Human activity recognition (HAR) has been actively researched in fields such as healthcare to understand and analyze human behavior in human-robot interaction. However, most studies have struggled to recognize activities like turning and motion transitions, which are often associated with dynamic balance. Therefore, we propose a novel HAR approach using a single sensor to collect and early fuse motion and position data. The aim is to enhance the accuracy of motion classification for daily activities and those that cause imbalance, which have traditionally been difficult to recognize. We constructed a quarantine room environment for data collection and to evaluate the impact of the suggested features on behavior. Five deep learning models were trained and evaluated to identify the optimal model. The collected data was classified and analyzed by the selected model, which demonstrated an average accuracy of 98.96%.
This paper presents an improved input shaping method to eliminate vibration during circular interpolation of a flexible 2-axis positioning system. Due to the time delay introduced by input shaping, simultaneous 2-axis positioning with circular interpolation results in a certain amount of errors from the intended track or trajectory. This study investigated the track errors associated with circular interpolation caused by input shaping for a flexible 2-axis positioning system. The following three strategies for reducing such errors were proposed: velocity reduction in circular interpolation, adjustment of the time delay between 2 axes commands, and employment of a velocity profile compensation function. Simulations were performed to discuss the pros and cons of the three proposed strategies. Experiments were also performed to validate the results. Simulation and experiments showed that the track errors due to input shaping can be sufficiently reduced by combined use of the proposed strategies.
Citations
Citations to this article as recorded by
A Study on the Improvement of Machining Precision by Applying Input Shaping Method to Machining Center Kang-Ho Ko, Dong-Wook Lim, Seong-Wook Hong Journal of the Korean Society of Manufacturing Technology Engineers.2023; 32(4): 189. CrossRef
Input-shaping-based improvement in the machining precision of laser micromachining systems Dong-Wook Lim, Seong-Wook Hong, Seok-Jae Ha, Ji-Hun Kim, Hyun-Taek Lee The International Journal of Advanced Manufacturing Technology.2023; 125(9-10): 4415. CrossRef
Application of Input Shaping to a CNC Laser Processing Machine to Enhance Processing Precision Kang Ho Ko, Jin Uk Sim, Seong-Wook Hong Journal of the Korean Society of Manufacturing Technology Engineers.2022; 31(5): 346. CrossRef
This paper proposes an IMU method for location tracking in power plants and indoor environments without GPS. IMU-based sensors use accelerometer, angular accelerometer, earth magnetometer, and altimeter. It is a method for recognizing the movement of pedestrians or moving objects. However, errors can be caused, as noise and bias increase due to long-term measurement. VIO-SLAM type sensor T265, which uses a combination of cameras and IMU, and can accurately track paths in invisible spaces, is used in this study. In addition, this type of sensor can be corrected in real time with a filter function inserted into the sensor and errors can be minimized. As a comparison experiment with the encoder, it is possible to evaluate the location of the scanner within a ±10 mm error from the actual distance in 1,500 × 700 (mm) space. The usefulness of this method is verified by measuring real specimens of boiler pipes and tubes, which are the major components of power plants.
Most positioning systems experience residual vibration during operation. Such residual vibration can be eliminated or reduced to an acceptable level by using the input shaping method. However, adopting the input shaping methods typically introduces a certain amount of time-delay into a system. This study focused on the development of a delay-time adjustable input shaping method to eliminate vibration caused by repetitive motion in positioning systems. The proposed input shaping method, called the virtual mode (VM) input shaper, uses a virtual frequency parameter that adjusts delay-time and cancels residual vibration. Unlike most previous input shaping studies, this study investigated VM input shaping performance to eliminate the steady-state vibration induced by repetitive motion in positioning systems. To this end, an analytical formulation was derived and used for simulating the input shaping performance with varying dominant parameters involved in a system. Experiments were also performed to validate the proposed method.
Citations
Citations to this article as recorded by
Data Driven Vibration Control: A Review Weiyi Yang, Shuai Li, Xin Luo IEEE/CAA Journal of Automatica Sinica.2024; 11(9): 1898. CrossRef
Improved Input Shaping Method for Circular Interpolation of a 2-Axis Positioning System Jin Uk Sim, Pil Kyu Choi, Sun-Woong Kwon, Seong-Wook Hong Journal of the Korean Society for Precision Engineering.2022; 39(4): 283. CrossRef
Application of Input Shaping to a CNC Laser Processing Machine to Enhance Processing Precision Kang Ho Ko, Jin Uk Sim, Seong-Wook Hong Journal of the Korean Society of Manufacturing Technology Engineers.2022; 31(5): 346. CrossRef
This paper introduces a new outdoor localization method for practical application to guide robots. This method uses only encoder data from the robot’s wheels and non-inertial sensors, such as GPS and a digital compass, to guarantee ease of use and economy in real world usage without cumulative error. Position and orientation information from DGPS (Differential Global Positioning System) and a digital compass are combined with encoder data from the robot’s wheels to more accurately estimate robot position using an extended Kalman filter. Conventional robot guidance methods use different types of fusion that rely on DGPS. We use a very simple and consistent method that ensures localization stability by using the validation gate to evaluate DGPS reliability and digital compass data that can be easily degraded by various noise sources. Experimental results of the localization are presented that show the feasibility and effectiveness of the methods using a real robot in real world conditions.
Citations
Citations to this article as recorded by
Indoor Localization of a Mobile Robot based on Unscented Kalman Filter Using Sonar Sensors Soo Hee Seo, Jong Hwan Lim Journal of the Korean Society for Precision Engineering.2021; 38(4): 245. CrossRef
Unscented Kalman Filter Based 3D Localization of Outdoor Mobile Robots Woo Seok Lee, Min Ho Choi, Jong Hwan Lim Journal of the Korean Society for Precision Engineering.2020; 37(5): 331. CrossRef
Estimation of Vertical Displacement based on Inertial Sensor Signals Combined with Joint Constraint Jung Keun Lee Journal of the Korean Society for Precision Engineering.2019; 36(3): 233. CrossRef
Kinematic Constraint-Projected Kalman Filter to Minimize Yaw Estimation Errors Induced by Magnetic Distortions Tae Hyeong Jeon, Jung Keun Lee Journal of the Korean Society for Precision Engineering.2019; 36(7): 659. CrossRef
Extended Kalman Filter Based 3D Localization Method for Outdoor Mobile Robots Woo Seok Lee, Min Ho Choi, Jong Hwan Lim Journal of the Korean Society for Precision Engineering.2019; 36(9): 851. CrossRef
Unscented Kalman Filter based Outdoor Localization of a Mobile Robot Woo Seok Lee, Jong Hwan Lim Journal of the Korean Society for Precision Engineering.2019; 36(2): 183. CrossRef
Dynamic Accuracy Improvement of a MEMS AHRS for Small UAVs Min-Shik Roh, Beom-Soo Kang International Journal of Precision Engineering and Manufacturing.2018; 19(10): 1457. CrossRef
Study on Robust Lateral Controller for Differential GPS-Based Autonomous Vehicles Hyung-Gyu Park, Kyoung-Kwan Ahn, Myeong-Kwan Park, Seok-Hee Lee International Journal of Precision Engineering and Manufacturing.2018; 19(3): 367. CrossRef
GPS-Based Human Tracking Methods for Outdoor Robots Woo Seok Lee, In Ho Cho, Jong Hwan Lim Journal of the Korean Society for Precision Engineering.2018; 35(4): 413. CrossRef
First
Prev
