首页|New Findings in Robotics Described from Xingtai (Design and research of an autom atic grasping system for a robotarm based on visual image capture technology)
New Findings in Robotics Described from Xingtai (Design and research of an autom atic grasping system for a robotarm based on visual image capture technology)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on ro botics. According to news originating fromXingtai, People’s Republic of China, by NewsRx correspondents, research stated, “Traditional robotic armsrely on com plex programming and predefined trajectories to operate, which limits their appl icability.”Our news correspondents obtained a quote from the research from Department of Me chanical Engineering:“To improve the flexibility and adaptability of the robot arm, the research focuses on improvingthe grasping performance of the robot arm based on vision technology. Kinect technology is used tocapture human arm move ments, and Kalman filter is introduced to smooth image data, so as to optimizet he motion recognition process. In this study, the residual network model is furt her improved, and ELUactivation function and pre-activation mechanism are intro duced to enhance the classification accuracy ofgesture images. The results show ed that the improved ResNet50 model achieves 95% recognition accuracy after 25 iterations of training, while the original model is 80% . The application of Kalman filtermakes the motion tracking curve smoother and shows the correction effect of this method. In simulationtests, the robotic arm is able to identify different elbow bending angles with 90-96 percent accuracy, whilemimicking five specific hand gestures with 96-98 percent accuracy.”
Department of Mechanical EngineeringXingtaiPeople’s Republic of ChinaAsiaEmerging TechnologiesMachine LearningRobotRoboticsRobotsTechnology
NETL
NSTL
