{"componentChunkName":"component---src-templates-blog-post-js","path":"/blog/a-simpler-method-for-learning-to-control-a-robot/","result":{"data":{"site":{"siteMetadata":{"title":"No Frills News"}},"contentfulNfnPost":{"postTitle":"A simpler method for learning to control a robot","slug":"a-simpler-method-for-learning-to-control-a-robot","createdLocal":"2023-07-26 14:31:03.607974","publishDate":"None","feedName":"Autonomous Vehicle News","sourceUrl":{"sourceUrl":"https://news.mit.edu/2023/simpler-method-learning-control-robot-0726"},"postSummary":{"childMarkdownRemark":{"html":"<p>One way to think about this structure is as a hint that can help guide how to control a system.\nThis could help their learning-based control system achieve better performance faster in rapidly changing environments.\nLearning a controllerDetermining the best way to control a robot to accomplish a given task can be a difficult problem, even when researchers know how to model everything about the system.\n“We found that beyond learning the dynamics, it’s also essential to learn the control-oriented structure that supports effective controller design.\nThe result is a data-efficient learning process that outputs dynamic models that enjoy intrinsic structure that enables effective, stable, and robust control.</p>"}}}},"pageContext":{"slug":"a-simpler-method-for-learning-to-control-a-robot"}}}