{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/visual-robot-task-planning","title":"Visual Robot Task Planning","arxiv_id":"1804.00062","date":"2018-03-30","proceeding":null,"authors":["Chris Paxton","Yotam Barnoy","Kapil Katyal","Raman Arora","Gregory D. Hager"],"abstract":"Prospection, the act of predicting the consequences of many possible futures,\nis intrinsic to human planning and action, and may even be at the root of\nconsciousness. Surprisingly, this idea has been explored comparatively little\nin robotics. In this work, we propose a neural network architecture and\nassociated planning algorithm that (1) learns a representation of the world\nuseful for generating prospective futures after the application of high-level\nactions, (2) uses this generative model to simulate the result of sequences of\nhigh-level actions in a variety of environments, and (3) uses this same\nrepresentation to evaluate these actions and perform tree search to find a\nsequence of high-level actions in a new environment. Models are trained via\nimitation learning on a variety of domains, including navigation,\npick-and-place, and a surgical robotics task. Our approach allows us to\nvisualize intermediate motion goals and learn to plan complex activity from\nvisual information.","url_abs":"http://arxiv.org/abs/1804.00062v1","url_pdf":"http://arxiv.org/pdf/1804.00062v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"visual-robot-task-planning","repo_url":"https://github.com/jhu-lcsr/costar_plan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"robot-task-planning","task_name":"Robot Task Planning"},{"task_slug":"task-planning","task_name":"Task Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00062","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}