Robotics & Machine Learning Daily News2024,Issue(Jun.28) :48-48.

Studies from German Aerospace Center (DLR) in the Area of Robotics Reported (Gui ding Real-world Reinforcement Learning for In-contact Manipulation Tasks With Sh ared Control Templates)

德国航空航天中心(DLR)在机器人领域的研究报告(Gui Ding真实世界强化学习,用于带Sh ARED控制模板的接触操作任务)

Robotics & Machine Learning Daily News2024,Issue(Jun.28) :48-48.

Studies from German Aerospace Center (DLR) in the Area of Robotics Reported (Gui ding Real-world Reinforcement Learning for In-contact Manipulation Tasks With Sh ared Control Templates)

德国航空航天中心(DLR)在机器人领域的研究报告(Gui Ding真实世界强化学习,用于带Sh ARED控制模板的接触操作任务)

扫码查看

摘要

由一位新闻记者兼机器人与机器学习的新闻编辑每日新闻-关于机器人的最新研究结果已经发表。根据NewsRx记者从德国韦斯林发回的新闻报道,研究表明:“对大量训练事件的要求一直是Reenforcement Learning(RL)在机器人领域应用的一个主要限制因素。直接在真实机器人上学习技能需要时间,造成磨损,并可能由于不安全的探索行动而导致机器人和环境的破坏。”这项研究的资助者包括德国研究基金会(DFG)、德国研究基金会(DFG)、地平线欧洲研究基础设施。

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Robotics have been published. According to news reporting originating from Wessling, Germany, by NewsRx correspondents, research stated, “The requirement for a high number o f training episodes has been a major limiting factor for the application of Rein forcement Learning (RL) in robotics. Learning skills directly on real robots req uires time, causes wear and tear and can lead to damage to the robot and environ ment due to unsafe exploratory actions.” Funders for this research include German Research Foundation (DFG), German Resea rch Foundation (DFG), Horizon Europe Research Infrastructures.

Key words

Wessling/Germany/Europe/Emerging Tech nologies/Machine Learning/Nano-robot/Reinforcement Learning/Robot/Robotics/German Aerospace Center (DLR)

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文