首页|New Robotics Findings from King's College London Outlined (Marker or Markerless? Mode-switchable Optical Tactile Sensing for Diverse Robot Tasks)
New Robotics Findings from King's College London Outlined (Marker or Markerless? Mode-switchable Optical Tactile Sensing for Diverse Robot Tasks)
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
2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Robotics. According to news reporting originating from London, United Kingdom, b y NewsRx correspondents, research stated, "Optical tactile sensors play a pivota l role in robot perception and manipulation tasks. The membrane of these sensors can be painted with markers or remain markerless, enabling them to function in either marker or markerless mode." Funders for this research include National Natural Science Foundation of China ( NSFC), Engineering & Physical Sciences Research Council (EPSRC). Our news editors obtained a quote from the research from King's College London, "However, this uni-modal selection means the sensor is only suitable for either manipulation or perception tasks. While markers are vital for manipulation, they can also obstruct the camera, thereby impeding perception. The dilemma of selec ting between marker and markerless modes presents a significant obstacle. To add ress this issue, we propose a novel mode-switchable optical tactile sensing appr oach that facilitates transitions between the two modes. The marker-to-markerles s transition is achieved through a generative model, whereas its inverse transit ion is realized using a sparsely supervised regressive model. Our approach allow s a single-mode optical sensor to operate effectively in both marker and markerl ess modes without the need for additional hardware, making it well-suited for bo th perception and manipulation tasks. Extensive experiments validate the effecti veness of our method. For perception tasks, our approach decreases the number of categories that include misclassified samples by 2 and improves contact area se gmentation IoU by 3.53%."
LondonUnited KingdomEuropeEmerging TechnologiesMachine LearningRobotRoboticsKing's College London
NETL
NSTL
