New Findings on Robotics Described by Investigators at Southeast University (Fot s: a Fast Optical Tactile Simulator for Sim2real Learning of Tactile-motor Robot Manipulation Skills)
New Findings on Robotics Described by Investigators at Southeast University (Fot s: a Fast Optical Tactile Simulator for Sim2real Learning of Tactile-motor Robot Manipulation Skills)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on Ro botics. According to news reporting out of Nanjing, People’s Republic of China, by NewsRx editors, research stated, “Simulation is a widely used tool in robotic s to reduce hardware consumption and gather large-scale data. Despite previous e fforts to simulate optical tactile sensors, there remain challenges in efficient ly synthesizing images and replicating marker motion under different contact loa ds.” Financial support for this research came from Zhejiang Lab. Our news journalists obtained a quote from the research from Southeast Universit y, “In this work, we propose a fast optical tactile simulator, named FOTS, for s imulating optical tactile sensors. We utilize multi-layer perceptron mapping and planar shadow generation to simulate the optical response, while employing mark er distribution approximation to simulate the motion of surface markers caused b y the elastomer deformation. Experimental results demonstrate that FOTS outperfo rms other methods in terms of image generation quality and rendering speed, achi eving 28.6 fps for optical simulation and 326.1 fps for marker motion simulation on a single CPU without GPU acceleration.”
Key words
Nanjing/People’s Republic of China/Asi a/Emerging Technologies/Machine Learning/Robot/Robotics/Southeast Universit y
NETL
NSTL