Massage control method and massage chair

Abstract

The invention provides a massage control method, a massage chair and a controller applied to the massage chair, the massage chair at least comprises the controller, a massage chair main body, an image acquisition device and at least one massage arm.The method comprises the steps that if it is detected that a user sits stably, the image acquisition device is controlled to acquire a current image of the user; identifying a body model of the user according to the current image; and according to the body type model and the current massage mode, determining an action track sequence of each massage arm, and according to the action track sequence of each massage arm, controlling each massage arm to execute massage. The massage process can cover a wider massage area, the personalized massage path can be automatically generated according to the body shape of the user, the massage fitting degree and comfort degree are improved, the whole body surface of the user is massaged, meanwhile, the personalized adaptation capacity of the massage process is improved, and the user experience is improved. The massage experience of the user in the massage process is enhanced, and the personification of the massage process is improved.

Description

Technical Field

[0001] This application relates to the field of equipment control technology, and more specifically, to a massage control method and a massage chair. Background Technology

[0002] With the rapid development of science and technology and the improvement of people's living standards, massage equipment has developed rapidly due to demand and the advancement of intelligent and automated technologies.

[0003] Current massage chairs primarily massage the human body through fixedly installed components such as massage heads and airbags. In terms of working principle, the massage heads typically rely on motors to perform simple rotation and extension movements, while the airbags achieve compression massage through inflation and deflation.

[0004] However, existing massage chairs have shortcomings in terms of massage coverage area, personalization, and functional diversity. Specifically, regarding massage coverage area, due to the fixed positions of their massage components, they can only massage the back and waist areas, failing to directly target the chest, abdomen, and front thighs. This makes it difficult to effectively alleviate common problems in sedentary individuals such as abdominal muscle relaxation and chest muscle tension. In terms of personalization, the sensors in existing massage chairs are typically fixed in specific locations, such as back pressure sensors, and cannot dynamically scan the user's body shape. For users of different heights and body types, the massage position varies significantly, making it difficult to provide precise massage services based on individual differences and severely impacting the massage effect. Regarding functional diversity, traditional devices lack human-like operation capabilities and cannot simulate the fine massage techniques of human hands, such as spinal manipulation and acupressure. Furthermore, traditional massage chairs lack auxiliary functions such as object grabbing. If users need to use items such as mobile phones or water cups during the massage, they must interrupt the massage to retrieve them, greatly affecting the user experience. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing a massage control method and a massage chair, thereby solving the problems in the prior art regarding massage coverage area, personalized adaptation, and functional diversity.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, one embodiment of this application provides a massage control method applied to a controller of a massage chair. The massage chair includes at least: a controller, a massage chair body, an image acquisition device, and at least one massage arm. The image acquisition device and each of the massage arms are fixedly mounted on the massage chair body. The controller is connected to a massage device drive device in the massage chair body and a drive device in the massage arm. The drive device in the massage arm is connected to an end effector of the massage arm. The method includes:

[0008] If the user's posture is detected to be stable and seated, the image acquisition device is controlled to acquire the user's current image;

[0009] Based on the current image, identify the user's body shape model, which is used to indicate the user's key body points;

[0010] Based on the body model and the current massage mode, the motion trajectory sequence of each massage arm is determined, and each massage arm is controlled to perform massage according to the motion trajectory sequence of each massage arm. The motion trajectory sequence of the massage arm includes multiple motion sequences arranged in chronological order. Each motion sequence is used to indicate the position of the massage arm, the position of the end effector, and the massage parameters of the end effector at the corresponding time.

[0011] As one possible implementation, the image acquisition device includes: an infrared camera and a depth camera;

[0012] The control of the image acquisition device to acquire the user's current image includes:

[0013] The infrared camera and the depth camera are controlled to acquire infrared images and depth images, respectively.

[0014] The step of identifying the user's body shape model based on the current image includes:

[0015] Based on the depth image, a foreground image is extracted, which is used to indicate the area where the user and the main body of the massage chair are located;

[0016] Based on the infrared image, the user's human body region image is extracted;

[0017] The user's body shape model is identified based on the foreground image and the human body region image.

[0018] As one possible implementation, identifying the user's body shape model based on the foreground image and the human body region image includes:

[0019] The human body region image is mapped to the coordinate system of the foreground image to obtain the mapped human body region image;

[0020] Based on the mapped human body region image and the foreground image, determine the user's binary mask image;

[0021] The user's body shape model is determined based on the human body region image and the binary mask image.

[0022] As one possible implementation, determining the user's body shape model based on the human body region image and the binary mask image includes:

[0023] The user's body shape model is obtained based on the human body region image, the binary mask image, and the preset body shape recognition model. The preset body shape recognition model is obtained by training with sample human body images, which are images of sample users taken inside a massage chair.

[0024] As one possible implementation, determining the motion trajectory sequence of each massage arm based on the body shape model and the current massage mode includes:

[0025] Determine the current pose of the massage arm and the current pose of the end effector;

[0026] The motion trajectory sequence of the massage arm is calculated and obtained based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector.

[0027] As one possible implementation, the massage arm includes a plurality of joints connected in sequence, and the driving device in the massage arm includes: a drive motor corresponding to each joint;

[0028] The step of calculating and obtaining the motion trajectory sequence of the massage arm based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector includes:

[0029] Based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector, the motion trajectory sequence of the massage arm and the drive parameters of the drive motor corresponding to each joint during the movement of the massage arm according to the motion trajectory sequence are calculated and obtained.

[0030] As one possible implementation, the end effector includes: a robotic arm;

[0031] The method further includes:

[0032] Based on the current massage mode, the massage method and massage parameters of the robotic hand's wrist and / or each finger are calculated and obtained.

[0033] As one possible implementation, a six-axis force sensor is provided on the end effector, and the six-axis force sensor is located between the end effector and the end joint of the massage arm;

[0034] The method further includes:

[0035] The feedback contact force of the massage arm is monitored and obtained through the six-axis force sensor.

[0036] The need to adjust massage parameters is determined based on the feedback contact force.

[0037] As one possible implementation, before controlling each of the massage arms to perform massage according to the sequence of motion trajectories of each of the massage arms, the method further includes:

[0038] Obtain massage commands input by the user, wherein the massage commands include at least one of the following: massage mode, massage intensity, and massage area.

[0039] Secondly, another embodiment of this application provides a massage chair, which includes at least: a controller, a massage chair body, an image acquisition device, and at least one massage arm. The image acquisition device and each of the massage arms are fixedly mounted on the massage chair body. The controller is connected to a massage device drive device in the massage chair body and a drive device in the massage arm. The drive device in the massage arm is connected to an end effector of the massage arm. The controller is used to perform the steps of any of the methods described in the first aspect above.

[0040] The beneficial effects of this application are as follows: By installing at least one robotic arm in the massage chair and controlling an image acquisition device to capture the user's current image, the user's body shape model is identified based on the current image. Based on the body shape model and the current massage mode, the motion trajectory sequence of each massage arm is determined, and each massage arm is controlled to perform the massage according to the motion trajectory sequence. This allows the massage process to not only cover a wider massage area but also automatically generate personalized massage paths based on the user's body shape, improving massage fit and comfort. While achieving a full-body massage for the user, it enhances the personalized adaptation capability of the massage process and strengthens the user's massage experience. Furthermore, the end effectors of the massage arms can be quickly replaced to simulate various massage techniques, improving the anthropomorphism of the massage process and providing the user with a richer massage experience. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of the structure of a massage chair provided in an embodiment of this application;

[0043] Figure 2 A schematic diagram of a massage arm in a massage chair provided in an embodiment of this application;

[0044] Figure 3 Another structural schematic diagram of the massage arm in the massage chair provided in the embodiments of this application;

[0045] Figure 4 This is another structural schematic diagram of the massage arm in a massage chair provided in an embodiment of this application;

[0046] Figure 5 A flowchart of a massage control method provided in an embodiment of this application;

[0047] Figure 6 A flowchart illustrating the process of identifying a user's body shape model in a massage control method provided in an embodiment of this application;

[0048] Figure 7 Another flowchart for recognizing a user's body shape model in the massage control method provided in this application embodiment;

[0049] Figure 8 This is a flowchart illustrating the process of determining the motion trajectory sequence of each massage arm in the massage control method provided in this application embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0051] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0052] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0053] First, the structure of the massage chair provided in the embodiments of this application will be described. Figure 1 This is a schematic diagram of a massage chair provided in an embodiment of this application, with reference to... Figure 1 As shown, the massage chair includes at least: a controller 100, a massage chair body 200, an image acquisition device 300, and at least one massage arm 400. The image acquisition device 300 and each massage arm 400 are fixedly mounted on the massage chair body 200. The controller 100 is connected to the massage device drive device in the massage chair body and the drive device in the massage arm. The drive device in the massage arm is connected to the end effector of the massage arm.

[0054] The massage chair body 200 may be equipped with a massage function module, which includes multiple massage devices. The massage chair body 200 is also equipped with multiple massage device drive devices corresponding to each massage device. Each massage device drive device is connected to the controller 100. For example, the massage devices may include airbags, heat therapy, and vibration devices to provide users with a basic massage experience.

[0055] Optionally, the massage chair body 200 may also be equipped with a pressure sensor array, so that the controller 100 can determine the user's usage status based on the pressure detection results of the pressure sensor array.

[0056] The massage chair body 200 has base mounting interfaces for massage arms on its back and seat, so that the massage arms 400 can be connected to the massage chair body 200.

[0057] The massage chair body 200 can use a metal frame with an engineering plastic shell to ensure the overall stability of the massage arm 400 during movement, reduce the vibration amplitude, and provide a stable support platform for the massage arm 400.

[0058] For example, Figure 1Taking a massage chair including two massage arms 400 as an example, it can be understood that the number of massage arms can be adjusted according to the actual situation, and this application does not limit this.

[0059] The massage arm 400 can be a high-degree-of-freedom robotic arm, comprising multiple joints connected in sequence and an end effector. For example, the massage arm 400 can be a six-degree-of-freedom robotic arm, that is, based on the degree-of-freedom distribution of the human shoulder, elbow, and wrist joints.

[0060] For example, taking a robotic arm as the end effector, Figure 2 This is a schematic diagram of the structure of a massage arm in a massage chair provided in an embodiment of this application, with reference to... Figure 2 As shown, the massage arm 400 includes: a base 401, a plurality of arm joints 402 connected in sequence, and an end effector 403.

[0061] For example, continue to refer to Figure 2 As shown, the multiple arm joints 402 may include: a first arm joint, a second arm joint, a third arm joint, and a fourth arm joint. The first arm joint can drive the end effector 403 to rotate around its rotation axis. The second arm joint can drive the end effector 403 to rotate around its rotation axis. The third arm joint can drive the end effector 403 to rotate around its rotation axis. The rotation axes of the first arm joint, the second arm joint, the third arm joint, and the fourth arm joint are perpendicular to each other.

[0062] For example, the end effector can be configured with different massage components according to different massage needs. The massage component can be at least one of the following: a robotic arm, a massage hammer, a physiotherapy patch heating device, a low-frequency electrical stimulation device, a hot and cold alternating massage component, a vibration physiotherapy device, and a laser irradiation device, etc.

[0063] For example, Figure 3 This is another structural schematic diagram of the massage arm in the massage chair provided in the embodiments of this application, referred to... Figure 3 As shown, the end effector 403 can be a detachable massage hammer with adjustable vibration frequency, and can be equipped with a roller massage head and biomimetic protrusions on the surface, thereby providing users with a variety of massage methods.

[0064] The robotic hand can be designed to mimic the five-finger structure of a human hand, with each finger having three degrees of freedom. The fingertip integrates a tactile sensor with a resolution of 1mm and a maximum gripping force of 20N. It can grip objects weighing ≤2kg and provide massage and assisted gripping functions.

[0065] Optionally, the massage arm 400 also includes drive devices corresponding to each arm joint 402 and a drive device corresponding to the end effector 403. For example, the drive devices in the massage arm 400 can be harmonic reducers and drive motors to improve positioning accuracy during the massage process. The drive devices corresponding to each arm joint 402 and the end effector 403 are both connected to the controller 100.

[0066] Optionally, the massage arm 400 also includes joint angle sensors corresponding to each arm joint 402, so that the controller 100 can determine the pose of the end effector in three-dimensional space.

[0067] Optionally, Figure 4 This is another structural schematic diagram of the massage arm in the massage chair provided in the embodiments of this application, referred to... Figure 4 As shown, the massage arm 400 also includes a six-axis force sensor 404, which is located between the end effector 403 and the end joint 402 of the massage arm 400 to detect feedback contact force during massage.

[0068] Optionally, the image acquisition device 300 can be a sensor assembly fixedly mounted on the top of the massage chair body 200. Exemplarily, it may include at least one of the following: an infrared camera, a depth camera, a red-green-blue camera (RGB camera), a thermal imaging camera, and a time-of-flight camera (TOF camera).

[0069] The controller 100 is used to execute the steps of the massage control method provided in the embodiments of this application to provide massage to the user.

[0070] For example, the installation process of the massage chair provided in this application embodiment may include: the base of the massage arm 400 is connected to the base mounting interface of the massage arm on the massage chair body 200 by high-strength bolts, and the levelness is calibrated. The circuit of the harmonic reducer and the drive motor in the joint of the massage arm 400 is connected to the controller 100 along the internal wire groove of the massage arm, and the data line of the image acquisition device 300 on the top of the massage chair body 200 is connected to the controller 100.

[0071] The massage control method provided in this application will be described in detail below with reference to several embodiments.

[0072] Figure 5 A flowchart of a massage control method provided in an embodiment of this application is shown below. Figure 5 As shown, the executing entity of this method can be the controller in the massage chair mentioned above, and the method includes:

[0073] S501. If the user's posture is detected to be stable and seated, the image acquisition device is controlled to acquire the user's current image.

[0074] Optionally, the controller 100 in the massage chair can detect the user's posture in real time. When it detects that the user is sitting stably, it controls the image acquisition device 300 to acquire the user's current image.

[0075] For example, the controller 100 can control the image acquisition device 300 to continuously acquire multiple frames of images of the user at a preset frequency, and determine the image with the most stable body position of the user from the multiple frames as the current image.

[0076] Here, "user" refers to the person currently using the massage chair, and "user posture" refers to the geometric state of the user's body while sitting on the massage chair. Stable sitting can be understood as the user sitting fully with their back against the chair back in an ergonomically standard posture, with a stable center of gravity and no limbs hanging off the edge or moving significantly.

[0077] Depending on the image acquisition device, the current image can be at least one of the following: infrared image, depth image, RGB image, thermal imaging image, and TOF image.

[0078] In the first example, the user's posture can be determined to be stable by the pressure detection results from the pressure sensor array in the massage chair body 200. Specifically, the pressure detection results can be judged, and if the pressure detection results meet the preset pressure detection conditions, it can be determined that the user's posture is stable.

[0079] The preset pressure check conditions can be determined based on at least one of the following: pressure coverage area, pressure value, left-right symmetry of pressure, pressure duration, and pressure fluctuation. For example, if the pressure detection result indicates that the current pressure covers the normal sitting posture area, and the total pressure is greater than a preset pressure threshold, the left-right symmetry of the pressure is greater than a preset symmetry threshold, the duration of the pressure is greater than a preset duration threshold, and the pressure fluctuation value is less than a preset fluctuation threshold, then the user's posture can be determined to be stable sitting.

[0080] In the second example, the image acquired by the image acquisition device 300 can also be used to determine whether the user's posture is stable. Specifically, the image acquired by the image acquisition device 300 can be input into a pre-trained image posture recognition model for recognition to determine whether the user's posture is stable.

[0081] In the third example, the user's posture can also be determined as a stable sitting position by the feedback contact force from the aforementioned six-axis force sensor. Specifically, the robotic arm can be controlled to contact the user's legs or waist with a preset force, and the feedback contact force can be obtained through the six-axis force sensor. If the fluctuation range of the feedback force value is within a preset threshold range within a preset time period, it can be determined that the user's posture is stable.

[0082] In the fourth example, the stability of the user's posture can be determined based on the pressure detection results from the pressure sensor array, the image acquired by the image acquisition device 300, and the feedback contact force from the six-axis force sensor. Specifically, the pressure detection results, image, and feedback contact force can be fused and combined with preset weights to calculate the sitting confidence level. If the sitting confidence level is greater than a preset sitting threshold, the user's posture can be determined to be stable.

[0083] S502. Based on the current image, identify the user's body shape model.

[0084] Optionally, after obtaining the current image, image processing can be performed on the current image to identify the user's body shape model.

[0085] For example, the current image can be input into a pre-trained body shape recognition model for body shape recognition processing to identify the user's body shape model. The pre-trained body shape recognition model can be implemented based on an object detection model.

[0086] The body model can be understood as a three-dimensional geometric model of the human body, which is used to indicate the key points of the user's body. These key points include at least the following body features: height, shoulder width, chest circumference, hip circumference, spinal curvature, sitting posture, acromion, spinal nodes, hip joints, and knee joints.

[0087] It is worth noting that, depending on the device mode and the precision of the image acquisition device, the current image can be obtained at different resolutions. The accuracy of the body shape model obtained will also vary depending on the resolution of the current image.

[0088] For example, when the current image is a high-resolution image, the body model is used to indicate the user's acupoints and key body features such as height, shoulder width, chest circumference, hip circumference, spinal curvature, sitting posture, acromion, spinal nodes, hip joint, and knee joint. Among them, acupoints may include, for example, acromion, Dazhui (GV14), Mingmen (GV4).

[0089] For example, when the current image is a low-resolution image, the body model is used to indicate key body features of the user, such as height, shoulder width, chest circumference, hip circumference, spinal curvature, sitting posture, acromion, spinal nodes, hip joint, and knee joint.

[0090] S503. Based on the body model and the current massage mode, determine the motion trajectory sequence of each massage arm, and control each massage arm to perform massage according to the motion trajectory sequence of each massage arm.

[0091] Optionally, after obtaining the body model, the motion trajectory of each massage arm can be planned according to the body model and the current massage mode, the motion trajectory sequence of each massage arm can be determined, and each massage arm can be controlled to perform massage according to the motion trajectory sequence of each massage arm.

[0092] The current massage mode refers to the user's current massage task mode, including the current massage goal, path planning parameters, technique combination, intensity setting, and safety control strategy.

[0093] The motion trajectory sequence of the massage arm includes multiple motion sequences arranged in chronological order. Each motion sequence is used to indicate the pose of the massage arm, the pose of the end effector, and the massage parameters of the end effector at the corresponding moment.

[0094] The term "pose" includes both position and orientation. The pose of the massage arm at a given moment refers to its spatial position and orientation. The pose of the end effector refers to the position and angle of its point of action on the target body part at a given moment. The massage parameters of the end effector can include its massage intensity, duration, and speed.

[0095] For example, users can interact with the massage chair to enable the controller to determine the current massage mode. Specifically, this interaction can be achieved through an interactive panel on the massage chair, voice commands, or an application on a mobile device.

[0096] For example, the initial motion trajectory sequence of each massage arm can be generated first according to the current massage mode, and the initial motion trajectory sequence of each massage arm can be optimized by using a body model to obtain the motion trajectory sequence of each massage arm.

[0097] For example, the motion trajectory sequence of each massage arm can be traversed, and the drive device in each massage arm can be driven sequentially according to the motion sequence of each massage arm to control each massage arm to perform massage.

[0098] For example, the motion trajectory sequence of the robotic arm can be traversed, and for the current motion sequence traversed, the feedback contact force from the six-axis force sensor can be obtained. Based on the feedback contact force, the current motion sequence can be optimized to generate an updated motion sequence. Based on the updated motion sequence, the drive device in the massage arm can be driven to control the robotic arm to perform massage.

[0099] In this embodiment, by installing at least one robotic arm in the massage chair and controlling an image acquisition device to capture the user's current image, the system identifies the user's body shape model based on the image. Then, based on the body shape model and the current massage mode, it determines the motion trajectory sequence of each massage arm and controls each arm to perform the massage according to this sequence. This allows the massage process to not only cover a wider massage area but also automatically generate personalized massage paths based on the user's body shape, improving the massage fit and comfort. While providing a full-body massage, it enhances the personalized adaptation of the massage process, thus improving the user's massage experience. Furthermore, the end effectors of the massage arms can be quickly replaced to simulate various massage techniques, increasing the anthropomorphism of the massage process and providing the user with a richer massage experience.

[0100] As one possible implementation, the image acquisition device includes an infrared camera and a depth camera. The step S501 above, controlling the image acquisition device to acquire the user's current image, includes:

[0101] The infrared camera and depth camera are controlled separately to acquire infrared and depth images.

[0102] For example, the controller can send acquisition commands to the infrared camera and the depth camera, and receive image frames with their respective timestamps returned by the infrared camera and the depth camera, and match them according to the timestamps to obtain the infrared image and the depth image with the same timestamp as the current image.

[0103] For example, the infrared camera can be set as the main camera and the depth camera as the slave camera. The controller sends a capture command to the main camera, the main camera sends a synchronization signal, and the slave camera starts capturing frames simultaneously after receiving the synchronization signal. The controller receives the synchronization signal and records the timestamp, thus obtaining the infrared image and depth image at the same timestamp as the current image.

[0104] As one possible implementation method, Figure 6 A flowchart illustrating the process of identifying a user's body shape model in the massage control method provided in this application embodiment, with reference to... Figure 6 As shown, in step S502 above, recognizing the user's body shape model based on the current image includes:

[0105] S601. Extract the foreground image based on the depth image.

[0106] Optionally, the depth image can be filtered and denoised first to remove isolated noise points, filter out regions that are irrelevant to distance, and preserve edge details, resulting in a denoised depth image. Specifically, isolated noise points can be removed by median filtering, edge details can be preserved by bilateral filtering, and regions that are irrelevant to distance can be filtered by preset maximum and minimum depth thresholds. For example, the maximum depth threshold can be 150cm and the minimum depth threshold can be 50cm.

[0107] Optionally, an initial foreground image can be obtained by extracting an image from the denoised depth image using a preset depth range threshold. For example, the preset depth range threshold can be 60cm ≤ depth ≤ 150cm.

[0108] Alternatively, the initial foreground image can be processed using connected component analysis to retain the largest connected region in the initial foreground image, thus obtaining the foreground image.

[0109] The foreground image is used to indicate the area where the user and the main body of the massage chair are located. The foreground image can represent three-dimensional spatial information related to the user, such as the user's body outline or posture.

[0110] S602. Based on the infrared image, extract the image of the user's human body area.

[0111] Optionally, the infrared image can be extracted using a threshold segmentation method to obtain the user's human body region image. Specifically, a temperature range threshold can be set based on the human body's temperature range, and the infrared image can be extracted using this temperature range threshold to obtain the human body region image. For example, the temperature range threshold could be 30℃~38℃.

[0112] Alternatively, the infrared image can be input into a pre-trained thermal target detection model for target detection, thereby extracting the user's human body region image. The pre-trained thermal target detection model can be implemented based on a lightweight CNN model.

[0113] Among them, the human body region image can be represented as a binary mask of the human body region.

[0114] S603. Based on the foreground image and the human body region image, identify the user's body shape model.

[0115] Optionally, after obtaining the foreground image and the human body region image, the foreground image and the human body region image can be overlaid to identify the user's body shape model.

[0116] The foreground image is extracted from the depth image, and the human body region image of the user is extracted from the infrared image. Based on the foreground image and the human body region image, the user's body shape model can be identified. The fusion of depth image and infrared image can enhance the robustness of human body boundary detection and build a more accurate body shape model. It also has the advantages of strong applicability and high environmental adaptability.

[0117] As one possible implementation method, Figure 7 Another flowchart for identifying the user's body shape model in the massage control method provided in this application embodiment is shown below. Figure 7 As shown, in step S603 above, recognizing the user's body shape model based on the foreground image and the human body region image includes:

[0118] S701. Map the human body region image to the coordinate system of the foreground image to obtain the mapped human body region image.

[0119] Optionally, the human body region image can be mapped to the coordinate system of the foreground image using the extrinsic matrix of the infrared camera and the intrinsic and extrinsic matrices of the depth image, thus obtaining the mapped human body region image.

[0120] For example, the pixel coordinates in the human body region image can be transformed to the three-dimensional coordinate system of the infrared camera to obtain the three-dimensional point set of the human body region image in the infrared camera coordinate system.

[0121] For example, the three-dimensional point set of the human body region image in the infrared camera coordinate system is mapped to the coordinate system of the foreground image by the extrinsic parameter matrix of the infrared camera and the extrinsic parameter matrix of the depth image, so as to obtain the three-dimensional point set of the human body region image in the coordinate system of the foreground image, which is used as the mapped human body region image.

[0122] S702. Determine the user's binary mask image based on the mapped human body region image and the foreground image.

[0123] Optionally, bitwise operations can be performed on the mapped human body region image and the foreground image according to pixels to obtain the user's binary mask image.

[0124] S703. Determine the user's body shape model based on the human body region image and the binary mask image.

[0125] Optionally, after obtaining the human body region image and the binary mask image, the binary mask image can be processed by an edge detection algorithm to extract the human body contour, and based on the human body contour, the user's height, shoulder width, chest circumference, hip circumference, key point coordinates and other body shape data can be calculated.

[0126] Optionally, the human body region image is converted into a three-dimensional point cloud, and the three-dimensional point cloud is cropped in combination with the user's body shape data to obtain the human body region point cloud, thereby obtaining the user's body shape model.

[0127] Alternatively, the user's body shape model can be determined by using the human body region image and the binary mask image through a pre-trained model.

[0128] By mapping the human body region image to the coordinate system of the foreground image, a mapped human body region image is obtained. Based on the mapped human body region image and the foreground image, the user's binary mask image is determined. Thus, based on the human body region image and the binary mask image, the user's body shape model is determined. This can reduce the computational resource overhead in the body shape model generation process while improving the accuracy and robustness of body shape modeling, thereby enhancing the adaptability to complex environments and enhancing the anthropomorphic massage experience.

[0129] As one possible implementation, in S703 above, determining the user's body shape model based on the human body region image and the binary mask image includes:

[0130] The user's body shape model is obtained based on the human body region image, the binary mask image, and the preset body shape recognition model.

[0131] Optionally, the human body region image and the binary mask image can be input into a pre-trained body shape recognition model to obtain the user's body shape model.

[0132] The preset body shape recognition model is trained using sample human images, which are images taken of sample users inside the massage chair. These sample human images can include both infrared and depth images of the sample human body.

[0133] By using human body region images, binary mask images, and preset body shape recognition models, the user's body shape model is obtained, enabling more refined body shape features and thus accurate localization of human body regions.

[0134] As one possible implementation method, Figure 8 A flowchart illustrating the determination of the motion trajectory sequence of each massage arm in the massage control method provided in this application embodiment, with reference to... Figure 8 As shown, in S503 above, the motion trajectory sequence of each massage arm is determined based on the body model and the current massage mode, including:

[0135] S801, Determine the current position of the massage arm and the current position of the end effector.

[0136] Optionally, the joint angles of each joint in the massage arm can be obtained by the joint angle sensor in the massage arm, and the current position of the massage arm and the current pose of the end effector can be calculated by combining the joint angles of the massage arm with the forward kinematics model and the intermediate link transformation matrix.

[0137] The current pose of the massage arm refers to its position and orientation in space at the current moment. The current pose of the end effector refers to the position and angle of the point of action of the end effector on the target human body part at the current moment.

[0138] S802. Calculate and obtain the motion trajectory sequence of the massage arm based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector.

[0139] Optionally, after obtaining the current pose of the massage arm and the current pose of the end effector, trajectory planning can be performed based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector to calculate and obtain the motion trajectory sequence of the massage arm.

[0140] For example, the location of each massage point when massaging the user can be determined first by using the body model and the current massage mode. After obtaining the location of each massage point, topological relationship modeling can be performed to obtain multiple massage areas, the priority order of each massage area, and the massage method of each massage area.

[0141] Specifically, the body shape model and the current massage mode can be input into a pre-trained massage point recognition model to identify the location of each massage point. The pre-trained massage point recognition model can be trained based on a human acupoint atlas.

[0142] For example, after obtaining multiple massage areas, the priority order of each massage area, and the massage method of each massage area, a path planning algorithm can be used to plan the multiple massage areas, the priority order of each massage area, and the massage method of each massage area to generate an initial motion trajectory sequence.

[0143] For example, after obtaining the initial motion trajectory sequence, the initial motion trajectory sequence, the current pose of the massage arm, and the current pose of the end effector can be solved by inverse kinematics algorithm to convert the initial motion trajectory into joint angles. Then, the joint angles are smoothed, obstacle avoidance and safety are checked by a preset verification algorithm to obtain the motion trajectory sequence.

[0144] Specifically, if the angles of each joint meet the preset verification algorithm, the initial motion trajectory sequence can be used as the motion trajectory sequence; if the angles of each joint do not meet the preset verification algorithm, the angles of each joint can be corrected by the trajectory replanning algorithm.

[0145] The preset verification algorithms may include spline interpolation and geometric obstacle avoidance. The trajectory replanning algorithm may be, for example, the MPC (Model Predictive Control) algorithm.

[0146] By using body shape model, current massage mode, current pose of massage arm and current pose of end effector, the motion trajectory sequence of massage arm is calculated and obtained, which can provide precise and personalized massage according to individual user differences, thereby enhancing the user's massage experience.

[0147] As one possible implementation, the massage arm includes multiple joints connected in sequence, and the driving device in the massage arm includes a drive motor corresponding to each joint. In step S802 above, based on the body shape model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector, the motion trajectory sequence of the massage arm is calculated and obtained, including:

[0148] Based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector, the motion trajectory sequence of the massage arm and the drive parameters of the drive motor corresponding to each joint during the movement of the massage arm according to the motion trajectory sequence are calculated and obtained.

[0149] Optionally, multiple massage areas, the priority order of each massage area, and the massage method of each massage area can be identified first through body shape model, current massage mode, and pre-trained massage point recognition model.

[0150] Optionally, multiple massage areas can be converted into spatial motion trajectories of the massage arm and end effector using path interpolation methods, and a time dimension can be added to generate a temporal pose trajectory sequence. This temporal pose trajectory sequence indicates the trajectory sequence of the massage arm and end effector's pose changing over time during massage.

[0151] Optionally, after obtaining the time pose trajectory sequence, the time pose trajectory sequence, the current pose of the massage arm, and the current pose of the end effector can be solved by inverse kinematics algorithm to convert the time pose trajectory sequence into the position and angle of each joint at different times. The position and angle of each joint at different times are then smoothed, obstacle avoidance and safety are verified by a preset verification algorithm to obtain the motion trajectory sequence.

[0152] Specifically, if the position and angle of each joint at different times meet the preset verification algorithm, the motion trajectory sequence can be obtained based on the time pose trajectory sequence and the position and angle of each joint at different times. If the position and angle of each joint at different times do not meet the preset verification algorithm, the position and angle of each joint at different times can be corrected by the trajectory replanning algorithm, or the time pose trajectory sequence can be redefined.

[0153] The preset verification algorithms may include spline interpolation and geometric obstacle avoidance. The trajectory replanning algorithm can be the MPC predictive control algorithm.

[0154] Optionally, after obtaining the motion trajectory sequence, the driving parameters of each motion sequence in the sequence are calculated using a pre-built dynamic model. These driving parameters include joint velocity, joint torque, and joint angle. The pre-built dynamic model can be implemented based on the Lagrange equations or the Newton-Euler method.

[0155] By using body model, current massage mode, current pose of massage arm, and current pose of end effector, the motion trajectory sequence of massage arm and the drive parameters of the drive motor corresponding to each joint during the movement of massage arm according to the motion trajectory sequence are calculated. This enables precise trajectory control and multi-degree-of-freedom collaborative massage based on individual differences during the massage process, thereby enriching the user's massage experience.

[0156] As one possible implementation, the end effector includes a robotic arm. The method also includes:

[0157] Based on the current massage mode, calculate and obtain the massage method and massage parameters for the robotic hand's wrist and / or each finger.

[0158] Optionally, based on the current massage mode and the mapping relationship between the current massage mode and the end effector's motion, the massage method and massage parameters of the robotic hand's wrist and / or each finger can be determined when the end effector is a robotic hand. This allows for switching to the corresponding massage technique in different massage modes and precise control of the output force and motion trajectory.

[0159] The massage modes for the robotic arm's wrist indicate the movement patterns of the wrist, such as rotation, flexion, and extension. The massage parameters for the robotic arm's wrist include the force, frequency, and temperature of the movement. Similarly, the massage modes for each finger indicate the movement patterns of the individual fingers, such as opening and closing, pressing, and kneading. The massage parameters for each finger include the force, frequency, and temperature of the movement.

[0160] As one possible implementation, a six-axis force sensor is mounted on the end effector, located between the end effector and the end joint of the massage arm. The method also includes:

[0161] The feedback contact force of the massage arm is monitored and obtained by a six-axis force sensor, and the massage parameters are adjusted based on the feedback contact force.

[0162] Optionally, during the massage, the feedback contact force of the massage arm can be monitored and obtained in real time by a six-axis force sensor, and the feedback contact force can be compared with a preset contact force threshold to determine whether the massage parameters need to be adjusted. This allows for dynamic adjustment during the massage through tactile perception.

[0163] For example, when the feedback contact force is greater than a preset contact force threshold, the massage intensity can be gradually reduced according to a preset intensity attenuation rule. When the feedback contact force is less than the preset contact force threshold, the massage intensity can be gradually increased according to a preset intensity enhancement rule.

[0164] As one possible implementation, before controlling each massage arm to perform massage according to the motion trajectory sequence of each massage arm in the above-mentioned S503, it also includes:

[0165] Get the massage commands input by the user.

[0166] Optionally, before controlling each massage arm to perform a massage according to the sequence of motion trajectories of each massage arm, massage commands input by the user can be obtained. These massage commands may include at least one of the following: massage mode, massage intensity, and massage area.

[0167] Optionally, after obtaining the massage command input by the user, the massage arm can be controlled to perform massage according to the massage command input by the user and the motion trajectory sequence of each massage arm.

[0168] For example, taking a massage instruction input by the user that includes a massage area as an example, the motion sequence of each massage arm related to the massage area can be fine-tuned according to the massage area, and each massage arm can be controlled to perform massage based on the fine-tuned motion trajectory sequence.

[0169] Specifically, fine-tuning the motion sequence related to the massage area in the motion trajectory sequence of each massage arm may include at least one of the following: adjusting the massage duration of the motion sequence related to the massage area in the motion trajectory sequence of each massage arm, adjusting the massage intensity of the motion sequence related to the massage area in the motion trajectory sequence of each massage arm, and adjusting the massage speed of the motion sequence related to the massage area in the motion trajectory sequence of each massage arm.

[0170] For example, taking a massage instruction input by the user that includes massage intensity as an example, the massage intensity corresponding to each motion sequence in the motion trajectory sequence of each massage arm can be adjusted according to the massage intensity, and each massage arm can be controlled to perform massage based on the adjusted motion trajectory sequence.

[0171] By acquiring the massage commands input by the user, the massage process can not only automatically generate personalized massage paths based on the user's body shape, improving the fit and comfort of the massage, but also adjust according to the user's subjective wishes, further enhancing the user's massage experience.

[0172] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A massage control method, characterized in that, A controller for a massage chair, the massage chair comprising at least: a controller, a massage chair body, an image acquisition device, and at least one massage arm, wherein the image acquisition device and each of the massage arms are fixedly mounted on the massage chair body, the controller is connected to a massage device drive device in the massage chair body and a drive device in the massage arm, and the drive device in the massage arm is connected to an end effector of the massage arm, the method comprising: If the user's posture is detected to be stable and seated, the image acquisition device is controlled to acquire the user's current image; Based on the current image, identify the user's body shape model, which is used to indicate the user's key body points; Based on the body model and the current massage mode, the motion trajectory sequence of each massage arm is determined, and each massage arm is controlled to perform massage according to the motion trajectory sequence of each massage arm. The motion trajectory sequence of the massage arm includes multiple motion sequences arranged in chronological order. Each motion sequence is used to indicate the position of the massage arm, the position of the end effector, and the massage parameters of the end effector at the corresponding time.

2. The massage control method according to claim 1, characterized in that, The image acquisition device includes: an infrared camera and a depth camera; The control of the image acquisition device to acquire the user's current image includes: The infrared camera and the depth camera are controlled to acquire infrared images and depth images, respectively. The step of identifying the user's body shape model based on the current image includes: Based on the depth image, a foreground image is extracted, which is used to indicate the area where the user and the main body of the massage chair are located; Based on the infrared image, the user's human body region image is extracted; The user's body shape model is identified based on the foreground image and the human body region image.

3. The massage control method according to claim 2, characterized in that, The step of identifying the user's body shape model based on the foreground image and the human body region image includes: The human body region image is mapped to the coordinate system of the foreground image to obtain the mapped human body region image; Based on the mapped human body region image and the foreground image, determine the user's binary mask image; The user's body shape model is determined based on the human body region image and the binary mask image.

4. The massage control method according to claim 3, characterized in that, The step of determining the user's body shape model based on the human body region image and the binary mask image includes: The user's body shape model is obtained based on the human body region image, the binary mask image, and the preset body shape recognition model. The preset body shape recognition model is obtained by training with sample human body images, which are images of sample users taken inside a massage chair.

5. The massage control method according to claim 1, characterized in that, The step of determining the motion trajectory sequence of each massage arm based on the body shape model and the current massage mode includes: Determine the current pose of the massage arm and the current pose of the end effector; The motion trajectory sequence of the massage arm is calculated and obtained based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector.

6. The massage control method according to claim 5, characterized in that, The massage arm includes multiple joints connected in sequence, and the driving device in the massage arm includes: a drive motor corresponding to each joint; The step of calculating and obtaining the motion trajectory sequence of the massage arm based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector includes: Based on the body model, the current massage mode, the current pose of the massage arm, and the current pose of the end effector, the motion trajectory sequence of the massage arm and the drive parameters of the drive motor corresponding to each joint during the movement of the massage arm according to the motion trajectory sequence are calculated and obtained.

7. The massage control method according to claim 6, characterized in that, The end effector includes: a robotic arm; The method further includes: Based on the current massage mode, the massage method and massage parameters of the robotic hand's wrist and / or each finger are calculated and obtained.

8. The massage control method according to claim 1, characterized in that, The end effector is equipped with a six-axis force sensor, which is located between the end effector and the end joint of the massage arm. The method further includes: The feedback contact force of the massage arm is monitored and obtained through the six-axis force sensor. The need to adjust massage parameters is determined based on the feedback contact force.

9. The massage control method according to claim 1, characterized in that, Before controlling each massage arm to perform massage according to the movement trajectory sequence of each massage arm, the method further includes: Obtain massage commands input by the user, wherein the massage commands include at least one of the following: massage mode, massage intensity, and massage area.

10. A massage chair, said massage chair comprising at least: The massage chair includes a controller, a massage chair body, an image acquisition device, and at least one massage arm. The image acquisition device and each of the massage arms are fixedly mounted on the massage chair body. The controller is connected to a massage device drive device in the massage chair body and a drive device in the massage arm. The drive device in the massage arm is connected to an end effector of the massage arm. The controller is used to execute the steps of the massage control method as described in any one of claims 1 to 9.

Images