Apparatus and method for recognizing gait motion

• US 9,737,240 B2
• Filed: 12/01/2014
• Issued: 08/22/2017
• Est. Priority Date: 07/29/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Jang, Jun-Won, Kim, Kyung-Rock, Shim, Youngbo, Lee, Jusuk, Lim, Bokman
• Primary Examiner(s): Stout, Michael C
• Assistant Examiner(s): Kolderman, Nicholas E
• Application Number:
  US14/556,841
• Publication Number:
  US 20160029928A1
• Time in Patent Office: 995 Days
• CPC Class Codes: A61B 5/112 Gait analysis
• CPC Class Codes: A61B 5/1122 of movement trajectories
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61H 1/0244 Hip A61H1/0255 takes precedence
• CPC Class Codes: A61H 2201/165 Wearable interfaces
• CPC Class Codes: A61H 2201/5058 Sensors or detectors
• CPC Class Codes: A61H 2201/5061 Force sensors
• CPC Class Codes: A61H 2201/5069 Angle sensors
• CPC Class Codes: A61H 2201/5079 Velocity sensors
• CPC Class Codes: A61H 2201/5084 Acceleration sensors
• CPC Class Codes: A61H 3/00 Appliances for aiding patients or disabled persons to walk about apparatus for helping babies to walk A47D13/04; orthopaedic devices for correcting deformities of, or supporting, limbs A61F5/0102; exercising apparatus for the feet or toes A63B23/10; stairways or ramps E04F11/00
• CPC Class Codes: G07C 1/22 in connection with sports or games

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.

Claims

1. An apparatus for recognizing a gait motion, the apparatus comprising:

at least one sensor configured to sense acceleration information and right and left hip joint angle information of a user;

a controller configured to,

detect a landing point in time of a foot of the user based on the sensed acceleration information, the landing point in time is a time point at which a foot of the user lands, and further 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,

infer a gait motion based on the sensed right and left hip joint angle information of the user, the right and left hip joint angle information sensed at the landing point in time,

detect a landing leg between both legs of the user based on the inferred gait motion, and

output a control signal based on at least one of the inferred gait motion and the detected landing leg; and

a driver configured to drive a hip joint of the user based on the control signal.

2. The apparatus of claim 1, wherein the sensed 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, wherein the base horizon is set to follow a freeze horizon set from a previous landing point in time.

5. The apparatus of claim 1, wherein the controller is further 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.

6. The apparatus of claim 1, wherein the controller is further configured to infer the gait motion using a fuzzy logic.

7. The apparatus of claim 6, wherein the controller is further configured to infer the gait motion by performing defuzzification based on a fuzzy rule and a value obtained by fuzzification of the sensed right and left hip joint angle information using a member function, and

the member function is set based on the sensed right and left hip joint angle information.

8. The apparatus of claim 1, wherein the controller is further 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 sensed 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.

9. The apparatus of claim 1, wherein the controller is further 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 sensed right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.

10. A walking assistance apparatus comprising:

a driving mechanism configured to drive a right hip joint and a left hip joint of a user;

a sensor 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

detect a landing point in time of a foot of the user based on the sensed acceleration information,

infer a gait motion of the user based on the right and left hip joint angle information of the user sensed at the detected landing point in time of the foot of the user,

detect a landing leg based on the inferred gait motion, and

control the driving mechanism based on at least one of the inferred gait motion of the user and the detected landing leg,

wherein the controller 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.

11. The apparatus of claim 10, wherein the controller is further configured to infer the gait motion using a fuzzy logic.

12. The apparatus of claim 10, wherein the controller is further 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 sensed 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

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 sensed right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.

13. A method of recognizing a gait motion, the method comprising:

sensing, by at least one sensor, acceleration information of a user;

detecting, by a controller, a landing point in time of a foot of a user based on the sensed acceleration information;

sensing, by the at least one sensor, right and left hip joint angle information of the user at the detected landing point in time of the foot of the user;

inferring, by the controller, a gait motion based on the sensed right and left hip joint angle information of the user;

detecting, by the controller, a landing leg between both legs of the user based on the inferred gait motion;

outputting a control signal based on at least one of the inferred gait motion and the detected landing leg; and

driving a hip joint of the user based on the control signal,

wherein the detecting a landing point in time includes 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.

14. The method of claim 13, wherein the inferring comprises inferring the gait motion by performing defuzzification based on a fuzzy rule and a value obtained by fuzzification of the sensed right and left hip joint angle information using a member function, and

the member function is set based on the sensed right and left hip joint angle information.

15. The method of claim 13, 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 sensed 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 sensed right and left hip joint angle information when the inferred gait motion corresponds to a walking motion in a downward inclined direction.