Patents by Inventor SEHOON HA
SEHOON HA has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11608641Abstract: In a method for recycling energy from stairs, a step platform is moveable between an upper and lower position. An energy storage device, coupled to the platform, stores energy when a downward force is applied thereto, causing the step platform to move to the lower position. The energy storage device (also releases stored energy as the step platform moves from to the upper position. A controllable locking mechanism (locks the step platform in the lower position when the downward force has caused the step platform to move into the lower position. A sensor determines when a downward force has been applied to the next higher step platform. A controller signals the controllable locking mechanism to unlock the step platform when the step platform is in the lower position, and when the downward force has been applied to the next higher step platform.Type: GrantFiled: April 13, 2021Date of Patent: March 21, 2023Assignees: Georgia Tech Research Corporation, Emory UniversityInventors: Cheng-Yun Karen Liu, Sehoon Ha, Yun Seong Song, Lena Ting
-
Patent number: 11436441Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.Type: GrantFiled: December 17, 2019Date of Patent: September 6, 2022Assignee: GOOGLE LLCInventors: Jie Tan, Sehoon Ha, Tingnan Zhang, Xinlei Pan, Brian Andrew Ichter, Aleksandra Faust
-
Publication number: 20220143819Abstract: Techniques are disclosed that enable training a plurality of policy networks, each policy network corresponding to a disparate robotic training task, using a mobile robot in a real world workspace. Various implementations include selecting a training task based on comparing a pose of the mobile robot to at least one parameter of a real world training workspace. For example, the training task can be selected based on the position of a landmark, within the workspace, relative to the pose. For instance, the training task can be selected such that the selected training task moves the mobile robot towards the landmark.Type: ApplicationFiled: November 10, 2020Publication date: May 12, 2022Inventors: Jie Tan, Sehoon Ha, Peng Xu, Sergey Levine, Zhenyu Tan
-
Publication number: 20210277661Abstract: In a method for recycling energy from stairs, a step platform is moveable between an upper and lower position. An energy storage device, coupled to the platform, stores energy when a downward force is applied thereto, causing the step platform to move to the lower position. The energy storage device (also releases stored energy as the step platform moves from to the upper position. A controllable locking mechanism (locks the step platform in the lower position when the downward force has caused the step platform to move into the lower position. A sensor determines when a downward force has been applied to the next higher step platform. A controller signals the controllable locking mechanism to unlock the step platform when the step platform is in the lower position, and when the downward force has been applied to the next higher step platform.Type: ApplicationFiled: April 13, 2021Publication date: September 9, 2021Inventors: Cheng-Yun Karen Liu, Sehoon Ha, Yun Seong Song, Lena Ting
-
Publication number: 20210182620Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.Type: ApplicationFiled: December 17, 2019Publication date: June 17, 2021Inventors: Jie Tan, Sehoon Ha, Tingnan Zhang, Xinlei Pan, Brian Andrew Ichter, Aleksandra Faust
-
Patent number: 10975574Abstract: In a mechanism for recycling energy from stairs (200), a step platform (210) is moveable between an upper and lower position. An energy storage device (220), coupled to the platform (210), stores energy when a downward force is applied thereto, causing the step platform (210) to move to the lower position. The energy storage device (220) also releases stored energy as the step platform (210) moves from to the upper position. A controllable locking mechanism (240) locks the step platform (210) in the lower position when the downward force has caused the step platform (210) to move into the lower position. A sensor (250) determines when a downward force has been applied to the next higher step platform (250). A controller (300) signals the controllable locking mechanism (242) to unlock the step platform (250) when the step platform (250) is in the lower position and when the downward force has been applied to the next higher step platform (250).Type: GrantFiled: May 23, 2018Date of Patent: April 13, 2021Assignees: Georgia Tech Research Corporation, Emory UniversityInventors: Cheng-Yun Karen Liu, Sehoon Ha, Yun Seong Song, Lena Ting
-
Publication number: 20200149285Abstract: In a mechanism for recycling energy from stairs (200), a step platform (210) is moveable between an upper and lower position. An energy storage device (220), coupled to the platform (210), stores energy when a downward force is applied thereto, causing the step platform (210) to move to the lower position. The energy storage device (220) also releases stored energy as the step platform (210) moves from to the upper position. A controllable locking mechanism (240) locks the step platform (210) in the lower position when the downward force has caused the step platform (210) to move into the lower position. A sensor (250) determines when a downward force has been applied to the next higher step platform (250). A controller (300) signals the controllable locking mechanism (242) to unlock the step platform (250) when the step platform (250) is in the lower position and when the downward force has been applied to the next higher step platform (250).Type: ApplicationFiled: May 23, 2018Publication date: May 14, 2020Inventors: Cheng-Yun Karen Liu, Sehoon Ha, Yun Seong Song, Lena Ting
-
Patent number: 10248085Abstract: A robot design system, and associated method, that is particularly well-suited for legged robots (e.g., monopods, bipeds, and quadrupeds). The system implements three stages or modules: (a) a motion optimization module; (b) a morphology optimization module; and (c) a link length optimization module. The motion optimization module outputs motion trajectories of the robot's center of mass (COM) and force effectors. The morphology optimization module uses as input the optimized motion trajectories and a library of modular robot components and outputs an optimized robot morphology, e.g., a parameterized mechanical design in which the number of links in each of the legs and other parameters are optimized. The link length optimization module takes this as input and outputs optimal link lengths for a particular task such that the design of a robot is more efficient. The system solves the problem of automatically designing legged robots for given locomotion tasks by numerical optimization.Type: GrantFiled: October 13, 2016Date of Patent: April 2, 2019Assignee: DISNEY ENTERPRISES, INC.Inventors: Sehoon Ha, Alexander Nicholas Alspach, Joohyung Kim, Katsu Yamane, Stelian Coros
-
Publication number: 20180107175Abstract: A robot design system, and associated method, that is particularly well-suited for legged robots (e.g., monopods, bipeds, and quadrupeds). The system implements three stages or modules: (a) a motion optimization module; (b) a morphology optimization module; and (c) a link length optimization module. The motion optimization module outputs motion trajectories of the robot's center of mass (COM) and force effectors. The morphology optimization module uses as input the optimized motion trajectories and a library of modular robot components and outputs an optimized robot morphology, e.g., a parameterized mechanical design in which the number of links in each of the legs and other parameters are optimized. The link length optimization module takes this as input and outputs optimal link lengths for a particular task such that the design of a robot is more efficient. The system solves the problem of automatically designing legged robots for given locomotion tasks by numerical optimization.Type: ApplicationFiled: October 13, 2016Publication date: April 19, 2018Inventors: SEHOON HA, ALEXANDER NICHOLAS ALSPACH, JOOHYUNG KIM, KATSU YAMANE, STELIAN COROS