# US 12,594,461 B2 · User exercise detection method, robot and computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,594,461 B2 - Document ID: US12594461B2 - Status: Granted - Kind: B2 - Application number: 18/209,425 - Filed: 2023-06-13 - Published: 2024-12-19 - Granted: 2026-04-07 - Earliest claimed: 2023-06-13 - Assignees: Ubtech Robotics Corp Ltd - Applicants: Ubtech Robotics Corp Ltd - Inventors: Sheryl Suet Ying Chau; Robert Malate; Chengkun Zhang; Huan Tan - Web page: https://patentgrep.com/patent/US12594461B2 ## CPC - A61B 5/1116: {Determining posture transitions} - A63B 24/0062: {Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance} - A63B 24/0087: {Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load} - A63B 2024/0093: {the load of the exercise apparatus being controlled by performance parameters, e.g. distance or speed} - A63B 2220/18: Inclination, slope or curvature - A63B 2220/40: Acceleration - A63B 2220/807: Photo cameras - A63B 2230/62: posture - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - A63B: APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT (apparatus for passive exercising, massage A61H) ## Abstract A user exercise detection method applicable in a robot includes: obtaining first measurement data from at least one inertial measurement unit (IMU) sensor that is arranged at a designated body part of the user, and detecting a posture of the user relative to the robot based on the first measurement data; obtaining second measurement data from the at least one IMU sensor, and determining whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting the threshold parameter according to the exercise data. ## Claims ### Claim 1 A computer-implemented user exercise detection method applicable in a robot, the method comprising: providing the robot comprises: a processor, and at least one inertial measurement unit (IMU) sensor arranged at a designated body part of a user; obtaining, through the at least one IMU sensor, first measurement data, and detecting, through the processor, a posture of the user relative to the robot based on the first measurement data; obtaining, through the at least one IMU sensor, second measurement data, and determining, through the processor, whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting, through the processor, control parameters of the robot and the threshold parameter according to the exercise data, and controlling the robot according to the adjusted control parameters. ### Claim 2 (depends on 1) The method of claim 1, further comprising, after determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data, in response to no detection of the exercise, repeating obtaining the second measurement data from the at least one IMU sensor; in response to an amount of times of the exercise not being detected reaching a preset value, outputting a first prompt message through an interaction interface of the robot to prompt the user to modify the threshold parameter; and modifying the threshold parameter based on an input from the user through the interaction interface. ### Claim 3 (depends on 2) The method of claim 2, further comprising, before obtaining the second measurement data from the at least one IMU sensor, obtaining personal information and a training session of the user through the interaction interface; and obtaining a threshold parameter matching the personal information and the training session of the user as the preset threshold parameter by searching a database according to the personal information and the training session of the user. ### Claim 4 (depends on 3) The method of claim 3, further comprising: generating a training report according to the personal information and the training session of the user, the threshold parameter and the exercise data, and sending the training report to a cloud server for analysis; and obtaining an analysis result output by the cloud server, and adjusting the threshold parameter according to the analysis result. ### Claim 5 (depends on 1) The method of claim 1, wherein the at least one IMU sensor is two in number, the two IMU sensors are respectively arranged on two legs of the user, and the first measurement data comprises two roll angles, two pitch angles and two yaw angles. ### Claim 6 (depends on 5) The method of claim 5, wherein the posture is a standing posture, and the second measurement data is the two pitch angles; determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data comprises: determining whether knee flexion angles of the user exceed a preset threshold according to the two pitch angles; and in response to the knee flexion angles of the user exceeding the preset threshold, determining that the exercise of the user corresponding to standing posture has been detected. ### Claim 7 (depends on 5) The method of claim 5, wherein the posture is a sitting posture, and the second measurement data is the two pitch angles; determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data comprises: determining whether a lifting height of a leg of the user exceeds a preset threshold according to the two pitch angles; and in response to the lifting height of the leg of the user exceeds the preset threshold, determining that the exercise of the user corresponding to sitting posture has been detected. ### Claim 8 (depends on 1) The method of claim 1, wherein the exercise data comprises a range of motion, a duration of the exercise, and sets/repetitions and a completion rate of the exercise; wherein the robot further comprises: a wheeled base, a seat, and a main body positioned on the wheeled base, the seat is connected to the main body and disposed above the wheeled base, and the main body comprises at least one handle; and wherein the control parameters comprise at least one of a movement speed, a height of the at least one handle, and a height of the seat. ### Claim 9 (depends on 1) The method of claim 1, further comprising, before obtaining the second measurement data from the at least one IMU sensor, and determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data, outputting second prompt information through an interaction interface of the robot to prompt the user to maintain a specified posture for a preset duration; and calibrating the at least one IMU sensor. ### Claim 10 (depends on 9) The method of claim 9, further comprising, after obtaining the first measurement data from the at least one IMU sensor, and detecting the posture of the user relative to the robot based on the first measurement data, a) obtaining feature data of a reference posture; b) capturing one or more pictures of the user through a camera system on the robot, and extracting feature data of the posture based on the one or more pictures; c) comparing the extracted feature data with the feature data of the reference posture to obtain a similarity between the extracted feature data and the feature data of the reference posture; and d) in response to the similarity not greater than a preset value, outputting third prompt information through the interaction interface to prompt the user to adjust the posture, and returning to step b). ### Claim 11 A robot comprising: at least one inertial measurement unit (IMU) sensor arranged at a designated body part of a user; one or more processors; and a memory coupled to the one or more processors, the memory storing programs that, when executed by the one or more processors, cause performance of operations comprising: obtaining first measurement data through the at least one IMU sensor, and detecting a posture of the user relative to the robot based on the first measurement data; obtaining second measurement data through the at least one IMU sensor, and determining whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting control parameters of the robot and the threshold parameter according to the exercise data, and controlling the robot according to the adjusted control parameters. ### Claim 12 (depends on 11) The robot of claim 11, wherein the operations further comprise, after determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data, in response to no detection of the exercise, repeating obtaining the second measurement data from the at least one IMU sensor; in response to an amount of times of the exercise not being detected reaching a preset value, outputting a first prompt message through an interaction interface of the robot to prompt the user to modify the threshold parameter; and modifying the threshold parameter based on an input from the user through the interaction interface. ### Claim 13 (depends on 12) The robot of claim 12, wherein the operations further comprise, before obtaining the second measurement data from the at least one IMU sensor, obtaining personal information and a training session of the user through the interaction interface; and obtaining a threshold parameter matching the personal information and the training session of the user as the preset threshold parameter by searching a database according to the personal information and the training session of the user. ### Claim 14 (depends on 13) The robot of claim 13, wherein the operations further comprise: generating a training report according to the personal information and the training session of the user, the threshold parameter and the exercise data, and sending the training report to a cloud server for analysis; and obtaining an analysis result output by the cloud server, and adjusting the threshold parameter according to the analysis result. ### Claim 15 (depends on 11) The robot of claim 11, wherein the at least one IMU sensor is two in number, the two IMU sensors are respectively arranged on two legs of the user, and the first measurement data comprises two roll angles, two pitch angles and two yaw angles. ### Claim 16 (depends on 15) The robot of claim 15, wherein the posture is a standing posture, and the second measurement data is the two pitch angles; determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data comprises: determining whether knee flexion angles of the user exceed a preset threshold according to the two pitch angles; and in response to the knee flexion angles of the user exceeding the preset threshold, determining that the exercise of the user corresponding to standing posture has been detected. ### Claim 17 (depends on 15) The robot of claim 15, wherein the posture is a sitting posture, and the second measurement data is the two pitch angles; determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data comprises: determining whether a lifting height of a leg of the user exceeds a preset threshold according to the two pitch angles; and in response to the lifting height of the leg of the user exceeds the preset threshold, determining that the exercise of the user corresponding to sitting posture has been detected. ### Claim 18 (depends on 11) The robot of claim 11, wherein the exercise data comprises a range of motion, a duration of the exercise, and sets/repetitions and a completion rate of the exercise. ### Claim 19 (depends on 11) The robot of claim 11, wherein the operations further comprise, before obtaining the second measurement data from the at least one IMU sensor, and determining whether the exercise of the user corresponding to the posture is detected according to the preset threshold parameter and the second measurement data, outputting second prompt information through an interaction interface of the robot to prompt the user to maintain a specified posture for a preset duration; and calibrating the at least one IMU sensor. ### Claim 20 A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of a robot, cause the at least one processor to perform a method, the method comprising: obtaining first measurement data from at least one inertial measurement unit (IMU) sensor that is arranged at a designated body part of the user, and detecting a posture of the user relative to the robot based on the first measurement data; obtaining second measurement data from the at least one IMU sensor, and determining whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting control parameters of the robot and the threshold parameter according to the exercise data, and controlling the robot according to the adjusted control parameters.