance combinations) to the robot via voice or by selecting them on the app. Second, the robot has its own movement programming capabilities, allowing users to program movements themselves via gestures or touchscreens on the robot's interface. The robot records and stores these movement instructions. Third, the robot can also access the latest movement library from a cloud server. This library, created and uploaded by professional fitness coaches and dance choreographers, contains movements of various types and difficulty levels. After demonstrating a movement, the robot can collect the user's movements and compare them with the current standard movements to identify and record any non-standard actions.

[0059] Based on the above embodiments, step S101 can be implemented in the following ways:

[0060] The system acquires image data collected by the camera module and extracts key points of the human body from the image data.

[0061] Specifically, cameras on the robot itself can be used to capture user movements in real time from multiple angles, obtaining continuous image sequences to ensure comprehensive capture of the movement information of human joints and limbs. Then, deep learning detection models, such as OpenPose and HRNet, are used to learn the feature patterns of different parts of the human body, thereby accurately detecting key points. These key points are critical joints in the human body, such as the shoulder, elbow, wrist, hip, knee, and ankle.

[0062] The user's current action is determined based on the relative position and current angle of each key point.

[0063] By analyzing the connections between key points, a skeletal structure can be constructed. By analyzing the relative positions and current angles of each joint within the skeletal structure, the current posture of the human body can be determined. For example, by calculating the angles and distances between the joints of the arm, it can be determined whether the arm is straight or bent, and the degree of bending.

[0064] Retrieve the standard position and standard angle of the preset point corresponding to the standard action, compare the standard position and standard angle with the relative position and the current angle respectively, and determine the current action with a similarity of less than the threshold as a non-compliant action.

[0065] In practical applications, image sequences of various standard movements and their corresponding preset point coordinates can be pre-collected and labeled to construct a standard movement library. The real-time detected movements are compared with the movements in the standard movement library to calculate the similarity between them. An appropriate threshold is set, and movements with a similarity less than the threshold are judged as non-standard movements.

[0066] Among them, the preset point refers to the preset joint point. During the comparison, the position distance and angle of the corresponding joint point can be compared separately. The similarity values ​​of distance and angle are calculated and then added together to obtain the similarity after fusion calculation, which can improve the accuracy of the judgment.

[0067] When recording non-compliant movements, the coordinates of detected key human body points and related feature data, such as joint angles, can be saved in the form of text files or databases. To facilitate the differentiation of key points, each key point can be assigned a unique corresponding number. During recording, the key point number, its coordinate value in the image, and feature values ​​can be saved for subsequent querying and analysis.

[0068] Furthermore, to improve the synchronization of actions during interaction, the height of the robot body can be adjusted before step S101, taking into account the user's height, to ensure it matches the user's height, thereby improving the efficiency and convenience of human-computer interaction. Specifically, the height of the robot body can be adjusted through the following embodiments:

[0069] The camera module identifies the user's actual height and obtains the ratio between the user's hand and height.

[0070] Specifically, when acquiring a user's height, a full-body frontal image of the user can be captured using the camera module. This ensures the user is standing stably on the same plane, with their body upright, and the camera is perpendicular to the user and within a suitable distance to obtain a clear and complete image of the human body. Then, deep learning-based human keypoint detection algorithms, such as OpenPose, are used to process the captured image and identify key nodes on the user's body, such as the top of the head and ankles. Based on the coordinates of the detected key points on the top of the head and ankles, the pixel distance between the two points is calculated. Since the camera's imaging principle and shooting parameters are known, the pixel distance can be converted into an actual height value using a pre-established mapping relationship between pixels and actual distances.

[0071] When determining the ratio of a user's hand to their height, specific key points of the hand can be identified, such as the acromion and fingertips. Then, the pixel distance from the acromion to the fingertips in the image is measured and compared with the calculated pixel distance of the user's height to determine the ratio of the user's hand to their height, thus enabling the user to better collaborate with the robot.

[0072] Based on the initial limb length and height of the robot body, combined with the aforementioned proportional relationship and height value, the adjustment parameters of the robot body's limb parts are calculated, including the hands and legs.

[0073] The adjustment parameter is the value corresponding to the adjustment range of the robot's limb length. After obtaining the user's height and limb ratio, the adjustment value of the limb parts when the robot body is adjusted to the user's corresponding height can be calculated.

[0074] Since leg length is crucial in determining overall height, the height difference between the user and the robot can be calculated, and this difference can be used to adjust the robot's legs. The adjustment value for the hands can be obtained by subtracting the robot's initial hand length from the product of the user's hand-to-height ratio and their height.

[0075] Adjust the robot's limbs according to the adjustment parameters to make the robot's height match the user's height.

[0076] The robot's hands and legs can be made of retractable material, and their length can be adjusted by controlling motors.

[0077] In step S101, in order to achieve personalized training for users, the movement speed of the robot body during the training process can also be adjusted. By comparing the error between the actual movement speed and the user's movement speed that is expected to be followed, the movement speed of the robot body is continuously adjusted so that the robot body can follow the changes in the user's movement speed more accurately and smoothly, thereby improving the accuracy of training.

[0078] Specifically, in some embodiments, the movement speed of the robot body can be adjusted through the following steps:

[0079] The system identifies key points of the human body in multiple frames of images captured by the camera module and calculates the displacement values ​​of the same key points in adjacent frames.

[0080] The camera module captures user movements in real time, identifies and tracks user body parts in multiple frames, obtains the position information of key points on the user's body and their changes over time, and can extract feature parameters related to movement speed, namely the displacement values ​​of each key point in adjacent frames.

[0081] Calculate the average value of multiple displacement values ​​to determine the preset standard displacement value corresponding to the robot body, and obtain the adjustment coefficient based on the ratio of the average value to the standard displacement value.

[0082] Understandably, since there are multiple key points, the user's speed can be determined by averaging the values ​​of these key points. In practical applications, a standard displacement value corresponding to the standard speed during the robot's movement can be pre-configured. The ratio of the average value to the standard displacement value yields an adjustment coefficient for offset, which can be used to adjust the robot's standard speed.

[0083] The standard speed of the robot body is offset and adjusted based on the product of the adjustment factor and the standard speed of the robot body.

[0084] By offsetting the standard speed, the robot's speed can be adjusted to match the user's speed based on the difference between the user's movement speed and the robot's current movement speed. For example, if the user's movement speed increases, the robot's movement speed can be increased accordingly; if the user's movement speed decreases, the robot's movement speed can be decreased.

[0085] In some other embodiments, the movement speed of the robot body can also be adjusted through the following steps:

[0086] Obtain the user's input proficiency level and control the robot's movements according to the preset speed corresponding to the proficiency level.

[0087] In practical applications, users can input their proficiency level in specific activities (such as dance, fitness, rehabilitation training, etc.). The proficiency level can be a user's subjective assessment of their ability level in the activity, such as being divided into different levels like beginner, intermediate, and advanced, or it can be a level determined through previous tests or training records.

[0088] Each proficiency level has a pre-set speed. For example, the preset speed for the beginner proficiency level is slower, suitable for beginners to gradually become familiar with the movements and rhythm; the preset speed for the advanced proficiency level is faster, suitable for users with a certain foundation and ability to conduct more challenging training.

[0089] The system collects the user's current speed in real time, obtains the speed difference between the preset speed and the current speed, and controls the robot's movements according to the preset speed that is one level lower than the current proficiency level when the speed difference is greater than the threshold.

[0090] When collecting the user's current speed, it can be obtained through image frames captured by the camera module, or specifically determined through the displacement values ​​of key points. After determining the current speed, it can be compared with the preset speed corresponding to the user's current proficiency level, and the speed difference between the two can be calculated. This difference reflects the discrepancy between the user's actual movement speed and the system's expected speed.

[0091] A speed difference threshold can also be set. This threshold is determined based on the nature and requirements of the activity and is used to determine if the difference between the user's current speed and the preset speed is too large. When the calculated speed difference is greater than this threshold, it indicates that the user may not be able to keep up with the preset speed corresponding to their current proficiency level, and may experience movement difficulties or other problems. Therefore, in this case, the robot's speed can be adjusted to a preset speed one level lower than the user's current proficiency level. The purpose of this is to make the robot's speed more in line with the user's actual ability, helping the user complete the activity better and avoiding situations where the user is injured or unable to continue training due to excessive speed. For example, if the user is currently at an intermediate proficiency level, when the speed difference is greater than the threshold, the robot will move at the preset speed corresponding to the beginner proficiency level, providing the user with a more suitable training rhythm.

[0092] S102, determine the calibration location corresponding to the non-compliant action, activate the electrode plate corresponding to the calibration location, and make it fit with the corresponding metal component of the interactive device carrier.

[0093] The calibration area refers to the body part corresponding to the non-standard movement, such as the arm. Understandably, once the non-standard body part of the user is identified, after the user puts on the interactive device, the electrode pads of the robot body can be attached to the corresponding metal parts in the interactive device. This allows the robot to control the movement of the corresponding part according to the action commands, thus inducing the user to perform actions and calibrating the user's movements.

[0094] It's important to note that the electrode pads on the robot body do not generate magnetism when not energized. The reason for identifying the calibration area before energizing the corresponding electrode pads is to allow the robot to apply force more effectively to specific areas, achieving precise control and calibration of movements. For example, when performing fine hand movements, energizing only the electrode pads near the wrist and arm joints allows the robot to precisely adjust the force and movement trajectory in these areas, avoiding unnecessary interference from energized areas and improving the accuracy of movement execution.

[0095] Specifically, after determining the calibration location, the position of the metal patch corresponding to the calibration location in the interactive device carrier can be determined. After the robot body adjusts its own position, it will adsorb and attach the corresponding electrode plate and metal component. During the attachment process, the selected electrode plate can be energized to generate magnetism. The start-up process is the energization process.

[0096] Based on the above embodiments, step S102 can be implemented in the following ways:

[0097] The actual position of the metal component corresponding to the electrode is identified based on the image data collected by the imaging module.

[0098] Specifically, the camera can identify the location of metal parts on a user's clothing. For example, by extracting features of the metal parts in an image (such as shape, color, and texture), the exact location of the metal parts in the image can be accurately determined. Then, the actual location of the metal part corresponding to the corresponding electrode plate can be determined. This can be done by converting the center point coordinates of the metal part through the mapping relationship between pixels and actual distance.

[0099] Starting from the current position of the electrode plate at the calibration site and ending at the actual position of the metal component, an optimal path is generated.

[0100] The starting point of the path is determined by the current position of the electrode pads on the calibration site (e.g., the user's arm, leg, or other body part requiring electrode attachment). This position can be obtained by the robot itself using its encoders, gyroscopes, or other sensors. The actual position of the metal component serves as the ending point of the path. Based on the starting and ending point positions, a path planning algorithm (such as Dijkstra's algorithm) is used to generate a path from the current position of the electrode pads to the actual position of the metal component. The optimal path is the best path from the current position to the actual position, which can be the shortest path.

[0101] During the path generation process, various factors can be considered, such as collecting surrounding obstacles and avoiding them when planning the path.

[0102] The robot body's calibration section is moved according to the preferred path, and the corresponding electrode plates are activated to perform a bonding operation between the electrode plates and metal parts at the calibration section.

[0103] Based on the generated preferred path, commands are sent to the robot's control system to control the movement of the robot's calibration parts (such as the robotic arm) along the path. The robot's drive system precisely adjusts the angles and movements of each joint according to the commands, causing the calibration parts to gradually approach the metal component along the preferred path. During the movement of the robot's calibration parts, the electrode plates associated with those parts can be activated. The electrode plates can be energized to generate magnetism, allowing them to interact with the metal component. When the calibration parts move near the metal component, due to the physical properties of the electrode plates (such as magnetism), the electrode plates will attract and adhere to the metal component. The purpose of this adhesion operation is to ensure a tight connection between the electrode plates and the metal component so that they can function properly in subsequent activities, enabling effective interaction and collaboration between the robot and the user.

[0104] In some embodiments, the movement of the calibration section of the robot body can be controlled according to a preferred path through the following steps:

[0105] The system acquires the distance values ​​between the corresponding electrode plates and metal components in the calibration area during movement. When the distance value is greater than a distance threshold, the calibration area is moved according to a preset speed. When the distance value is less than or equal to the distance threshold, the preset speed is offset based on the product of the ratio of the distance value to the distance threshold and the preset speed, and the calibration area is moved according to the offset speed.

[0106] As the robot moves the calibration area according to a preferred path to achieve contact between the electrode plate and the metal component, the distance between them can be continuously monitored. During this process, the robot's calibration area constantly changes position, and the relative positions of the electrode plate and the metal component also change dynamically.

[0107] When the obtained distance value is greater than the distance threshold, it indicates that the electrode plate and the metal component are still relatively far apart. At this point, the calibration area can be moved at a pre-set speed. This pre-set speed can be a relatively fast and safe speed, the purpose of which is to allow the robot body to quickly approach the metal component, improve the efficiency of the bonding operation, and avoid collisions caused by excessive speed. The distance threshold can be determined based on factors such as the characteristics of the electrode plate and the metal component, the bonding requirements, and the robot's motion performance.

[0108] When the distance between the electrode and the metal component is less than or equal to a distance threshold, it means that they are relatively close. In this case, to more accurately control the bonding process between the electrode and the metal component and avoid impact or inaccurate bonding due to excessive speed, the movement speed of the calibration part needs to be adjusted.

[0109] The ratio of the distance value to the distance threshold is calculated, and then this ratio is multiplied by the preset speed to obtain a speed offset. The principle behind this calculation is that as the electrode and the metal component get closer (the distance value decreases), the speed offset decreases accordingly, thus gradually reducing the movement speed of the calibration part. For example, if the distance value is half the distance threshold, then the speed offset is half the preset speed, meaning the movement speed of the calibration part will become half of the original preset speed.

[0110] Based on the calculated speed offset, the preset speed is adjusted to obtain the offset speed. Then, based on this offset speed, the calibration part is controlled to continue moving, allowing the electrode to approach the metal part at a slower and more precise speed, ultimately achieving an accurate and smooth bonding operation.

[0111] The above method allows for dynamic adjustment of the calibration area's movement speed based on the distance between the electrode and the metal component, improving both bonding efficiency and accuracy.

[0112] S103 controls the robot body to perform standard actions and generates reminder information.

[0113] After the fitting operation is completed, the robot body can control the movement of the corresponding joints according to the motion instructions corresponding to the standard action, so as to drive the user to perform the action. For example, when performing the action of "raising the hand to the horizontal position", the robot's shoulder motor and elbow motor work together to smoothly raise the user's arm according to the preset motion trajectory and speed.

[0114] During the user's action calibration process, the robot can continuously monitor the user's action status through various sensors, and generate reminder information when the action status deviates from the standard status, thereby reminding the user to calibrate.

[0115] In practical applications, reminders can be voice prompts. For example, the robot itself can have a built-in speech synthesis module that, when it detects that the user's movement is not in place, will play a pre-recorded or real-time synthesized prompt through a speaker. For example, "Your arm is not extended enough, please straighten it a little more," clearly and explicitly informing the user of what needs to be improved.

[0116] Through the above methods, precise calibration of actions can be achieved through interaction between the robot and the user.

[0117] Based on the above embodiments, step S103 can be implemented in the following ways:

[0118] The robot body is controlled to perform standard actions, and the force feedback module collects the force applied by the user at the corresponding position of each electrode. When the force applied is not within the standard force range, a reminder message is generated.

[0119] The force feedback module can be a force sensor, where the applied force value refers to the force exerted by the user. Force sensors can be installed at the points of contact between the robot and the user to detect the magnitude and direction of the force applied by the user during the follow-up movement. For example, when the robot guides the user in raising their arm, if the force applied by the user is significantly too large or too small, differing greatly from the force required for the standard movement, it may indicate that the user's force application method is incorrect or that muscle control is uncoordinated, resulting in an improper movement. In this case, a reminder message can be generated to alert the user.

[0120] The standard force range can be a pre-set range of values ​​corresponding to normal force application. For example, when performing a joint extension movement in rehabilitation training, a specific force range is set according to the normal range of motion of the joint and the muscle strength requirements to ensure that the user trains within the correct force range.

[0121] In addition to providing reminders, the robot itself will also adjust the motion parameters of its joints and apply appropriate external force to assist the user in correcting their movements, depending on the degree of difference. Specific examples include the following:

[0122] When the applied force value is less than the minimum value of the interval, obtain the first adjustment value corresponding to the difference between the minimum value of the interval and the applied force value, and add the first adjustment value to the current value of the corresponding electrode. When the applied force value is greater than the maximum value of the interval, obtain the second adjustment value corresponding to the difference between the applied force value and the maximum value of the interval, and subtract the second adjustment value from the current value of the corresponding electrode.

[0123] Specifically, the robot continuously monitors the force applied at various locations by the force feedback module and compares it with the standard force application range. When the force applied at a certain location is found to be less than the minimum value of the standard force application range, it indicates that the user is applying insufficient force at that location, failing to reach the force level required for the standard movement. To adjust the user's force application, the difference between the minimum value of the range and the current force applied can be calculated. Then, based on a pre-defined correspondence (e.g., a mapping table between differences and adjustment values ​​established through experimental data), a first adjustment value corresponding to this difference is obtained. This first adjustment value represents the magnitude of adjustment required to adjust the current of the corresponding electrode to bring the force application within the standard range. After obtaining the first adjustment value, the current value of the corresponding electrode can be manipulated by adding the first adjustment value to the current value, thereby changing the electromagnetic attraction force, increasing the attraction force of the electrode at that location, and guiding the user to move in the correct direction. For example, if the user's arm is raised too low, the robot increases the attraction force of the shoulder electrode to assist the user in raising their arm to the appropriate position.

[0124] Similarly, when the force applied at a specific electrode location exceeds the maximum value of the standard force range, it indicates that the user is applying excessive force at that location, exceeding the reasonable range allowed by standard movements. Such excessive force may lead to issues such as movement distortion and increased risk of injury. In this case, the difference between the applied force and the maximum value of the range can be calculated, and a second adjustment value corresponding to this difference can be obtained based on a pre-set correspondence. This second adjustment value is used to adjust the electrode current to reduce the user's applied force. The second adjustment value is subtracted from the current value of the corresponding electrode. The reduction in electrode current weakens the attraction force it generates, thus reducing the force experienced by the user at that location and bringing the applied force back within the standard force range.

[0125] By adjusting the electrode current based on the relationship between the applied force value and the standard range, the system can automatically intervene and adjust when the user applies abnormal force, helping the user to better complete the standard movements, improve training results, and ensure user safety while avoiding adverse consequences caused by improper force application.

[0126] Based on the above embodiments, this solution also includes the following embodiments:

[0127] Obtain the average adjustment value of the first adjustment value and / or the second adjustment value after each electrode plate has completed calibration. Determine the position of the electrode plate whose average adjustment value is greater than the preset threshold as the error-prone high-incidence position. Calculate the average value of the historical current values ​​of the error-prone high-incidence position and set the current value of the corresponding electrode plate to the average value in the next interactive operation.

[0128] After the calibration process is completed, the first adjustment value (when the applied force is less than the minimum value of the range) and / or the second adjustment value (when the applied force is greater than the maximum value of the range) for each electrode can be recorded throughout the calibration process due to the mismatch between the user's applied force value and the standard applied force value range. These adjustment values ​​reflect the changes made to the electrode current to make the applied force conform to the standard.

[0129] For each electrode, the average of all its first and / or second adjustment values ​​is calculated to obtain the average adjustment value for that electrode. This average adjustment value comprehensively reflects the degree and trend of abnormal force application at the corresponding position of that electrode during this calibration process.

[0130] In practical applications, a preset threshold can be set beforehand, and the average adjustment value of each electrode pad can be compared with this threshold. If the average adjustment value of a certain electrode pad is greater than the preset threshold, it indicates that the corresponding position of that electrode pad has been subjected to abnormally frequent and significant force during this calibration, thus identifying that position as a high-risk error-prone area. For example, in rehabilitation training, if the average adjustment value of the electrode pads at the wrist is large, it indicates that the user frequently deviates from the standard range in applying force to wrist-related movements; the wrist position is a high-risk error-prone area. This helps to accurately locate the body parts where the user is prone to force application problems during movement execution. High-risk error-prone areas are the body parts where the user is prone to force application problems.

[0131] For identified error-prone locations, the current values ​​of the corresponding electrode pads at that location can be queried and collected from past interactive operations, i.e., historical current values. By statistically analyzing these historical current values, their average value can be calculated. These historical current values ​​reflect the current adjustments used to correct force application problems at that location during different calibration processes. For example, after multiple rehabilitation training sessions, the system records the current values ​​of the electrode pads at the wrist during each training session; by calculating the average of these values, a reference-meaning current value can be obtained.

[0132] Before the next interactive operation (such as a new round of rehabilitation training), the current value of the corresponding electrode pads at high-risk locations can be set to the calculated historical average current value. The purpose of this is to optimize the current of the electrode pads at high-risk locations in advance based on past experience. Previous calibration operations have shown that this average current value is effective in guiding the force applied at that location closer to the standard range. For example, at the start of a new round of rehabilitation training, directly setting the current of the wrist electrode pads to the previously calculated historical average value can more quickly help the user achieve the standard force requirements in wrist movements, improving training efficiency and effectiveness.

[0133] See Figure 3This is a schematic diagram of a robot behavior control system with human-computer interaction function provided in an embodiment of the present invention. The robot behavior control system with human-computer interaction function includes:

[0134] It includes a robot body and an interactive device carrier. The robot body is equipped with multiple electrode plates, and the interactive device carrier is equipped with metal components corresponding to the electrode plates, including:

[0135] The recognition module is used to identify the user's current action based on the robot's camera module, and record the user's non-compliant actions by combining the comparison results of the current action and the standard action.

[0136] The bonding module is used to identify the calibration area corresponding to the non-compliant action, activate the electrode plate corresponding to the calibration area, and bond it with the corresponding metal part of the interactive device carrier.

[0137] The calibration module is used to control the robot body to perform standard actions and generate reminder messages.

[0138] Figure 3 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 2 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A robot behavior control method with human-robot interaction function, characterized by, The robot body and the interactive device carrier are provided with a plurality of electrode pieces and metal parts corresponding to the electrode pieces, respectively. The electrode pieces generate magnetism when powered on to interact with the metal parts. When the calibration part moves close to the metal part, the electrode pieces are attracted to the metal part due to the magnetism of the electrode pieces to achieve adhesion. The purpose of adhesion is to ensure that the electrode pieces are closely connected to the metal parts. The method comprises: identifying the current action of the user according to the shooting module of the robot body, and recording the non-compliant action of the user in combination with the comparison result of the current action and the standard action; determining the calibration part corresponding to the non-compliant action, and starting the electrode piece corresponding to the calibration part to adhere to the corresponding metal part of the interactive device carrier, comprising: identifying the actual position of the metal part corresponding to the electrode piece according to the image data collected by the shooting module; taking the current position of the electrode piece of the calibration part as the starting point and the actual position of the metal part as the ending point to generate an optimal path; controlling the robot body to move according to the optimal path, and starting the corresponding electrode piece to perform adhesion operation on the electrode piece of the calibration part and the metal part; controlling the robot body to perform the standard action, and generating a prompt information, comprising: controlling the robot body to perform the standard action, and acquiring the force value of the user at the position corresponding to each electrode piece based on the force feedback module; when the force value is not in the standard force value interval, generating a prompt information; when the force value is not in the standard force value interval, generating a prompt information, further comprising: when the force value is less than the interval minimum value, obtaining a first adjustment value corresponding to the difference between the interval minimum value and the force value, and adding the first adjustment value to the current current value of the corresponding electrode piece; when the force value is greater than the interval maximum value, obtaining a second adjustment value corresponding to the difference between the force value and the interval maximum value, and subtracting the second adjustment value from the current current value of the corresponding electrode piece; further comprising: obtaining the average adjustment value of the first adjustment value and / or the second adjustment value of each electrode piece after calibration, and determining the position corresponding to the electrode piece with the average adjustment value greater than a preset threshold as a high-error-prone position; calculating the mean of the historical current value of the high-error-prone position, and setting the current value of the corresponding electrode piece to the mean during the next interaction operation.

2. The method of claim 1, wherein the current action of the user is identified according to the shooting module of the robot body, and the non-compliant action of the user is recorded in combination with the comparison result of the current action and the standard action, comprising: obtaining image data collected by the shooting module, and extracting key points of the human body in the image data; determining the current action of the user according to the relative position and the current angle of each key point; calling the standard position and the standard angle of the preset point corresponding to the standard action, comparing the standard position and the standard angle with the relative position and the current angle respectively, and determining the current action with a comparison similarity less than a threshold as a non-compliant action.

3. The method of claim 1, wherein before the current action of the user is identified according to the shooting module of the robot body, and the non-compliant action of the user is recorded in combination with the comparison result of the current action and the standard action, further comprising: ​ ​ According to the shooting module, the actual height value of the user is identified, and the proportion relationship between the hand of the user and the height is obtained; According to the initial limb length and height of the robot body, the adjustment parameters of the limb parts of the robot body are calculated in combination with the proportion relationship and the height value, and the limb parts include the hand and the leg; According to the adjustment parameters, the limb parts of the robot body are adjusted, so that the height of the robot body is consistent with the height value of the user.

4. The method of claim 1, wherein, In the process of identifying the current action of the user according to the shooting module of the robot body, and recording the non-compliance action of the user in combination with the comparison result of the current action and the standard action, further comprising: Identify the key points of the human body in the multiple image frames collected by the shooting module, and calculate the displacement values of the same key points in adjacent frames; Calculate the average value of the multiple displacement values, determine the standard displacement value corresponding to the robot body, and obtain the adjustment coefficient according to the ratio of the average value and the standard displacement value; According to the product of the adjustment coefficient and the standard speed of the robot body, the standard speed of the robot body is adjusted.

5. The method of claim 1, wherein, In the process of identifying the current action of the user according to the shooting module of the robot body, and recording the non-compliance action of the user in combination with the comparison result of the current action and the standard action, further comprising: Obtain the proficiency level input by the user, and control the action of the robot body according to the preset speed corresponding to the proficiency level; Real-time acquisition of the current speed of the user, obtaining the speed difference value between the preset speed and the current speed, when the speed difference value is greater than the threshold value, then controlling the action of the robot body according to the preset speed corresponding to the proficiency level which is one level lower than the current proficiency level.

6. The method of claim 1, wherein, According to the preferred path, the calibration part of the robot body is controlled to move, comprising: Obtain the distance value between the corresponding electrode sheet and metal part in the calibration part during the movement; When the distance value is greater than the distance threshold value, the calibration part is controlled to move according to the preset speed; When the distance value is less than or equal to the distance threshold value, the preset speed is offset according to the product of the ratio of the distance value and the distance threshold value and the preset speed, and the calibration part is controlled to move according to the offset speed.

Images