首页|Findings from University of Utah Provides New Data about Robotics (Accounting fo r Hysteresis In the Forward Kinematics of Nonlinearly-routed Tendon-driven Conti nuum Robots Via a Learned Deep Decoder Network)
Findings from University of Utah Provides New Data about Robotics (Accounting fo r Hysteresis In the Forward Kinematics of Nonlinearly-routed Tendon-driven Conti nuum Robots Via a Learned Deep Decoder Network)
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 reportingout of Salt Lake City, Utah, by NewsR x editors, research stated, "Tendon-driven continuum robots havebeen gaining po pularity in medical applications due to their ability to curve around complex an atomicalstructures, potentially reducing the invasiveness of surgery. However, accurate modeling is required to planand control the movements of these flexibl e robots."Financial supporters for this research include Natural Sciences and Engineering Research Council ofCanada (NSERC), National Science Foundation (NSF).Our news journalists obtained a quote from the research from the University of U tah, "Physics-basedmodels have limitations due to unmodeled effects, leading to mismatches between model prediction andactual robot shape. Recently proposed l earning-based methods have been shown to overcome some of theselimitations but do not account for hysteresis, a significant source of error for these robots. T o overcomethese challenges, we propose a novel deep decoder neural network that predicts the complete shape oftendon-driven robots using point clouds as the s hape representation, conditioned on prior configurationsto account for hysteres is."
Salt Lake CityUtahUnited StatesNor th and Central AmericaEmerging TechnologiesMachine LearningNano-robotRob otRoboticsUniversity of Utah
NETL
NSTL
