• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.4
• /
• pp.154-161
• /
• 2014

In this research we investigate motion controller performance for mobile robots according to changes in the control loop sampling time. As a result, we suggest a proper range of the sample time, which can minimize final posture errors while improving tracking capability of the controller. For controller implementation into real mobile robots, we use a smooth and continuous motion controller, which can respect robot's path curvature limitation. We examine motion control performance in experimental tests while changing the control loop sampling time. Toward this goal, we compare and analyze experimental results using two different mobile robot platforms; one with real-time control and powerful hardware capability and the other with non-real-time control and limited hardware capability.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.2_2
• /
• pp.249-254
• /
• 2023

The use of robots in automated factories requires accurate bin-picking to ensure that objects are correctly identified and selected. In the case of atypical objects with multiple reflections from their surfaces, this is a challenging task. In this paper, we developed a random 3D bin picking system by integrating the low-cost vision system with the robotics system. The vision system identifies the position and posture of candidate parts, then the robot system validates if one of the candidate parts is pickable; if a part is identified as pickable, then the robot will pick up this part and place it accurately in the right location.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.5
• /
• pp.67-73
• /
• 2017

We propose several techniques which can be employed in a 3D fitness program for monitoring and correcting user's posture. To implement a 3D fitness program, improved reference motion generating techniques and visualizing techniques are necessary. First, in order to understand the difference between the user and the reference movement of a professional, a retargeting method between two different body shapes are studied. Second, the problem of self-occlusion, which occurs when using a low-cost depth sensor to represent complex motions, is solved by using a sample database and time consistency. The system proposed in this paper evaluates the user's posture considering the physical characteristics of the user, and then provides feedback to the user.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.5
• /
• pp.157-166
• /
• 2022

Exercise is necessary for a healthy life, but it is recommended that it be conducted in a non-face-to-face environment in the context of an epidemic such as COVID-19. However, in the existing non-face-to-face exercise content, it is possible to recognize exercise movements, but the process of interpreting and providing feedback information is not automated. Therefore, in this paper, to solve this problem, we propose a method of creating a formalized rule to track the contents of exercise and the motions that constitute it. To make such a rule, first make a rule for the overall exercise content, and then create a tracking rule for the motions that make up the exercise. A motion tracking rule can be created by dividing the motion into steps and defining a key frame pose that divides the steps, and creating a transition rule between states and states represented by the key frame poses. The rules created in this way are premised on the use of posture and motion recognition technology using motion capture equipment, and are used for logical development for automation of application of these technologies. By using the rules proposed in this paper, not only recognizing the motions appearing in the exercise process, but also automating the interpretation of the entire motion process, making it possible to produce more advanced contents such as an artificial intelligence training system. Accordingly, the quality of feedback on the exercise process can be improved.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1099-1104
• /
• 2003

In this paper, the position control of a car-like mobile robot using neural network is proposed. The positional information of the mobile robot is given by a laser range finder located remotely through wireless communication. The heading angle is measured by a gyro sensor. Considering these two sensor information as references, the robot posture by localization is corrected by a cascaded controller. In order to improve the tracking performance, a neural network with a cascaded controller is used to compensate for any uncertainty in the robot. The remotely located neural network filter modifies the reference trajectories to minimize the positional errors by wireless communication. A car-like mobile robot is built as a test-bed and experimental studies of proposed several control algorithms are performed. It turns out that the best position control can be achieved by a cascaded controller with neural network.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.269-276
• /
• 2011

This paper proposes a novel control method using phase plane for a hydraulic biped humanoid robot. In biped walking control, it is much more difficult to control the posture of a biped robot in the coronal plane because the supporting area formed by the both feet in the coronal plane is much narrower than that of the sagittal plane. When the biped robot walks stably, the phase portrait of the pelvis in the coronal plane makes an elliptical shape. From this point of view, we develop an ankle torque controller and a foot placement controller for tracking the desired phase portrait during walking. We design these controllers by using simulations of a simplified compass gait biped model to regulate the desired phase portrait of pelvis. The effectiveness of the proposed control method is proved through full-body dynamic walking simulations and real experiments of the SARCOS hydraulic biped humanoid.

• Journal of Drive and Control
• /
• v.18 no.2
• /
• pp.20-31
• /
• 2021

An excavator is a construction machine that can perform various tasks such as trenching, piping, excavating, slope cutting, grading, and rock demolishing. In the 2010s, unmanned construction equipment using ICT technology was continuously developed. In this paper, the path design process was studied to implement the output data of the decision stage, and the path design algorithm was developed. For example, the output data of the decision stage were terrain data around the excavator, excavator mechanism information, excavator hydraulic information, the position and posture of the bucket at key points, the speed of the desired bucket path, and the required excavation volume. The result of the path design was the movement of the hydraulic cylinder, boom arm, bucket, and bucket edge. The core functions of the path design algorithm are the function of avoiding impact during the excavation process, the function to calculate the excavation depth that satisfies the required excavation volume, and the function that allows the bucket to pass through the main points of the excavation process while maintaining the speed of the desired path. In particular, in the process of developing the last function, the node tracking method expressed in the path design table was newly developed. The path design algorithm was verified as this path design satisfied the JCMAS H02 requirement.

• Electronics and Telecommunications Trends
• /
• v.37 no.2
• /
• pp.30-41
• /
• 2022

As the society is superaging, the number of patients with movement disabilities due to musculoskeletal or nervous system illness is rapidly increasing. To improve public health and reduce medical expenses, it is essential to develop rehabilitation systems that allow patients to resume their daily-life activities. However, the existing musculoskeletal illness diagnosis and rehabilitation method is limited in terms of precision and efficiency because it is based on an empirical diagnosis and prescription without regard for individual characteristics. To overcome these limits, it is critical to design a novel concept of routine rehabilitation therapy device that is capable of inducing musculoskeletal balance by the precise analysis of musculoskeletal usage patterns via the motion and the muscle activity tracking of linked muscles. This study introduces the trend of on-skin sensor device technology for routine musculoskeletal monitoring and therapy. For on-skin rehabilitation systems, skin-adhesive and stretchable motion/posture, electromyography, pressure sensors, small-size and low-power wireless sensor interfaces, and user-friendly rehabilitation contents based on new algorithms are combined.

• The Journal of Korean Physical Therapy
• /
• v.33 no.1
• /
• pp.47-52
• /
• 2021

Purpose: Biofeedback using various ways has helped correct the sitting posture. This study compared the multifidus muscle activity, pelvic and 2nd sacrum tilting angle during typing in nonspecific lower back pain (NCLBP) subjects with and without visual biofeedback. Methods: Thirty subjects with NCLBP were enrolled in this study. An electromyography device was used to measure the multifidus muscle activity. An electromagnetic tracking motion device was used to measure the pelvic and 2nd sacrum tilting angle. The multifidus muscle activity, pelvic, and 2nd sacrum tilting angle were measured before and after typing for 30 minutes in the sitting position. An independent t-test was used to compare the changing values for 30 minutes between the group with and without visual biofeedback. Results: The changing values of the multifidus muscle activity, pelvic, and 2nd sacrum tilting angle were significantly smaller in the group with visual biofeedback than the group without visual biofeedback (p<0.05). Conclusions: In subjects with NCLBP, the visual biofeedback can be recommended to maintain the multifidus muscle activity, pelvic, and 2nd sacrum tilting angle during typing for 30 minutes.