http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
멀티비전을 이용한 실시간 테니스 공 궤적 및 낙하지점 예측방법
양요셉(Yo Seph Yang),최동일(Dongil Choi) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.11
Recently, the development of robots that can exercise and play sports with humans is actively progressing. In sports such as tennis and table tennis, it is important to predict the trajectory of a moving ball to receive the ball. The problem of predicting the trajectory of a ball using robot camera images is a topic that is being actively studied in the field of computer vision. In this paper, we introduce a tennis ball trajectory prediction method using a multi-vision system. In order to predict the trajectory of the ball, the identification of the position and speed of the tennis ball must be prioritized. Our multi vision system sets up two cameras and estimates ball position and landing point in real-time through object detection. The performance of the proposed method was evaluated through Gazebo simulation. As a result of predicting landing points for 500 samples with a tennis ball speed of 65 to 90 km/h, the x-axis error MAE is 0.3 m, the RMSE is 0.406 m, the y-axis error MAE is 0.065 m, and the RMSE is 0.119 m.
양요셉(Yo Seph Yang),안성민(Seongmin Ahn),김성현(Seong Hyeon Kim),최동일(Dongil Choi) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Recently, as the service robot market has grown, robots have emerged in various fields such as industry, service, and sports. In the field of sports, robots that can play with humans such as Forpheus, Robomintoner, and Ldric have been developed. These robots can act as coaches by providing human race data as well as athletic events. We developed a vision system that detects balls and predicts trajectories to develop tennis sports robots. In this paper, we introduce ball detection artificial neural networks and ball trajectory prediction using stereo vision. As a result, the accuracy of the neural network for ball detection in actual tennis images reaches 81%. The ball trajectory prediction error in Gaz ebo simulation is 29.6 cm in the x-axis, 7.2 cm in the y-axis, and 11.7 cm in the z-axis on average.
양요셉(Yo Seph Yang),안성민(Seongmin Ahn),김성현(Seong Hyeon Kim),최동일(Dongil Choi) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Recently, as the service robot market has grown, robots have emerged in various fields such as industry, service, and sports. In the field of sports, robots that can play with humans such as Forpheus, Robomintoner, and Ldric have been developed. These robots can act as coaches by providing human race data as well as athletic events. We developed a vision system that detects balls and predicts trajectories to develop tennis sports robots. In this paper, we introduce ball detection artificial neural networks and ball trajectory prediction using stereo vision. As a result, the accuracy of the neural network for ball detection in actual tennis images reaches 81%. The ball trajectory prediction error in Gaz ebo simulation is 29.6 cm in the x-axis, 7.2 cm in the y-axis, and 11.7 cm in the z-axis on average.
CMG Unicycle-Legged Robot의 개발과 Decoupled 최적제어
신승철(Seung Chul Shin),허성용(Seong Yong Hur),양요셉(Yo Seph Yang),최동일(Dong Il Choi) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
The wheeled-legged robot has excellent stable flat driving and ability to overcome obstacles. However, when faced with a narrow footprint, there is a limit to the ability to move. To solve this problem, we developed a CMG (control moment gyroscope) unicycle robot. A scissored pair of CMG was applied to control the roll direction balance, and the pitch direction balance was controlled assuming that the robot was a double inverted pendulum. In a system where the control systems in the roll direction and the pitch direction were decoupled, LQR and MPC optimal control were performed, and the performance of these controllers was verified as gazebo simulator.
CMG Unicycle-Legged Robot의 개발과 Decoupled 최적제어
신승철(Seung Chul Shin),허성용(Seong Yong Hur),양요셉(Yo Seph Yang),최동일(Dong Il Choi) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
The wheeled-legged robot has excellent stable flat driving and ability to overcome obstacles. However, when faced with a narrow footprint, there is a limit to the ability to move. To solve this problem, we developed a CMG (control moment gyroscope) unicycle robot. A scissored pair of CMG was applied to control the roll direction balance, and the pitch direction balance was controlled assuming that the robot was a double inverted pendulum. In a system where the control systems in the roll direction and the pitch direction were decoupled, LQR and MPC optimal control were performed, and the performance of these controllers was verified as gazebo simulator.