首页|Findings from Xiamen University Reveals New Findings on Robotics (Solving Roboti c Trajectory Sequential Writing Problem Via Learning Character's Structural and Sequential Information)
Findings from Xiamen University Reveals New Findings on Robotics (Solving Roboti c Trajectory Sequential Writing Problem Via Learning Character's Structural and Sequential Information)
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-New research on Robotics is the subjec t of a report. According to news reportingoriginating from Xiamen, People's Rep ublic of China, by NewsRx correspondents, research stated, "Thewriting sequence of numerals or letters often affects aesthetic aspects of the writing outcomes. As such,it remains a challenge for robotic calligraphy systems to perform, mim icking human writers' implicitintention."Financial supporters for this research include Natural Science Foundation of Fuj ian Province, StrategicPartner Acceleration Award under the Ser Cymru II Progra mme, U.K..Our news editors obtained a quote from the research from Xiamen University, "Thi s article presents anew robot calligraphy system that is able to learn writing sequences with limited sequential information,producing writing results compati ble to human writers with good diversity. In particular, the systeminnovatively applies a gated recurrent unit (GRU) network to generate robotic writing action s with thesupport of a prelabeled trajectory sequence vector. Also, a new evalu ation method is proposed thatconsiders the shape, trajectory sequence, and stru ctural information of the writing outcome, therebyhelping ensure the writing qu ality. A swarm optimization algorithm is exploited to create an optimal setof p arameters of the proposed system. The proposed approach is evaluated using Arabi c numerals, andthe experimental results demonstrate the competitive writing per formance of the system against state-ofthe-art approaches regarding multiple cr iteria (including FID, MAE, PSNR, SSIM, and PerLoss), as wellas diversity perfo rmance concerning variance and entropy."
XiamenPeople's Republic of ChinaAsiaEmerging TechnologiesLeisureMachine LearningRoboticsRobotsXiamen Uni versity
NETL
NSTL
