首页|Researcher at University of Duisburg-Essen Describes Research in Robotics (Keep the Human in the Loop: Arguments for Human Assistance in the Synthesis of Simula tion Data for Robot Training)
Researcher at University of Duisburg-Essen Describes Research in Robotics (Keep the Human in the Loop: Arguments for Human Assistance in the Synthesis of Simula tion Data for Robot Training)
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 Daily News Daily News – Researchers detail new data in robotic s. According to news reporting out of Essen, Germany, by NewsRx editors, researc h stated, “Robot training often takes place in simulated environments, particula rly with reinforcement learning.” Funders for this research include German Federal Ministry of Education And Resea rch. The news editors obtained a quote from the research from University of Duisburg- Essen: “Therefore, multiple training environments are generated using domain ran domization to ensure transferability to real-world applications and compensate f or unknown real-world states. We propose improving domain randomization by invol ving human application experts in various stages of the training process. Expert s can provide valuable judgments on simulation realism, identify missing propert ies, and verify robot execution. Our human-in-the-loop workflow describes how th ey can enhance the process in five stages: validating and improving real-world s cans, correcting virtual representations, specifying application-specific object properties, verifying and influencing simulation environment generation, and ve rifying robot training. We outline examples and highlight research opportunities .”
University of Duisburg-EssenEssenGer manyEuropeEmerging TechnologiesMachine LearningRobotRobotics
NETL
NSTL
