首页|Researchers at University of California Los Angeles (UCLA) Target Robotics (Dismech: a Discrete Differential Geometry-based Physical Simulator for Soft Robots and Structures)
Researchers at University of California Los Angeles (UCLA) Target Robotics (Dismech: a Discrete Differential Geometry-based Physical Simulator for Soft Robots and Structures)
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 - Data detailed on Robotics have been pr esented. According to news originating fromLos Angeles, California, by NewsRx c orrespondents, research stated, “Fast, accurate, and generalizablesimulations a re a key enabler of modern advances in robot design and control. However, existi ng simulationframeworks in robotics either model rigid environments and mechani sms only, or if they include flexible orsoft structures, suffer significantly i n one or more of these performance areas.”Financial support for this research came from National Science Foundation (NSF).Our news journalists obtained a quote from the research from the University of C alifornia Los Angeles(UCLA), “To close this ‘sim2real’ gap, we introduce DisMec h, a simulation environment that models highlydynamic motions of rod-like soft continuum robots and structures, quickly and accurately, with arbitraryconnecti ons between them. Our methodology combines a fully implicit discrete differentia l geometrybasedphysics solver with fast and accurate contact handling, all in an intuitive software interface. Crucially,we propose a gradient descent approa ch to easily map the motions of hardware robot prototypes to controlinputs in D isMech. We validate DisMech through several highly-nuanced soft robot simulation s whiledemonstrating an order of magnitude speed increase over previous state o f the art. Our real2sim validationshows high physical accuracy versus hardware, even with complicated soft actuation mechanisms such asshape memory alloy wires.”
Los AngelesCaliforniaUnited StatesNorth and Central AmericaEmerging TechnologiesMachine LearningNano-robotRobotRoboticsUniversity of California Los Angeles (UCLA)
NETL
NSTL
