US20170296100A1 - Apparatus and method for recognizing gait motion - Google Patents
Apparatus and method for recognizing gait motion Download PDFInfo
- Publication number
- US20170296100A1 US20170296100A1 US15/641,655 US201715641655A US2017296100A1 US 20170296100 A1 US20170296100 A1 US 20170296100A1 US 201715641655 A US201715641655 A US 201715641655A US 2017296100 A1 US2017296100 A1 US 2017296100A1
- Authority
- US
- United States
- Prior art keywords
- hip joint
- motion
- time
- horizon
- landing point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 256
- 230000005021 gait Effects 0.000 title claims abstract description 158
- 238000000034 method Methods 0.000 title claims abstract description 32
- 210000004394 hip joint Anatomy 0.000 claims abstract description 203
- 210000002414 leg Anatomy 0.000 claims abstract description 118
- 230000001133 acceleration Effects 0.000 claims abstract description 93
- 238000005259 measurement Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 210000002683 foot Anatomy 0.000 description 31
- 230000006870 function Effects 0.000 description 21
- 238000012545 processing Methods 0.000 description 14
- 238000001514 detection method Methods 0.000 description 9
- 210000003414 extremity Anatomy 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 210000001624 hip Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011017 operating method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241001025261 Neoraja caerulea Species 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
- A61B5/1122—Determining geometric values, e.g. centre of rotation or angular range of movement of movement trajectories
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
- A61H1/02—Stretching or bending or torsioning apparatus for exercising
- A61H1/0237—Stretching or bending or torsioning apparatus for exercising for the lower limbs
- A61H1/0244—Hip
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H3/00—Appliances for aiding patients or disabled persons to walk about
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/22—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people in connection with sports or games
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/16—Physical interface with patient
- A61H2201/1602—Physical interface with patient kind of interface, e.g. head rest, knee support or lumbar support
- A61H2201/165—Wearable interfaces
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
- A61H2201/5061—Force sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
- A61H2201/5069—Angle sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
- A61H2201/5079—Velocity sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
- A61H2201/5084—Acceleration sensors
Definitions
- Example embodiments relate to apparatuses and/or methods for recognizing a gait motion, and more particularly, to apparatuses and/or methods for recognizing a gait motion based on biometric data of a user sensed by, for example, a walking assistance apparatus.
- Human walking is performed using different operating mechanisms of hip joints for level walking, walking in an upward inclined direction, for example, walking up stairs, and walking in a downward inclined direction, for example, walking down stairs.
- the walking assistance apparatus may assist walking by, for example, collectively generating an oscillator-based pattern for each gait motion.
- a walking assistance apparatus may not provide a walking assistance.
- the walking assistance apparatus may operate differently, using operating mechanisms, with respect to recognized gait motions, respectively, thereby providing an optimized walking assistance.
- At least one example embodiment relates to an apparatus for recognizing a gait motion.
- an apparatus for recognizing a gait motion includes a gait motion inference unit configured to infer a gait motion based on right and left hip joint angle information of a user, the right and left hip joint angle information sensed at a point in time at which a foot of the user lands, and a landing leg detector configured to detect a landing leg between both legs of the user based on the inferred gait motion.
- the right and left hip joint angle information may include at least one of angles of a right hip joint and a left hip joint, a difference between the angles of the right hip joint and the left hip joint, and motion directions of the right hip joint and the left hip joint.
- the gait motion may include a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- the apparatus may further include a landing point in time detector configured to detect a landing point in time of a foot of the user based on sensed acceleration information.
- the landing point in time detector may be configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- the base horizon may be set to follow a freeze horizon preset from a previous landing point in time to prevent or mitigate an error in detection of the landing point in time.
- the landing point in time detector may be configured to detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value.
- the mean acceleration for the base horizon may be updated for each step or preset to a first acceleration.
- the gait motion inference unit may be configured to infer the gait motion using a fuzzy logic.
- the gait motion inference unit may be configured to infer the gait motion by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a membership function, and the membership function may be set based on the right and left hip joint angle information.
- the landing leg detector may be configured to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction.
- the landing leg detector may be configured to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to a walking assistance apparatus.
- a walking assistance apparatus includes a driving portion configured to drive a right hip joint and a left hip joint of a user, a sensor portion configured to sense right and left hip joint angle information, an inertial measurement unit (IMU) sensor configured to sense acceleration information in response to walking of the user, and a controller configured to control the driving portion by inferring a gait motion of the user based on the right and left hip joint angle information, the right and left hip joint angle information sensed at a landing point in time of a foot of the user, the landing point in time detected based on the acceleration information, and detect a landing leg based on the inferred gait motion.
- IMU inertial measurement unit
- the controller may include a landing point in time detector configured to detect the landing point in time of the foot of the user based on the sensed acceleration information, a gait motion inference unit configured to infer the gait motion based on the right and left hip joint angle information of the user sensed at the detected landing point in time, and a landing leg detector configured to detect the landing leg between both legs of the user based on the inferred gait motion.
- the landing point in time detector may be further configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- the gait motion inference unit may be configured to infer the gait motion using a fuzzy logic.
- the landing leg detector may be configured to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction, and to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to a method of recognizing a gait motion.
- a method of recognizing a gait motion includes inferring a gait motion based on right and left hip joint angle information of a user sensed at a landing point in time of a foot of the user, and detecting a landing leg between both legs of the user based on the inferred gait motion.
- the method may further include detecting the landing point in time of the foot of the user based on sensed acceleration information.
- the detecting a landing point in time may include detecting a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- the inferring may include inferring the gait motion using a fuzzy logic, and inferring the gait motion by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a membership function.
- the membership function may be set based on the right and left hip joint angle information.
- the detecting a landing leg may include detecting, as the landing leg, a leg having a greater hip joint angle between angles of a right hip joint and a left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction, and detecting, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to an operating method of a walking assistance apparatus.
- an operating method of a walking assistance apparatus includes determining a gait motion based on sensed right and left hip joint angle information of a user, and outputting a driving control signal to drive a right hip joint and a left hip joint of the user based on the determined gait motion.
- the method may further include detecting a landing leg between a right leg and a left leg of the user based on the gait motion.
- FIG. 1 illustrates a user wearing a walking assistance apparatus according to an example embodiment
- FIG. 2 shows a block diagram of an apparatus for recognizing a gait motion according to an example embodiment
- FIG. 3 illustrates a sensed acceleration and horizons to be used to detect a landing point in time according to an example embodiment
- FIG. 4 illustrates a process of inferring a gait motion using a fuzzy logic according to an example embodiment
- FIG. 5 illustrates trajectories of angles of both hip joints of a user for a walking motion in an upward inclined direction according to an example embodiment
- FIG. 6 illustrates trajectories of angles of both hip joints of a user for a walking motion in a downward inclined direction according to an example embodiment
- FIG. 7 illustrates trajectories of angles of both hip joints of a user for a level walking motion according to an example embodiment
- FIG. 8 shows a flow chart illustrating a method of recognizing a gait motion according to an example embodiment
- FIG. 9 shows a flow chart illustrating a method of detecting a landing point in time according to an example embodiment.
- FIG. 1 illustrates a user wearing a walking assistance apparatus according to example embodiments.
- the walking assistance apparatus includes a driving portion 110 , a sensor portion 120 , an inertial measurement unit (IMU) sensor 130 , and a controller 140 .
- FIG. 1 illustrates a hip-type walking assistance apparatus, the type of the walking assistance apparatus is not limited thereto.
- the walking assistance apparatus may be applicable to, for example, a walking assistance apparatus that supports an entire pelvic limb, a walking assistance apparatus that supports a portion of a pelvic limb, etc.
- the walking assistance apparatus that supports a portion of a pelvic limb may be applicable to, for example, a walking assistance apparatus that supports up to a knee, a walking assistance apparatus that supports up to an ankle, etc.
- the driving portion 110 may be disposed on, for example, each of a right hip portion and a left hip portion of a user to drive both hip joints of the user.
- the sensor portion 120 may measure both hip joint angle information of the user while the user is walking.
- the both hip joint angle information may also be referred to as right and left hip joint angle information.
- the sensor portion 120 may be disposed in the driving portion 110 .
- the both hip joint angle information sensed by the sensor portion 120 may include at least one of angles of both hip joints, a difference between the angles of both hip joints, and motion directions of both hip joints.
- the IMU sensor 130 may measure acceleration information and posture information while the user is walking. A landing point in time of a foot of the user may be detected based on the acceleration information measured by the IMU sensor 130 . However, when a sensor capable of detecting a landing point in time of a foot is included in the walking assistance apparatus, the IMU sensor 130 may not be provided to recognize a gait motion.
- the controller 140 may infer a gait motion of the user based on right and left hip joint angle information sensed at the detected landing point in time of the foot of the user, and detect a landing leg based on the inferred gait motion.
- the gait motion of the user recognized by the controller 140 may include, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- human walking is performed using different operating mechanisms of hip joints for level walking, walking in an upward inclined direction(e.g., walking up stairs), and walking in a downward inclined direction (e.g., walking down stairs).
- an upward inclined direction e.g., walking up stairs
- a downward inclined direction e.g., walking down stairs
- the controller 140 may recognize the gait motion of the user as described above, and output a control signal to control the driving portion 110 based on at least one of the inferred gait motion and the detected landing leg.
- the driving portion 110 may drive the hip joints of the user suitably for the recognized gait motion based on the control signal output from the controller 140 .
- FIG. 2 shows a block diagram of an apparatus 200 for recognizing a gait motion according to an example embodiment.
- the apparatus 200 for recognizing a gait motion includes a landing point in time detector 210 , a gait motion inference unit 220 , and a landing leg detector 230 .
- the landing point in time detector 210 may detect a landing point in time of a foot of a user based on acceleration information sensed by the IMU sensor 130 of FIG. 1 or a separate acceleration sensor (not shown).
- a walking assistance apparatus that supports an entire pelvic limb of a user may include a foot force sensor configured to detect a landing point in time of a foot of the user
- the landing point in time detector 210 may detect a landing point in time of a foot of a user based on acceleration information sensed by the foot force sensor.
- the foot force sensor may be provided on a bottom of a shoe to easily detect a landing point in time.
- the landing point in time detector 210 may not be included in the walking assistance apparatus.
- a walking assistance apparatus that supports a portion of a pelvic limb may not include a foot force sensor configured to detect a landing point in time of a foot of a user. In such cases, the landing point in time of the foot of the user is to be detected separately.
- the landing point in time detector 210 may detect the landing point in time of the foot of the user based on the acceleration information sensed by the IMU sensor 130 or the acceleration sensor.
- the acceleration information may be, for example, a vertical acceleration, or a sum of squares of accelerations in an x-axial direction, a y-axial direction, and a z-axial direction corresponding to a vertical direction.
- the landing point in time detector 210 may detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- the base horizon may refer to a horizon in which a landing point in time does not occur in the previous step duration horizon.
- the base horizon may be set to follow a freeze horizon preset from a landing point in time after a previous landing point in time occurs.
- the base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon.
- the mean acceleration for the base horizon may also be updated for each step, or may be predetermined to be a uniform value as desired.
- the base horizon and the mean acceleration for the base horizon may be preset based on a general gait motion of a human. However, to detect a landing point in time more precisely based on characteristics of each user, the base horizon and the mean acceleration for the base horizon may be updated for each step.
- the prediction horizon may start after a freeze horizon and a base horizon occur subsequent to the previous landing point in time. This reflects that a desired (or alternatively, predetermined) time is required between a current landing point in time and a subsequent landing point in time during human walking. Thus, the prediction horizon may be minimized. Further, detection of the landing point in time may be attempted in a horizon with a relatively high landing point in time detection probability. Thus, a detection performance may increase.
- the landing point in time detector 210 may detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value.
- the prediction horizon may be set to be a horizon with a relatively high landing point in time detection probability.
- a horizon in which a landing point in time is detected for each step of the user may be non-uniform depending on a walking condition for the user.
- the landing point in time may not be detected in the prediction horizon set to follow the base horizon.
- the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value, it may be determined that landing does not occur in the prediction horizon.
- the landing point in time detector 210 may shift the prediction horizon, and compare the mean acceleration for the base horizon to a mean acceleration for the shifted prediction horizon.
- a method of the landing point in time detector 210 detecting the landing point in time of the foot of the user will be described later with reference to FIG. 3 .
- the gait motion inference unit 220 may infer a gait motion based on right and left hip joint angle information of the user sensed at the landing point in time of the foot of the user.
- the gait motion inference unit 220 may infer the gait motion of the user based on right and left hip joint angle information at a single step point in time of the user.
- the gait motion inference unit 220 may infer the gait motion using a fuzzy logic.
- the gait motion inference unit 220 may infer the gait motion of the user based on, for example, angles of both hip joints of the user at the landing point in time of the foot of the user, a difference between the angles of both hip joints of the user, and motion directions of both hip joints of the user.
- the gait motion of the user may be inferred by comparing the both hip joint angle information of the user to a threshold value, or through a separately preset rule.
- a threshold value or through a separately preset rule.
- the gait motion inference unit 220 may receive the right and left hip joint angle information of the user, and infer the gait motion of the user through fuzzification and defuzzification of the received right and left hip joint angle information.
- the gait motion inference unit 220 may infer the gait motion of the user by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the received right and left hip joint angle information using a membership function.
- the membership function may be set based on the right and left hip joint angle information.
- the fuzzy rule may be “IF-THEN” rules which are set based on both hip joint angle information for, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- the landing leg detector 230 may detect a landing leg between both legs of the user based on the gait motion inferred by the gait motion inference unit 220 .
- the landing leg may be detected.
- the landing leg detector 230 may detect the landing leg using different methods depending on the inferred gait motion.
- the landing leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint.
- the landing leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint.
- the landing leg detector 230 may set a method of detecting the landing leg differently for the gait motion inferred by the gait motion inference unit 220 .
- a method of detecting the landing leg using the landing leg detector 230 will be described later with reference to FIGS. 5 through 7 .
- the gait motion recognized by the apparatus 200 for recognizing a gait motion may be applied as information to be used by the walking assistance apparatus to provide a user with a walking assistance optimized for each gait motion.
- FIG. 3 illustrates a sensed acceleration and horizons to be used to detect a landing point in time according to an example embodiment.
- FIG. 3 is a graph illustrating a relationship between a time and an acceleration sensed by the IMU sensor 130 of FIG. 1 or an acceleration sensor.
- t_psh denotes a previous stride horizon
- t_sh denotes a current stride horizon
- t_bh denotes a base horizon
- t_fh denotes a freeze horizon
- t_ph denotes a prediction horizon.
- the base horizon may be a horizon in which a landing point in time does not occur in a previous step duration horizon.
- the base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon.
- the base horizon may be set to follow the freeze horizon preset from a previous landing point in time to prevent or mitigate an error in detection of the landing point in time after the landing point in time is detected. Taking into account that a time period is required between the landing point in time and a subsequent landing point in time, the prediction horizon may be set to follow the base horizon.
- a method of detecting a landing point in time of a subsequent step based on a current step using the landing point in time detector 210 will be described.
- a horizon for the current step may be estimated using a horizon for a previous step.
- a desired freeze horizon may be set from the landing point in time.
- the freeze horizon may be a horizon set or preset to prevent or mitigate an error in detection of the landing point in time.
- a mean acceleration for the base horizon may be compared to a mean acceleration for a prediction horizon.
- the freeze horizon set or preset to prevent or mitigate an error in detection of the landing point in time may be set to accurately set the mean acceleration for the base horizon estimated to be a horizon in which a landing point in time does not occur.
- the current base horizon may be set based on a step duration horizon for the previous step.
- the horizon for the current step may be estimated based on the previous step duration horizon, and the base horizon may be set based on the estimated horizon for the current step.
- a difference between a mean acceleration for a previous base horizon and a mean acceleration for an initially set prediction horizon may be less than a threshold value.
- the prediction horizon may be shifted to detect the landing point in time.
- an actual duration horizon for the previous step estimated based on a step previous to the previous step may increase to an extent corresponding to a shifted portion of the prediction horizon.
- the horizon for the current step may be set based on the actual duration horizon for the previous step.
- the current base horizon may be updated to a horizon obtained by adding the shifted portion of the prediction horizon to the previous base horizon.
- the prediction horizon may be shifted and set to follow the freeze horizon and the base horizon after the landing point in time of the current step occurs.
- the prediction horizon may be set or preset to minimize the prediction horizon and to allow the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon to be greater than or equal to the threshold value when the landing point in time occurs.
- the landing point in time detector 210 may detect the prediction horizon as the landing point in time. For example, a point in time at which acceleration is maximized in the prediction horizon may be detected as the landing point in time.
- the landing point in time detector 210 may determine that landing of the foot of the user does not occur in the prediction horizon.
- the landing point in time detector 210 may shift the prediction horizon, and compare a difference between the mean acceleration for the base horizon and a mean acceleration for the shifted prediction horizon to the threshold value.
- the landing point in time detector 210 may detect the landing point in time by shifting the prediction horizon until the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is greater than or equal to the threshold value.
- the landing point in time detector 210 may store a final step duration horizon corresponding to an actual duration horizon for the current step. By storing the final step duration horizon for the current step, the landing point in time detector 210 may estimate a horizon for the subsequent step.
- a duration horizon for the subsequent step may be estimated through the stored final step duration horizon for the current step. Further, a subsequent base horizon may also be updated based on the base horizon for the current step and the prediction horizon in which the landing point in time is detected.
- the base horizon and the mean acceleration for the base horizon may be updated for each step. While the user is walking, a step duration horizon and an acceleration may be non-uniform. Thus, a current base horizon and a mean acceleration for the current base horizon may be updated for each step through a previous step duration horizon.
- the base horizon and the mean acceleration for the base horizon may be set to be uniform values, thereby reducing a computational complexity of the landing point in time detector 210 .
- a landing point in time may be detected through the landing point in time detector 210 .
- the landing point in time detected through the landing point in time detector 210 may be provided to the gait motion inference unit 220 .
- the gait motion inference unit 220 may infer a gait motion based on both hip joint angle information of the user at the provided landing point in time.
- FIG. 4 illustrates a process of inferring a gait motion using a fuzzy logic according to an example embodiment.
- an input 410 includes a landing point in time and both hip joint angle information to be input into the gait motion inference unit 220 .
- the input 410 includes, as an input parameter, at least one of a landing point in time, an angle of a left hip joint, an angle of a right hip joint, a difference between the angles of both hip joints, a motion direction of the left hip joint, and a motion direction of the right hip joint.
- a member function may be set or preset for each input 410 to be provided to the gait motion inference unit 220 .
- the member function may be set or preset based on a characteristic of each input parameter included in the input 410 .
- a member function set for the angle of the left hip joint, among the input parameters may be classified into ranges of NEMID, NELOW, ZERO, POLOW, POMID, POHIGH, and POVHIGH based on the angle of the left hip joint, and expressed as a membership function.
- the membership function may indicate a degree of a value of an input parameter belonging to a classified range based on the value of the input parameter.
- a member function corresponding to each of the input parameters may be classified into ranges and expressed as a membership function.
- the foregoing is provided as an example for ease of description, and may be set differently based on a characteristic of each input parameter and a characteristic of a user.
- the gait motion inference unit 220 may perform fuzzification 420 on a value of each input parameter through a member function corresponding to each input parameter.
- the gait motion inference unit 220 may obtain a fuzzified value of each input parameter by performing the fuzzification 420 on each input parameter through the member function.
- the fuzzification 420 may correspond to a process of calculating a degree of the value of each input parameter belonging to each range classified in a member function corresponding to each input parameter. For example, when the angle of the left hip joint is 20°, an input angle of the left hip joint belonging to POLOW by 0.5 and POMID by 0.5 may be expressed by the fuzzified value.
- the gait motion inference unit 220 may perform defuzzification 430 based on a set or preset fuzzy rule and the value obtained by the fuzzification 420 of each input parameter using the member function.
- the fuzzy rule may be “IF-THEN” rules which are set or preset based on both hip joint angle information for a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- fuzzy rule may be defined as “IF-THEN” rules as follows.
- Rules 1 through 6 may be included in a single fuzzy rule, and may be a fuzzy rule to be used to infer a gait motion based on each input parameter.
- Rule 1 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POVHIGH, an angle of a right hip joint belongs to POLOW, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in an upward inclined direction.
- Rule 2 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POVHIGH, an angle of a right hip joint belongs to ZERO, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in an upward inclined direction.
- Rule 3 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POMID, an angle of a right hip joint belongs to POMID, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in a downward inclined direction.
- Rule 4 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POMID, an angle of a right hip joint belongs to POMID, and a difference between the angles of both hip joints belongs to LOW, a gait motion is inferred as a walking motion in a downward inclined direction.
- Rule 5 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POHIGH, an angle of a right hip joint belongs to NELOW, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a level walking motion.
- Rule 6 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POHIGH, an angle of a right hip joint belongs to NEMID, and a difference between the angles of both hip joints belongs to VHIGH, a gait motion is inferred as a level walking motion.
- the “IF-THEN” rules are provided as an example for ease of description. It is obvious to those skilled in the art that the rules may be set differently depending on a characteristic of a gait motion.
- the gait motion inference unit 220 may infer a gait motion of a user by performing the defuzzification 430 based on the fuzzy rule, a range to which each input parameter belongs, and the value obtained by the fuzzification 420 of each input parameter using the member function.
- the gait motion inference unit 220 may output results 440 of finally inferring the gait motion through the defuzzification 430 .
- the results 440 of inferring the gait motion may be classified into, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion, and may be output.
- a fuzzy logic is one example of artificial intelligence technologies for performing deductive inference based on a fuzzy rule.
- the gait motion inference unit 220 may infer the gait motion of the user using the fuzzy logic, thereby inferring the gait motion of the user with a relatively intuitive and robust expression in comparison to a method using a simple threshold value and/or combination of rules.
- FIG. 5 illustrates trajectories of angles of both hip joints of a user for a walking motion in an upward inclined direction according to an example embodiment.
- a graph illustrating a trajectory 520 of an angle of a right hip joint of a user and a trajectory 530 of an angle of a left hip joint of the user for a walking motion in an upward inclined direction is provided.
- an x axis denotes a time
- a y axis denotes a hip joint angle.
- the landing leg detector 230 may detect, as a landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint.
- the landing leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint at each landing point in time 511 , 512 , 513 , 514 , or 515 .
- the landing leg at each landing point in time 511 , 512 , 513 , 514 , or 515 may be detected as follows.
- a right leg may be detected as the landing leg because the angle of the right hip joint is greater than the angle of the left hip joint.
- a left leg may be detected as the landing leg because the angle of the left hip joint is greater than the angle of the right hip joint.
- FIG. 6 illustrates trajectories of angles of both hip joints of a user for a walking motion in a downward inclined direction according to an example embodiment.
- a graph illustrating a trajectory 620 of an angle of a right hip joint of a user and a trajectory 630 of an angle of a left hip joint of the user for a walking motion in a downward inclined direction are provided.
- an x axis denotes a time
- a y axis denotes a hip joint angle.
- the landing leg detector 230 may detect, as a landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint.
- the landing leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between the motion directions of the right hip joint and the left hip joint at each landing point in time 611 , 612 , 613 , or 614 .
- the landing leg at each landing point in time 611 , 612 , 613 , or 614 may be detected as follows.
- a right leg may be detected as the landing leg because the motion direction of the right hip joint has a negative velocity.
- a left leg may be detected as the landing leg because the motion direction of the left hip joint has a negative velocity.
- FIG. 7 illustrates trajectories of angles of both hip joints of a user for a level walking motion according to an example embodiment.
- a graph illustrating a trajectory 720 of an angle of a right hip joint of a user and a trajectory 730 of an angle of a left hip joint of the user for a level walking motion is provided.
- an x axis denotes a time
- a y axis denotes a hip joint angle.
- the landing leg detector 230 may detect, as a landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint.
- the landing leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and a left hip joint at each landing point in time 711 , 712 , 713 , 714 , or 715 .
- the landing leg at each landing point in time 711 , 712 , 713 , 714 , or 715 may be detected as follows.
- a left leg may be detected as the landing leg because the angle of the left hip joint is greater than the angle of the right hip joint.
- a right leg may be detected as the landing leg because the angle of the right hip joint is greater than the angle of the left hip joint.
- the landing leg detector 230 may detect a landing leg based on different criteria for a gait motion inferred by the gait motion inference unit 220 .
- FIG. 8 shows a flow chart illustrating a method of recognizing a gait motion according to an example embodiment.
- the landing point in time detector 210 of FIG. 2 may detect a landing point in time of a foot of a user based on acceleration information sensed by the IMU sensor 130 of FIG. 1 or a separate acceleration sensor.
- the landing point in time detector 210 may detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- the landing point in time detector 210 may detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value.
- the gait motion inference unit 220 of FIG. 2 may infer a gait motion based on right and left hip joint angle information of the user sensed at the landing point in time of the foot of the user.
- the gait motion inference unit 220 may infer the gait motion of the user based on right and left hip joint angle information at a single step point in time of the user.
- the gait motion inference unit 220 may infer the gait motion using a fuzzy logic.
- the gait motion inference unit 220 may infer the gait motion of the user based on, for example, angles of both hip joints of the user at the landing point in time of the foot of the user, a difference between the angles of both hip joints of the user, and motion directions of both hip joints of the user.
- the gait motion inference unit 220 may infer the gait motion of the user by performing defuzzification based on a preset fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a member function.
- the member function may be set based on the right and left hip joint angle information.
- the landing leg detector 230 of FIG. 2 may detect a landing leg between both legs of the user based on the gait motion inferred by the gait motion inference unit 220 .
- the landing leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between angles of a right hip joint and a left hip joint.
- the landing leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint.
- FIG. 9 shows a flow chart illustrating a method of detecting a landing point in time according to an example embodiment.
- the landing point in time detector 210 of FIG. 2 may estimate a horizon for a current step based on a horizon for a previous step.
- the horizon for the current step may be estimated based on the horizon for the previous step considering that a horizon for each step may not differ greatly.
- the landing point in time detector 210 may set a base horizon based on the estimated horizon for the current step.
- the base horizon may be a horizon in which a landing point in time does not occur in a previous step duration horizon.
- the base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon.
- the landing point in time detector 210 may shift a prediction horizon to be set to follow a freeze horizon and the base horizon after a landing point in time of the current step occurs.
- the prediction horizon may be set or preset to minimize the prediction horizon and to allow a difference between a mean acceleration for the base horizon and a mean acceleration for the prediction horizon to be greater than or equal to a threshold value when the landing point in time occurs.
- the landing point in time detector 210 may compare the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon to the threshold value.
- the threshold value is a desired (or alternatively, preset) value, and a reference value to be used to determine whether the landing point in time occurs based on the difference between the mean accelerations.
- the landing point in time detector 210 may determine that landing of a foot of the user does not occur in the prediction horizon. In this example, the landing point in time detector 210 may shift the prediction horizon, and compare a difference between the mean acceleration for the base horizon and a mean acceleration for the shifted prediction horizon to the threshold value.
- the landing point in time detector 210 may detect the prediction horizon as the landing point in time. For example, a point in time at which an acceleration is maximized in the prediction horizon may be detected as the landing point in time.
- the landing point in time detector 210 may store a final step duration horizon corresponding to an actual duration horizon for the current step. By storing the final step duration horizon for the current step, the landing point in time detector 210 may estimate a horizon for the subsequent step.
- the portion, units and/or modules described herein may be implemented using hardware components and software components.
- the hardware components may include microphones, amplifiers, band-pass filters, audio to digital convertors, and processing devices.
- a processing device e.g., controller
- the processing device(s) may include a processor, a controller and an arithmetic logic unit, a digital signal processor, a microcomputer, a field programmable array, a programmable logic unit, a microprocessor or any other device capable of responding to and executing instructions in a defined manner.
- the processing device may run an operating system (OS) and one or more software applications that run on the OS.
- the processing device also may access, store, manipulate, process, and create data in response to execution of the software.
- OS operating system
- the description of a processing device is used as singular; however, one skilled in the art will appreciated that a processing device may include multiple processing elements and multiple types of processing elements.
- a processing device may include multiple processors or a processor and a controller.
- different processing configurations are possible, such a parallel processors.
- the software may include a computer program, a piece of code, an instruction, or some combination thereof, to independently or collectively instruct and/or configure the processing device to operate as desired, thereby transforming the processing device into a special purpose processor.
- Software and data may be embodied permanently or temporarily in any type of machine, component, physical or virtual equipment, computer storage medium or device, or in a propagated signal wave capable of providing instructions or data to or being interpreted by the processing device.
- the software also may be distributed over network coupled computer systems so that the software is stored and executed in a distributed fashion.
- the software and data may be stored by one or more non-transitory computer readable recording mediums.
- the methods according to the above-described example embodiments may be recorded in non-transitory computer-readable media including program instructions to implement various operations of the above-described example embodiments.
- the media may also include, alone or in combination with the program instructions, data files, data structures, and the like.
- the program instructions recorded on the media may be those specially designed and constructed for the purposes of example embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts.
- non-transitory computer-readable media examples include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROM discs, DVDs, and/or Blue-ray discs; magneto-optical media such as optical discs; and hardware devices that are specially configured to store and perform program instructions, such as read-only memory (ROM), random access memory (RAM), flash memory (e.g., USB flash drives, memory cards, memory sticks, etc.), and the like.
- program instructions include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter.
- the above-described devices may be configured to act as one or more software modules in order to perform the operations of the above-described example embodiments, or vice versa.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Engineering & Computer Science (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Physical Education & Sports Medicine (AREA)
- Rehabilitation Therapy (AREA)
- Pain & Pain Management (AREA)
- Epidemiology (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Rehabilitation Tools (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
Abstract
An apparatus and method for recognizing a gait motion by detecting a landing point in time of a foot of a user based on sensed acceleration information, inferring a gait motion based on right and left hip joint angle information of the user sensed at the detected landing point in time of the foot of the user, and detecting a landing leg between both legs of the user based on the inferred gait motion may be provided.
Description
- This is a Continuation application of U.S. application Ser. No. 14/556,841, filed Dec. 1, 2014, which claims priority under 35 U.S.C. §119 to Korean Patent Application No. 10-2014-0096320, filed on Jul. 29, 2014, in the Korean Intellectual Property Office, the entire contents of each of which are herein incorporated by reference.
- Example embodiments relate to apparatuses and/or methods for recognizing a gait motion, and more particularly, to apparatuses and/or methods for recognizing a gait motion based on biometric data of a user sensed by, for example, a walking assistance apparatus.
- Human walking is performed using different operating mechanisms of hip joints for level walking, walking in an upward inclined direction, for example, walking up stairs, and walking in a downward inclined direction, for example, walking down stairs.
- When a walking assistance apparatus is unable to recognize a gait motion of a user during assisting walking of the user, the walking assistance apparatus may assist walking by, for example, collectively generating an oscillator-based pattern for each gait motion. However, such a walking assistance apparatus may not provide a walking assistance.
- Thus, when human walking is to be assisted by, for example, a walking assistance apparatus, it is desired to recognize a gait motion of a user. The walking assistance apparatus may operate differently, using operating mechanisms, with respect to recognized gait motions, respectively, thereby providing an optimized walking assistance.
- At least one example embodiment relates to an apparatus for recognizing a gait motion.
- According to an example embodiment, an apparatus for recognizing a gait motion includes a gait motion inference unit configured to infer a gait motion based on right and left hip joint angle information of a user, the right and left hip joint angle information sensed at a point in time at which a foot of the user lands, and a landing leg detector configured to detect a landing leg between both legs of the user based on the inferred gait motion.
- According to some example embodiments, the right and left hip joint angle information may include at least one of angles of a right hip joint and a left hip joint, a difference between the angles of the right hip joint and the left hip joint, and motion directions of the right hip joint and the left hip joint.
- According to some example embodiments, the gait motion may include a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- According to some example embodiments, the apparatus may further include a landing point in time detector configured to detect a landing point in time of a foot of the user based on sensed acceleration information.
- According to some example embodiments provide that the landing point in time detector may be configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- According to some example embodiments, the base horizon may be set to follow a freeze horizon preset from a previous landing point in time to prevent or mitigate an error in detection of the landing point in time.
- According to some example embodiments, the landing point in time detector may be configured to detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value.
- According to some example embodiments, the mean acceleration for the base horizon may be updated for each step or preset to a first acceleration.
- According to some example embodiments provide that the gait motion inference unit may be configured to infer the gait motion using a fuzzy logic. The gait motion inference unit may be configured to infer the gait motion by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a membership function, and the membership function may be set based on the right and left hip joint angle information.
- According to some example embodiments, the landing leg detector may be configured to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction.
- According to some example embodiments provide that the landing leg detector may be configured to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to a walking assistance apparatus.
- According to an example embodiment, a walking assistance apparatus includes a driving portion configured to drive a right hip joint and a left hip joint of a user, a sensor portion configured to sense right and left hip joint angle information, an inertial measurement unit (IMU) sensor configured to sense acceleration information in response to walking of the user, and a controller configured to control the driving portion by inferring a gait motion of the user based on the right and left hip joint angle information, the right and left hip joint angle information sensed at a landing point in time of a foot of the user, the landing point in time detected based on the acceleration information, and detect a landing leg based on the inferred gait motion.
- According to some example embodiments, the controller may include a landing point in time detector configured to detect the landing point in time of the foot of the user based on the sensed acceleration information, a gait motion inference unit configured to infer the gait motion based on the right and left hip joint angle information of the user sensed at the detected landing point in time, and a landing leg detector configured to detect the landing leg between both legs of the user based on the inferred gait motion.
- According to some example embodiments, the landing point in time detector may be further configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- According to some example embodiments, the gait motion inference unit may be configured to infer the gait motion using a fuzzy logic.
- According to some example embodiments, the landing leg detector may be configured to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction, and to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to a method of recognizing a gait motion.
- According to an example embodiment, a method of recognizing a gait motion includes inferring a gait motion based on right and left hip joint angle information of a user sensed at a landing point in time of a foot of the user, and detecting a landing leg between both legs of the user based on the inferred gait motion.
- According to some example embodiments, the method may further include detecting the landing point in time of the foot of the user based on sensed acceleration information.
- According to some example embodiments, the detecting a landing point in time may include detecting a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
- According to some example embodiments, the inferring may include inferring the gait motion using a fuzzy logic, and inferring the gait motion by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a membership function. The membership function may be set based on the right and left hip joint angle information.
- According to some example embodiments, the detecting a landing leg may include detecting, as the landing leg, a leg having a greater hip joint angle between angles of a right hip joint and a left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction, and detecting, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
- At least one example embodiment relates to an operating method of a walking assistance apparatus.
- According to an example embodiment, an operating method of a walking assistance apparatus includes determining a gait motion based on sensed right and left hip joint angle information of a user, and outputting a driving control signal to drive a right hip joint and a left hip joint of the user based on the determined gait motion.
- According to some example embodiments, the method may further include detecting a landing leg between a right leg and a left leg of the user based on the gait motion.
- Additional aspects of example embodiments will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the disclosure.
- The above and/or other features will become apparent and more readily appreciated from the following description of example embodiments, taken in conjunction with the accompanying drawings of which:
-
FIG. 1 illustrates a user wearing a walking assistance apparatus according to an example embodiment; and -
FIG. 2 shows a block diagram of an apparatus for recognizing a gait motion according to an example embodiment; -
FIG. 3 illustrates a sensed acceleration and horizons to be used to detect a landing point in time according to an example embodiment; -
FIG. 4 illustrates a process of inferring a gait motion using a fuzzy logic according to an example embodiment; -
FIG. 5 illustrates trajectories of angles of both hip joints of a user for a walking motion in an upward inclined direction according to an example embodiment; -
FIG. 6 illustrates trajectories of angles of both hip joints of a user for a walking motion in a downward inclined direction according to an example embodiment; -
FIG. 7 illustrates trajectories of angles of both hip joints of a user for a level walking motion according to an example embodiment; -
FIG. 8 shows a flow chart illustrating a method of recognizing a gait motion according to an example embodiment; and -
FIG. 9 shows a flow chart illustrating a method of detecting a landing point in time according to an example embodiment. - Reference will now be made in detail with reference to various example embodiments, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout. Some example embodiments are described below to explain the present disclosure by referring to the figures.
- In the drawings, the thicknesses of layers and regions are exaggerated for clarity. Like reference numerals in the drawings denote like elements.
- Some detailed illustrative example embodiments are disclosed herein. However, specific structural and functional details disclosed herein are merely representative for purposes of describing the example embodiments. Example embodiments may be embodied in many alternate forms and should not be construed as limited to only those set forth herein.
- It should be understood that there is no intent to limit this disclosure to the particular example embodiments disclosed herein. On the contrary, the example embodiments described herein are to cover all modifications, equivalents, and alternatives falling within the scope of example embodiments.
- It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of this disclosure. As used herein, the term “and/or,” includes any and all combinations of one or more of the associated listed items.
- It will be understood that when an element is referred to as being “connected,” or “coupled,” to another element, it can be directly connected or coupled to the other element or intervening elements may be present. In contrast, when an element is referred to as being “directly connected,” or “directly coupled,” to another element, there are no intervening elements present. Other words used to describe the relationship between elements should be interpreted in a like fashion (e.g., “between,” versus “directly between,” “adjacent,” versus “directly adjacent,” etc.).
- The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms “a,” “an,” and “the,” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes,” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
- It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may in fact be executed substantially concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
- Various example embodiments will now be described more fully with reference to the accompanying drawings in which some example embodiments are shown.
-
FIG. 1 illustrates a user wearing a walking assistance apparatus according to example embodiments. - Referring to
FIG. 1 , the walking assistance apparatus includes a drivingportion 110, asensor portion 120, an inertial measurement unit (IMU)sensor 130, and acontroller 140. AlthoughFIG. 1 illustrates a hip-type walking assistance apparatus, the type of the walking assistance apparatus is not limited thereto. The walking assistance apparatus may be applicable to, for example, a walking assistance apparatus that supports an entire pelvic limb, a walking assistance apparatus that supports a portion of a pelvic limb, etc. The walking assistance apparatus that supports a portion of a pelvic limb may be applicable to, for example, a walking assistance apparatus that supports up to a knee, a walking assistance apparatus that supports up to an ankle, etc. - The driving
portion 110 may be disposed on, for example, each of a right hip portion and a left hip portion of a user to drive both hip joints of the user. Thesensor portion 120 may measure both hip joint angle information of the user while the user is walking. Herein, the both hip joint angle information may also be referred to as right and left hip joint angle information. Thesensor portion 120 may be disposed in the drivingportion 110. The both hip joint angle information sensed by thesensor portion 120 may include at least one of angles of both hip joints, a difference between the angles of both hip joints, and motion directions of both hip joints. - The
IMU sensor 130 may measure acceleration information and posture information while the user is walking. A landing point in time of a foot of the user may be detected based on the acceleration information measured by theIMU sensor 130. However, when a sensor capable of detecting a landing point in time of a foot is included in the walking assistance apparatus, theIMU sensor 130 may not be provided to recognize a gait motion. - The
controller 140 may infer a gait motion of the user based on right and left hip joint angle information sensed at the detected landing point in time of the foot of the user, and detect a landing leg based on the inferred gait motion. - The gait motion of the user recognized by the
controller 140 may include, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion. - As described above, human walking is performed using different operating mechanisms of hip joints for level walking, walking in an upward inclined direction(e.g., walking up stairs), and walking in a downward inclined direction (e.g., walking down stairs).
- The
controller 140 may recognize the gait motion of the user as described above, and output a control signal to control the drivingportion 110 based on at least one of the inferred gait motion and the detected landing leg. The drivingportion 110 may drive the hip joints of the user suitably for the recognized gait motion based on the control signal output from thecontroller 140. - Hereinafter, an apparatus for recognizing a gait motion included in the
controller 140, and a method thereof will be described. -
FIG. 2 shows a block diagram of anapparatus 200 for recognizing a gait motion according to an example embodiment. - Referring to
FIG. 2 , theapparatus 200 for recognizing a gait motion includes a landing point intime detector 210, a gaitmotion inference unit 220, and alanding leg detector 230. - The landing point in
time detector 210 may detect a landing point in time of a foot of a user based on acceleration information sensed by theIMU sensor 130 ofFIG. 1 or a separate acceleration sensor (not shown). For example, in the event that a walking assistance apparatus that supports an entire pelvic limb of a user may include a foot force sensor configured to detect a landing point in time of a foot of the user, the landing point intime detector 210 may detect a landing point in time of a foot of a user based on acceleration information sensed by the foot force sensor. - In the walking assistance apparatus that supports an entire pelvic limb, the foot force sensor may be provided on a bottom of a shoe to easily detect a landing point in time. In this example, the landing point in
time detector 210 may not be included in the walking assistance apparatus. However, a walking assistance apparatus that supports a portion of a pelvic limb may not include a foot force sensor configured to detect a landing point in time of a foot of a user. In such cases, the landing point in time of the foot of the user is to be detected separately. - The landing point in
time detector 210 may detect the landing point in time of the foot of the user based on the acceleration information sensed by theIMU sensor 130 or the acceleration sensor. The acceleration information may be, for example, a vertical acceleration, or a sum of squares of accelerations in an x-axial direction, a y-axial direction, and a z-axial direction corresponding to a vertical direction. - The landing point in
time detector 210 may detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value. - The base horizon may refer to a horizon in which a landing point in time does not occur in the previous step duration horizon. The base horizon may be set to follow a freeze horizon preset from a landing point in time after a previous landing point in time occurs. The base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon.
- The mean acceleration for the base horizon may also be updated for each step, or may be predetermined to be a uniform value as desired. As described above, the base horizon and the mean acceleration for the base horizon may be preset based on a general gait motion of a human. However, to detect a landing point in time more precisely based on characteristics of each user, the base horizon and the mean acceleration for the base horizon may be updated for each step.
- The prediction horizon may start after a freeze horizon and a base horizon occur subsequent to the previous landing point in time. This reflects that a desired (or alternatively, predetermined) time is required between a current landing point in time and a subsequent landing point in time during human walking. Thus, the prediction horizon may be minimized. Further, detection of the landing point in time may be attempted in a horizon with a relatively high landing point in time detection probability. Thus, a detection performance may increase.
- The landing point in
time detector 210 may detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value. As described above, the prediction horizon may be set to be a horizon with a relatively high landing point in time detection probability. However, a horizon in which a landing point in time is detected for each step of the user may be non-uniform depending on a walking condition for the user. - Thus, the landing point in time may not be detected in the prediction horizon set to follow the base horizon. When the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value, it may be determined that landing does not occur in the prediction horizon.
- In this example, the landing point in
time detector 210 may shift the prediction horizon, and compare the mean acceleration for the base horizon to a mean acceleration for the shifted prediction horizon. A method of the landing point intime detector 210 detecting the landing point in time of the foot of the user will be described later with reference toFIG. 3 . - The gait
motion inference unit 220 may infer a gait motion based on right and left hip joint angle information of the user sensed at the landing point in time of the foot of the user. The gaitmotion inference unit 220 may infer the gait motion of the user based on right and left hip joint angle information at a single step point in time of the user. - The gait
motion inference unit 220 may infer the gait motion using a fuzzy logic. The gaitmotion inference unit 220 may infer the gait motion of the user based on, for example, angles of both hip joints of the user at the landing point in time of the foot of the user, a difference between the angles of both hip joints of the user, and motion directions of both hip joints of the user. - The gait motion of the user may be inferred by comparing the both hip joint angle information of the user to a threshold value, or through a separately preset rule. However, because each user has different walking characteristics and a walking condition for each user can be non-uniform, it may be difficult to infer a gait motion of a user accurately by simply setting a threshold value or using a set rule.
- However, when a fuzzy logic is used, inference with a relatively intuitive and robust expression may be possible in comparison to the conventional threshold value based or set rule based method described above. According to some example embodiments, the gait
motion inference unit 220 may receive the right and left hip joint angle information of the user, and infer the gait motion of the user through fuzzification and defuzzification of the received right and left hip joint angle information. - For example, the gait
motion inference unit 220 may infer the gait motion of the user by performing defuzzification based on a desired (or alternatively, preset) fuzzy rule and a value obtained by fuzzification of the received right and left hip joint angle information using a membership function. The membership function may be set based on the right and left hip joint angle information. - The fuzzy rule may be “IF-THEN” rules which are set based on both hip joint angle information for, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
- A process of inferring the gait motion of the user based on the right and left hip joint angle information will be described later with reference to
FIG. 4 . - The
landing leg detector 230 may detect a landing leg between both legs of the user based on the gait motion inferred by the gaitmotion inference unit 220. For the walking assistance apparatus to assist walking of the user, the landing leg may be detected. - The
landing leg detector 230 may detect the landing leg using different methods depending on the inferred gait motion. When the inferred gait motion corresponds to the level walking motion or the walking motion in the upward inclined direction, thelanding leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint. - When the inferred gait motion corresponds to the walking motion in the downward inclined direction, the
landing leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint. - In view of the both hip joint angle information, the
landing leg detector 230 may set a method of detecting the landing leg differently for the gait motion inferred by the gaitmotion inference unit 220. A method of detecting the landing leg using thelanding leg detector 230 will be described later with reference toFIGS. 5 through 7 . - As described above, the gait motion recognized by the
apparatus 200 for recognizing a gait motion may be applied as information to be used by the walking assistance apparatus to provide a user with a walking assistance optimized for each gait motion. -
FIG. 3 illustrates a sensed acceleration and horizons to be used to detect a landing point in time according to an example embodiment. -
FIG. 3 is a graph illustrating a relationship between a time and an acceleration sensed by theIMU sensor 130 ofFIG. 1 or an acceleration sensor. In the graph, t_psh denotes a previous stride horizon, and t_sh denotes a current stride horizon. t_bh denotes a base horizon, t_fh denotes a freeze horizon, and t_ph denotes a prediction horizon. - The base horizon may be a horizon in which a landing point in time does not occur in a previous step duration horizon. The base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon.
- The base horizon may be set to follow the freeze horizon preset from a previous landing point in time to prevent or mitigate an error in detection of the landing point in time after the landing point in time is detected. Taking into account that a time period is required between the landing point in time and a subsequent landing point in time, the prediction horizon may be set to follow the base horizon.
- A method of detecting a landing point in time of a subsequent step based on a current step using the landing point in
time detector 210 will be described. A horizon for the current step may be estimated using a horizon for a previous step. When a landing point in time of the current step is detected, a desired freeze horizon may be set from the landing point in time. As described above, the freeze horizon may be a horizon set or preset to prevent or mitigate an error in detection of the landing point in time. - To detect the landing point in time of the subsequent step, a mean acceleration for the base horizon may be compared to a mean acceleration for a prediction horizon. The freeze horizon set or preset to prevent or mitigate an error in detection of the landing point in time may be set to accurately set the mean acceleration for the base horizon estimated to be a horizon in which a landing point in time does not occur.
- The current base horizon may be set based on a step duration horizon for the previous step. The horizon for the current step may be estimated based on the previous step duration horizon, and the base horizon may be set based on the estimated horizon for the current step.
- For example, in detection of the landing point in time of the current step from the previous step, a difference between a mean acceleration for a previous base horizon and a mean acceleration for an initially set prediction horizon may be less than a threshold value. In this example, the prediction horizon may be shifted to detect the landing point in time.
- When a landing point in time is detected in the shifted prediction horizon, an actual duration horizon for the previous step estimated based on a step previous to the previous step may increase to an extent corresponding to a shifted portion of the prediction horizon. The horizon for the current step may be set based on the actual duration horizon for the previous step. Thus, the current base horizon may be updated to a horizon obtained by adding the shifted portion of the prediction horizon to the previous base horizon.
- The prediction horizon may be shifted and set to follow the freeze horizon and the base horizon after the landing point in time of the current step occurs. The prediction horizon may be set or preset to minimize the prediction horizon and to allow the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon to be greater than or equal to the threshold value when the landing point in time occurs.
- When the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is greater than or equal to the threshold value, the landing point in
time detector 210 may detect the prediction horizon as the landing point in time. For example, a point in time at which acceleration is maximized in the prediction horizon may be detected as the landing point in time. - When the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value, the landing point in
time detector 210 may determine that landing of the foot of the user does not occur in the prediction horizon. - In this example, the landing point in
time detector 210 may shift the prediction horizon, and compare a difference between the mean acceleration for the base horizon and a mean acceleration for the shifted prediction horizon to the threshold value. The landing point intime detector 210 may detect the landing point in time by shifting the prediction horizon until the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is greater than or equal to the threshold value. - When the landing point in time of the subsequent step is detected, the landing point in
time detector 210 may store a final step duration horizon corresponding to an actual duration horizon for the current step. By storing the final step duration horizon for the current step, the landing point intime detector 210 may estimate a horizon for the subsequent step. - When a landing point in time of a step subsequent to the subsequent step is to be detected, a duration horizon for the subsequent step may be estimated through the stored final step duration horizon for the current step. Further, a subsequent base horizon may also be updated based on the base horizon for the current step and the prediction horizon in which the landing point in time is detected.
- As described above, the base horizon and the mean acceleration for the base horizon may be updated for each step. While the user is walking, a step duration horizon and an acceleration may be non-uniform. Thus, a current base horizon and a mean acceleration for the current base horizon may be updated for each step through a previous step duration horizon.
- However, when a step duration horizon and an acceleration of a user do not have large deviations for each step, the base horizon and the mean acceleration for the base horizon may be set to be uniform values, thereby reducing a computational complexity of the landing point in
time detector 210. - As described above, in a walking assistance apparatus not including a foot force sensor, a landing point in time may be detected through the landing point in
time detector 210. The landing point in time detected through the landing point intime detector 210 may be provided to the gaitmotion inference unit 220. The gaitmotion inference unit 220 may infer a gait motion based on both hip joint angle information of the user at the provided landing point in time. -
FIG. 4 illustrates a process of inferring a gait motion using a fuzzy logic according to an example embodiment. - Referring to
FIG. 4 , aninput 410 includes a landing point in time and both hip joint angle information to be input into the gaitmotion inference unit 220. Theinput 410 includes, as an input parameter, at least one of a landing point in time, an angle of a left hip joint, an angle of a right hip joint, a difference between the angles of both hip joints, a motion direction of the left hip joint, and a motion direction of the right hip joint. - A member function may be set or preset for each
input 410 to be provided to the gaitmotion inference unit 220. The member function may be set or preset based on a characteristic of each input parameter included in theinput 410. - For example, a member function set for the angle of the left hip joint, among the input parameters, may be classified into ranges of NEMID, NELOW, ZERO, POLOW, POMID, POHIGH, and POVHIGH based on the angle of the left hip joint, and expressed as a membership function. The membership function may indicate a degree of a value of an input parameter belonging to a classified range based on the value of the input parameter.
- Similar to the angle of the left hip joint, a member function corresponding to each of the input parameters may be classified into ranges and expressed as a membership function. However, the foregoing is provided as an example for ease of description, and may be set differently based on a characteristic of each input parameter and a characteristic of a user.
- The gait
motion inference unit 220 may performfuzzification 420 on a value of each input parameter through a member function corresponding to each input parameter. The gaitmotion inference unit 220 may obtain a fuzzified value of each input parameter by performing thefuzzification 420 on each input parameter through the member function. - The
fuzzification 420 may correspond to a process of calculating a degree of the value of each input parameter belonging to each range classified in a member function corresponding to each input parameter. For example, when the angle of the left hip joint is 20°, an input angle of the left hip joint belonging to POLOW by 0.5 and POMID by 0.5 may be expressed by the fuzzified value. - The gait
motion inference unit 220 may performdefuzzification 430 based on a set or preset fuzzy rule and the value obtained by thefuzzification 420 of each input parameter using the member function. For example, the fuzzy rule may be “IF-THEN” rules which are set or preset based on both hip joint angle information for a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion. - For example, the fuzzy rule may be defined as “IF-THEN” rules as follows.
-
- 1. rule: if FootStrike is ON and LeftHipAng is POVHIGH and RightHipAng is POLOW and AbsHipAngDiff is HIGH then WalkMode is STAIRUP
- 2. rule: if FootStrike is ON and LeftHipAng is POVHIGH and RightHipAng is ZERO and AbsHipAngDiff is HIGH then WalkMode is STAIRUP
- 3. rule: if FootStrike is ON and LeftHipAng is POMID and RightHipAng is POMID and AbsHipAngDiff is VLOW then WalkMode is STAIRDOWN
- 4. rule: if FootStrike is ON and LeftHipAng is POMID and RightHipAng is POMID and AbsHipAngDiff is LOW then WalkMode is STAIRDOWN
- 5. rule: if FootStrike is ON and LeftHipAng is POHIGH and RightHipAng is NELOW and AbsHipAngDiff is HIGH then WalkMode is LEVEL
- 6. rule: if FootStrike is ON and LeftHipAng is POHIGH and RightHipAng is NEMID and AbsHipAngDiff is VHIGH then WalkMode is LEVEL
- Rules 1 through 6 may be included in a single fuzzy rule, and may be a fuzzy rule to be used to infer a gait motion based on each input parameter.
- Rule 1 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POVHIGH, an angle of a right hip joint belongs to POLOW, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in an upward inclined direction.
- Rule 2 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POVHIGH, an angle of a right hip joint belongs to ZERO, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in an upward inclined direction.
- Rule 3 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POMID, an angle of a right hip joint belongs to POMID, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a walking motion in a downward inclined direction.
- Rule 4 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POMID, an angle of a right hip joint belongs to POMID, and a difference between the angles of both hip joints belongs to LOW, a gait motion is inferred as a walking motion in a downward inclined direction.
-
Rule 5 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POHIGH, an angle of a right hip joint belongs to NELOW, and a difference between the angles of both hip joints belongs to HIGH, a gait motion is inferred as a level walking motion. - Rule 6 is a rule in which, when a landing point in time is detected, an angle of a left hip joint belongs to POHIGH, an angle of a right hip joint belongs to NEMID, and a difference between the angles of both hip joints belongs to VHIGH, a gait motion is inferred as a level walking motion.
- However, the “IF-THEN” rules are provided as an example for ease of description. It is obvious to those skilled in the art that the rules may be set differently depending on a characteristic of a gait motion.
- As described above, the gait
motion inference unit 220 may infer a gait motion of a user by performing thedefuzzification 430 based on the fuzzy rule, a range to which each input parameter belongs, and the value obtained by thefuzzification 420 of each input parameter using the member function. - The gait
motion inference unit 220 mayoutput results 440 of finally inferring the gait motion through thedefuzzification 430. Theresults 440 of inferring the gait motion may be classified into, for example, a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion, and may be output. - A fuzzy logic is one example of artificial intelligence technologies for performing deductive inference based on a fuzzy rule. The gait
motion inference unit 220 may infer the gait motion of the user using the fuzzy logic, thereby inferring the gait motion of the user with a relatively intuitive and robust expression in comparison to a method using a simple threshold value and/or combination of rules. -
FIG. 5 illustrates trajectories of angles of both hip joints of a user for a walking motion in an upward inclined direction according to an example embodiment. - Referring to
FIG. 5 , a graph illustrating atrajectory 520 of an angle of a right hip joint of a user and atrajectory 530 of an angle of a left hip joint of the user for a walking motion in an upward inclined direction is provided. In the graph, an x axis denotes a time, and a y axis denotes a hip joint angle. - When a gait motion inferred by the gait
motion inference unit 220 corresponds to a walking motion in an upward inclined direction, thelanding leg detector 230 may detect, as a landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint. - Considering the
trajectories FIG. 5 , thelanding leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint at each landing point intime - Based on the foregoing description, the landing leg at each landing point in
time time time -
FIG. 6 illustrates trajectories of angles of both hip joints of a user for a walking motion in a downward inclined direction according to an example embodiment. - Referring to
FIG. 6 , a graph illustrating atrajectory 620 of an angle of a right hip joint of a user and atrajectory 630 of an angle of a left hip joint of the user for a walking motion in a downward inclined direction are provided. In the graph, an x axis denotes a time, and a y axis denotes a hip joint angle. - When a gait motion inferred by the gait
motion inference unit 220 corresponds to a walking motion in a downward inclined direction, thelanding leg detector 230 may detect, as a landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint. - Considering the trajectories of
angles FIG. 6 , thelanding leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between the motion directions of the right hip joint and the left hip joint at each landing point intime - Based on the foregoing description, the landing leg at each landing point in
time time time -
FIG. 7 illustrates trajectories of angles of both hip joints of a user for a level walking motion according to an example embodiment. - Referring to
FIG. 7 , a graph illustrating atrajectory 720 of an angle of a right hip joint of a user and atrajectory 730 of an angle of a left hip joint of the user for a level walking motion is provided. In the graph, an x axis denotes a time, and a y axis denotes a hip joint angle. - When a gait motion inferred by the gait
motion inference unit 220 corresponds to a level walking motion, thelanding leg detector 230 may detect, as a landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and the left hip joint. - Considering the
trajectories FIG. 7 , thelanding leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between the angles of the right hip joint and a left hip joint at each landing point intime - Based on the foregoing description, the landing leg at each landing point in
time time time - As described with reference to
FIGS. 5 through 7 , thelanding leg detector 230 may detect a landing leg based on different criteria for a gait motion inferred by the gaitmotion inference unit 220. -
FIG. 8 shows a flow chart illustrating a method of recognizing a gait motion according to an example embodiment. - Referring to
FIG. 8 , inoperation 810, the landing point intime detector 210 ofFIG. 2 may detect a landing point in time of a foot of a user based on acceleration information sensed by theIMU sensor 130 ofFIG. 1 or a separate acceleration sensor. The landing point intime detector 210 may detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value. - The landing point in
time detector 210 may detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value. - In
operation 820, the gaitmotion inference unit 220 ofFIG. 2 may infer a gait motion based on right and left hip joint angle information of the user sensed at the landing point in time of the foot of the user. The gaitmotion inference unit 220 may infer the gait motion of the user based on right and left hip joint angle information at a single step point in time of the user. - The gait
motion inference unit 220 may infer the gait motion using a fuzzy logic. The gaitmotion inference unit 220 may infer the gait motion of the user based on, for example, angles of both hip joints of the user at the landing point in time of the foot of the user, a difference between the angles of both hip joints of the user, and motion directions of both hip joints of the user. - The gait
motion inference unit 220 may infer the gait motion of the user by performing defuzzification based on a preset fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a member function. The member function may be set based on the right and left hip joint angle information. - In
operation 830, thelanding leg detector 230 ofFIG. 2 may detect a landing leg between both legs of the user based on the gait motion inferred by the gaitmotion inference unit 220. - When the gait motion inferred by the gait
motion inference unit 220 corresponds to a level walking motion or a walking motion in an upward inclined direction, thelanding leg detector 230 may detect, as the landing leg, a leg having a greater hip joint angle between angles of a right hip joint and a left hip joint. - When the gait motion inferred by the gait
motion inference unit 220 corresponds to a walking motion in a downward inclined direction, thelanding leg detector 230 may detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint. -
FIG. 9 shows a flow chart illustrating a method of detecting a landing point in time according to an example embodiment. - Referring to
FIG. 9 , inoperation 910, the landing point intime detector 210 ofFIG. 2 may estimate a horizon for a current step based on a horizon for a previous step. The horizon for the current step may be estimated based on the horizon for the previous step considering that a horizon for each step may not differ greatly. - In
operation 920, the landing point intime detector 210 may set a base horizon based on the estimated horizon for the current step. The base horizon may be a horizon in which a landing point in time does not occur in a previous step duration horizon. The base horizon may be set to be uniform for each step, or may be updated for each step based on a previous base horizon. - In
operation 930, the landing point intime detector 210 may shift a prediction horizon to be set to follow a freeze horizon and the base horizon after a landing point in time of the current step occurs. The prediction horizon may be set or preset to minimize the prediction horizon and to allow a difference between a mean acceleration for the base horizon and a mean acceleration for the prediction horizon to be greater than or equal to a threshold value when the landing point in time occurs. - In
operation 940, the landing point intime detector 210 may compare the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon to the threshold value. The threshold value is a desired (or alternatively, preset) value, and a reference value to be used to determine whether the landing point in time occurs based on the difference between the mean accelerations. - When the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value, the landing point in
time detector 210 may determine that landing of a foot of the user does not occur in the prediction horizon. In this example, the landing point intime detector 210 may shift the prediction horizon, and compare a difference between the mean acceleration for the base horizon and a mean acceleration for the shifted prediction horizon to the threshold value. - In
operation 950, when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is greater than or equal to the threshold value, the landing point intime detector 210 may detect the prediction horizon as the landing point in time. For example, a point in time at which an acceleration is maximized in the prediction horizon may be detected as the landing point in time. - In
operation 960, when a landing point in time of a subsequent step is detected, the landing point intime detector 210 may store a final step duration horizon corresponding to an actual duration horizon for the current step. By storing the final step duration horizon for the current step, the landing point intime detector 210 may estimate a horizon for the subsequent step. - The portion, units and/or modules described herein may be implemented using hardware components and software components. For example, the hardware components may include microphones, amplifiers, band-pass filters, audio to digital convertors, and processing devices. A processing device (e.g., controller) may be implemented using one or more hardware device configured to carry out and/or execute program code by performing arithmetical, logical, and input/output operations. The processing device(s) may include a processor, a controller and an arithmetic logic unit, a digital signal processor, a microcomputer, a field programmable array, a programmable logic unit, a microprocessor or any other device capable of responding to and executing instructions in a defined manner. The processing device may run an operating system (OS) and one or more software applications that run on the OS. The processing device also may access, store, manipulate, process, and create data in response to execution of the software. For purpose of simplicity, the description of a processing device is used as singular; however, one skilled in the art will appreciated that a processing device may include multiple processing elements and multiple types of processing elements. For example, a processing device may include multiple processors or a processor and a controller. In addition, different processing configurations are possible, such a parallel processors.
- The software may include a computer program, a piece of code, an instruction, or some combination thereof, to independently or collectively instruct and/or configure the processing device to operate as desired, thereby transforming the processing device into a special purpose processor. Software and data may be embodied permanently or temporarily in any type of machine, component, physical or virtual equipment, computer storage medium or device, or in a propagated signal wave capable of providing instructions or data to or being interpreted by the processing device. The software also may be distributed over network coupled computer systems so that the software is stored and executed in a distributed fashion. The software and data may be stored by one or more non-transitory computer readable recording mediums.
- The methods according to the above-described example embodiments may be recorded in non-transitory computer-readable media including program instructions to implement various operations of the above-described example embodiments. The media may also include, alone or in combination with the program instructions, data files, data structures, and the like. The program instructions recorded on the media may be those specially designed and constructed for the purposes of example embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of non-transitory computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROM discs, DVDs, and/or Blue-ray discs; magneto-optical media such as optical discs; and hardware devices that are specially configured to store and perform program instructions, such as read-only memory (ROM), random access memory (RAM), flash memory (e.g., USB flash drives, memory cards, memory sticks, etc.), and the like. Examples of program instructions include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter. The above-described devices may be configured to act as one or more software modules in order to perform the operations of the above-described example embodiments, or vice versa.
- A number of example embodiments have been described above. Nevertheless, it should be understood that various modifications may be made. For example, suitable results may be achieved if the described techniques are performed in a different order and/or if components in a described system, architecture, device, or circuit are combined in a different manner and/or replaced or supplemented by other components or their equivalents. Accordingly, other implementations are within the scope of the following claims.
Claims (20)
1. An apparatus for recognizing a gait motion, the apparatus comprising:
a gait motion inference unit configured to infer a gait motion based on right and left hip joint angle information of a user, the right and left hip joint angle information sensed at a point in time at which a foot of the user lands; and
a landing leg detector configured to detect a landing leg between both legs of the user based on the inferred gait motion.
2. The apparatus of claim 1 , wherein the right and left hip joint angle information comprises at least one of angles of a right hip joint and a left hip joint, a difference between the angles of the right hip joint and the left hip joint, and motion directions of the right hip joint and the left hip joint.
3. The apparatus of claim 1 , wherein the gait motion comprises a level walking motion, a walking motion in an upward inclined direction, a walking motion in a downward inclined direction, and a standing motion.
4. The apparatus of claim 1 , further comprising:
a landing point in time detector configured to detect a landing point in time of a foot of the user based on sensed acceleration information.
5. The apparatus of claim 4 , wherein the landing point in time detector is configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
6. The apparatus of claim 5 , wherein the base horizon is set to follow a freeze horizon set from a previous landing point in time.
7. The apparatus of claim 5 , wherein the landing point in time detector is configured to detect the landing point in time of the foot of the user by shifting the prediction horizon when the difference between the mean acceleration for the base horizon and the mean acceleration for the prediction horizon is less than the threshold value.
8. The apparatus of claim 1 , wherein the gait motion inference unit is configured to infer the gait motion using a fuzzy logic.
9. The apparatus of claim 8 , wherein the gait motion inference unit is configured to infer the gait motion by performing defuzzification based on a fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a member function, and
the member function is set based on the right and left hip joint angle information.
10. The apparatus of claim 1 , wherein the landing leg detector is configured to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction.
11. The apparatus of claim 1 , wherein the landing leg detector is configured to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
12. A walking assistance apparatus comprising:
a driving portion configured to drive a right hip joint and a left hip joint of a user;
a sensor portion configured to sense right and left hip joint angle information;
an inertial measurement unit (IMU) sensor configured to sense acceleration information in response to walking of the user; and
a controller configured to
control the driving portion by inferring a gait motion of the user based on the right and left hip joint angle information, the right and left hip joint angle information sensed at a landing point in time of a foot of the user, the landing point in time detected based on the acceleration information, and
detect a landing leg based on the inferred gait motion.
13. The apparatus of claim 12 , wherein the controller comprises:
a landing point in time detector configured to detect the landing point in time of the foot of the user based on the sensed acceleration information;
a gait motion inference unit configured to infer the gait motion based on the right and left hip joint angle information of the user sensed at the detected landing point in time; and
a landing leg detector configured to detect the landing leg between both legs of the user based on the inferred gait motion.
14. The apparatus of claim 13 , wherein the landing point in time detector is further configured to detect a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
15. The apparatus of claim 13 , wherein the gait motion inference unit is configured to infer the gait motion using a fuzzy logic.
16. The apparatus of claim 13 , wherein the landing leg detector is configured:
to detect, as the landing leg, a leg having a greater hip joint angle between angles of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction, and
to detect, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
17. A method of recognizing a gait motion, the method comprising:
detecting a landing point in time of a foot of a user based on sensed acceleration information;
inferring a gait motion based on right and left hip joint angle information of the user sensed at the detected landing point in time of the foot of the user; and
detecting a landing leg between both legs of the user based on the inferred gait motion.
18. The method of claim 17 , wherein the detecting a landing point in time comprises detecting a prediction horizon as the landing point in time when a difference between a mean acceleration for a base horizon set based on a previous step duration horizon and a mean acceleration for the prediction horizon is greater than or equal to a threshold value.
19. The method of claim 17 , wherein the inferring comprises inferring the gait motion by performing defuzzification based on a fuzzy rule and a value obtained by fuzzification of the right and left hip joint angle information using a member function, and
the member function is set based on the right and left hip joint angle information.
20. The method of claim 17 , wherein the detecting a landing leg comprises:
detecting, as the landing leg, a leg having a greater hip joint angle between angles of a right hip joint and a left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a level walking motion or a walking motion in an upward inclined direction; and
detecting, as the landing leg, a leg having a motion direction with a negative velocity between motion directions of the right hip joint and the left hip joint included in the right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/641,655 US20170296100A1 (en) | 2014-07-29 | 2017-07-05 | Apparatus and method for recognizing gait motion |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2014-0096320 | 2014-07-29 | ||
KR1020140096320A KR102378018B1 (en) | 2014-07-29 | 2014-07-29 | Gait motion recognition apparatus and method thereof |
US14/556,841 US9737240B2 (en) | 2014-07-29 | 2014-12-01 | Apparatus and method for recognizing gait motion |
US15/641,655 US20170296100A1 (en) | 2014-07-29 | 2017-07-05 | Apparatus and method for recognizing gait motion |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/556,841 Continuation US9737240B2 (en) | 2014-07-29 | 2014-12-01 | Apparatus and method for recognizing gait motion |
Publications (1)
Publication Number | Publication Date |
---|---|
US20170296100A1 true US20170296100A1 (en) | 2017-10-19 |
Family
ID=55178765
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/556,841 Active 2035-01-29 US9737240B2 (en) | 2014-07-29 | 2014-12-01 | Apparatus and method for recognizing gait motion |
US15/641,655 Abandoned US20170296100A1 (en) | 2014-07-29 | 2017-07-05 | Apparatus and method for recognizing gait motion |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/556,841 Active 2035-01-29 US9737240B2 (en) | 2014-07-29 | 2014-12-01 | Apparatus and method for recognizing gait motion |
Country Status (2)
Country | Link |
---|---|
US (2) | US9737240B2 (en) |
KR (3) | KR102378018B1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919943A (en) * | 2019-04-16 | 2019-06-21 | 广东省妇幼保健院 | Infant hip joint angle automatic testing method, system and calculating equipment |
GB2616682A (en) * | 2022-03-18 | 2023-09-20 | Biomex Ltd | Apparatus and method for determining phase of gait of a subject |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6660110B2 (en) * | 2015-07-23 | 2020-03-04 | 原田電子工業株式会社 | Gait analysis method and gait analysis system |
JP6418652B2 (en) * | 2016-04-22 | 2018-11-07 | トヨタ自動車株式会社 | Upper limb rehabilitation support apparatus and method for operating the same |
EP3778139B1 (en) * | 2016-08-17 | 2023-10-18 | Power Assist International Corporation | Wearable assist robot apparatus |
US11246507B2 (en) * | 2016-08-18 | 2022-02-15 | Sigmasense, Llc. | Wireless in-shoe physical activity monitoring apparatus |
KR102556924B1 (en) | 2016-09-05 | 2023-07-18 | 삼성전자주식회사 | Method for walking assist, and device operating the same |
KR102701390B1 (en) | 2017-02-21 | 2024-09-02 | 삼성전자주식회사 | Method and apparatus for walking assistance |
CN109325479B (en) * | 2018-11-28 | 2020-10-16 | 清华大学 | Step detection method and device |
CN110558991B (en) * | 2019-07-30 | 2022-05-20 | 福建省万物智联科技有限公司 | Gait analysis method |
KR102278728B1 (en) * | 2019-08-09 | 2021-07-16 | 재단법인대구경북과학기술원 | System for automatically determining scale of spasticity based on inertia sensor |
CN110522458A (en) * | 2019-10-15 | 2019-12-03 | 北京理工大学 | A kind of gait real-time identification method suitable for knee joint ectoskeleton |
CN112869732B (en) * | 2019-11-29 | 2024-05-28 | 宝成工业股份有限公司 | Method and device for analyzing gait |
WO2024034889A1 (en) * | 2022-08-12 | 2024-02-15 | 삼성전자주식회사 | Method for determining gait state, and device performing method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140121575A1 (en) * | 2012-11-01 | 2014-05-01 | Honda Motor Co., Ltd. | Walking motion assist device |
US20160107309A1 (en) * | 2013-05-31 | 2016-04-21 | President And Fellows Of Harvard College | Soft Exosuit for Assistance with Human Motion |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6360597B1 (en) | 1997-01-08 | 2002-03-26 | The Trustees Of Boston University | In-shoe remote telemetry gait analysis system |
US8864846B2 (en) | 2005-03-31 | 2014-10-21 | Massachusetts Institute Of Technology | Model-based neuromechanical controller for a robotic leg |
JP5120795B2 (en) * | 2005-11-15 | 2013-01-16 | 学校法人日本大学 | Human posture motion discrimination device and energy consumption calculation device |
KR100651639B1 (en) * | 2005-12-30 | 2006-12-01 | 서강대학교산학협력단 | Foot pressure sensor of robot for assistant exoskeletal power |
KR101252634B1 (en) * | 2006-04-07 | 2013-04-09 | 삼성전자주식회사 | system for analyzing walking motion |
JP2012516717A (en) * | 2009-01-30 | 2012-07-26 | マサチューセッツ インスティテュート オブ テクノロジー | Actuator-powered knee prosthesis with antagonistic muscle action |
KR101053491B1 (en) * | 2009-04-07 | 2011-08-08 | (주)휴레브 | Walking Cycle Detection System and Method Using Motion Sensor |
US9188963B2 (en) | 2009-07-06 | 2015-11-17 | Autonomous Id Canada Inc. | Gait-based authentication system |
JP5802131B2 (en) | 2009-10-21 | 2015-10-28 | 本田技研工業株式会社 | Method for controlling exercise assist device, walking assist device and rehabilitation method |
KR20130096631A (en) | 2010-04-05 | 2013-08-30 | 아이워크, 아이엔씨. | Controlling torque in a prosthesis or orthosis |
US8548740B2 (en) | 2010-10-07 | 2013-10-01 | Honeywell International Inc. | System and method for wavelet-based gait classification |
KR101384988B1 (en) * | 2011-04-08 | 2014-04-21 | 연세대학교 원주산학협력단 | System and method of robotic gait training |
JP5885292B2 (en) * | 2011-11-08 | 2016-03-15 | 公立大学法人首都大学東京 | Action recognition program and processing device for action recognition |
KR101317354B1 (en) * | 2011-11-21 | 2013-10-11 | 서강대학교산학협력단 | Control method of walking assistance torque and walking assistance apparatus |
KR101323019B1 (en) * | 2011-11-25 | 2013-10-29 | 신대섭 | Rehabilitation Therapy Device Using Walking Assist Robot |
KR101361362B1 (en) | 2012-02-14 | 2014-02-12 | 한국산업기술대학교산학협력단 | Walking Assistance Robot for Actively Determining Moving Speed Based on User Gait Cycle |
US9682005B2 (en) | 2012-02-24 | 2017-06-20 | Massachusetts Institute Of Technology | Elastic element exoskeleton and method of using same |
US9451881B2 (en) | 2012-12-06 | 2016-09-27 | Autonomous_Id Canada Inc. | Gait-based biometric system for detecting weight gain or loss |
US9204797B2 (en) | 2012-12-06 | 2015-12-08 | Autonomous Id Canada Inc. | Gait-based biometric system for detecting pathomechanical abnormalities relating to disease pathology |
KR101358943B1 (en) | 2013-02-12 | 2014-02-07 | 한국과학기술연구원 | Pelvis support device for gait rehabilitation robot |
KR102119536B1 (en) * | 2014-01-15 | 2020-06-05 | 삼성전자주식회사 | Wearable robot and control method for the same |
-
2014
- 2014-07-29 KR KR1020140096320A patent/KR102378018B1/en active IP Right Grant
- 2014-12-01 US US14/556,841 patent/US9737240B2/en active Active
-
2017
- 2017-07-05 US US15/641,655 patent/US20170296100A1/en not_active Abandoned
-
2022
- 2022-03-18 KR KR1020220033988A patent/KR102569009B1/en active IP Right Grant
-
2023
- 2023-08-16 KR KR1020230107221A patent/KR20230124532A/en not_active Application Discontinuation
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140121575A1 (en) * | 2012-11-01 | 2014-05-01 | Honda Motor Co., Ltd. | Walking motion assist device |
US20160107309A1 (en) * | 2013-05-31 | 2016-04-21 | President And Fellows Of Harvard College | Soft Exosuit for Assistance with Human Motion |
Non-Patent Citations (2)
Title |
---|
Martínez-Solís, Fermín, et al. "Design of a low cost measurement system based on accelerometers for gait analysis." Acta Scientiarum. Technology 36.1 (2014): 111-121. * |
Ng, Sau Kuen, and Howard Jay Chizeck. "Fuzzy model identification for classification of gait events in paraplegics." Fuzzy Systems, IEEE Transactions on 5.4 (1997): 536-544. * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919943A (en) * | 2019-04-16 | 2019-06-21 | 广东省妇幼保健院 | Infant hip joint angle automatic testing method, system and calculating equipment |
GB2616682A (en) * | 2022-03-18 | 2023-09-20 | Biomex Ltd | Apparatus and method for determining phase of gait of a subject |
Also Published As
Publication number | Publication date |
---|---|
KR20230124532A (en) | 2023-08-25 |
KR20220039694A (en) | 2022-03-29 |
KR20160014284A (en) | 2016-02-11 |
US9737240B2 (en) | 2017-08-22 |
US20160029928A1 (en) | 2016-02-04 |
KR102569009B1 (en) | 2023-08-21 |
KR102378018B1 (en) | 2022-03-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9737240B2 (en) | Apparatus and method for recognizing gait motion | |
US10449106B2 (en) | Method and apparatus for walking assistance | |
US11234890B2 (en) | Method and apparatus for recognizing gait task | |
US10575761B2 (en) | Method and apparatus for recognizing gait motion | |
US11219572B2 (en) | Method and apparatus for controlling a walking assistance apparatus | |
EP3166033A1 (en) | Walking assistance apparatus and method of controlling same | |
US11919156B2 (en) | Method and apparatus for recognizing user motion | |
US10835405B2 (en) | Method and apparatus for walking assist | |
JP6438579B2 (en) | Apparatus and method for determining a desired target | |
KR20160012537A (en) | Neural network training method and apparatus, data processing apparatus | |
US20180146890A1 (en) | Apparatus and method for recognizing gait state | |
US10548803B2 (en) | Method and device for outputting torque of walking assistance device | |
US20220142850A1 (en) | Method and apparatus for recognizing gait task | |
KR102046707B1 (en) | Techniques of performing convolutional neural network-based gesture recognition using inertial measurement unit | |
KR102018416B1 (en) | Device and system for monitoring micturition or ejaculation based on user's posture or change in posture, method of monitoring micturition or ejaculation, and computer-readable recording medium for implementing same method | |
KR101870542B1 (en) | Method and apparatus of recognizing a motion | |
JP7369783B2 (en) | Information processing method, program and information processing device | |
TWI505707B (en) | Abnormal object detecting method and electric device using the same | |
Ravindran et al. | Deictic option schemas | |
Bhattacharyya et al. | A Fall Detection System using Hybrid Inertial and Physiological Signal Classifiers for Dynamic Environments | |
KR20240061787A (en) | Method and apparatus for object tracking | |
Liang et al. | Studying the capture of stochastic events using radar and a mobile robot | |
Meriçli et al. | Dealing with Uncertainty in Structured Environments: A Robot Soccer Case Study | |
KR20210046219A (en) | Method and apparatus for detecting human interaction with an object | |
Merigli et al. | Dealing with Uncertainty in Structured Environments: A Robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |