|
Development of Myoelectric Hand Prosthesis Cover with Grip Force Recognition Function |
|
Sung Yoon Jung, Hyunjun Shin, Seung Gi Kim, Se Hoon Park(Korea Orthopedics & Rehabilitation Engineering Center, Korea) |
| In this study, we developed a myeoelectic hand prosthesis cover including a sensory recognitive function which closely mimics human hand skin. The proposed cover was made of flexible silicon to mimic the human hand skin, which can measure a grip force of less than 50 N using a tactile sensing module. The tactile sensing module was developed using a force-sensitive resistor sensor, and solid silicone vacuum compression molding by embedding the sensor and wires inside the cover was introduced for the fabrication process. From the experiment, we can suggest that the developed cover with sensory recognition can be directly applied to multi-DOF myoelectric hand prostheses. |
|
|
Performance Comparison of Reinforcement Learning Algorithms for Autonomous Navigation of Outdoor Mobile Robots |
|
Hoeryong Jung, Sanghun Lee, Jinwoo Mok, YunFeng Han, Joonseo Kim(Konkuk University, Korea) |
|
|
A Study on the Comparison of Transfer Rate Depending on the Number of Concurrent Clients in a Multi-robot System |
|
Jaeho Yang, Chunsung Park, MyungSik Ji(CLOBOT Co., Ltd, Korea) |
| In this paper compared the data transfer rate according to the characteristics of each communication method and number of clients for stable wireless communication between different system robots and robot control systems in robot industry. In communication between robot and server, data is transmitted and received by composing commands, robot status, sensor data, etc. in message format. In this paper, we propose GRPC as a wireless communication method in the field of multi-robot systems and robot control systems that require concurrent connection of many clients. |
|
|
Multiple LiDARs Fusion for Human Gait Tracking |
|
Toan Huu Duong, Young Soo Suh(University of Ulsan, Korea) |
| This paper proposes a multiple 2D LiDARs system for human gait tracking. This system is to compensate
the drawbacks of a single LiDAR system which has short tracking range and could lose leg scan data due to the occlusion between legs. We model the LiDAR measurement data with distance measurement noises which are proportional to
the measured distance. This model is used in calibration process and human leg center point estimation. With a new
calibration method that uses a cylinder, we estimate the relative parameters between the LiDARs and combine all scan
data to estimate the legs center points. |
|
|
QDD-TC: A Quasi-Direct-Drive Two-DOF Parallel-Elastic Mechanism with Tunable Compliance |
|
Sajiv Shah(Saratoga High School, United States) |
| QDD-TC: A Quasi-Direct-Drive Two-DOF Parallel-Elastic Mechanism with Tunable Compliance |
|
|
Discovering Low-Dimensional Data Structures Using Normalizing Flows with a Parametric Latent Distribution |
|
Eric Young-Uk Jin, Seokhyeon Kim, Sangwoong Yoon, Frank Chongwoo Park(Seoul National University, Korea) |
| This paper scrutinizes the aspect of normalizing flows that fetters their flexibility; a non-parametric latent distribution. Based on this analysis, a new normalizing flow model, whose latent distribution is parametric, is proposed. The presented model effectively learns and exploits the low-dimensional structure within the space of data, and accordingly, requires few resources to train it. |
|