{"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/virtualhome-simulating-household-activities","title":"VirtualHome: Simulating Household Activities via Programs","arxiv_id":"1806.07011","date":"2018-06-19","proceeding":"CVPR 2018 6","authors":["Xavier Puig","Kevin Ra","Marko Boben","Jiaman Li","Tingwu Wang","Sanja Fidler","Antonio Torralba"],"abstract":"In this paper, we are interested in modeling complex activities that occur in\na typical household. We propose to use programs, i.e., sequences of atomic\nactions and interactions, as a high level representation of complex tasks.\nPrograms are interesting because they provide a non-ambiguous representation of\na task, and allow agents to execute them. However, nowadays, there is no\ndatabase providing this type of information. Towards this goal, we first\ncrowd-source programs for a variety of activities that happen in people's\nhomes, via a game-like interface used for teaching kids how to code. Using the\ncollected dataset, we show how we can learn to extract programs directly from\nnatural language descriptions or from videos. We then implement the most common\natomic (inter)actions in the Unity3D game engine, and use our programs to\n\"drive\" an artificial agent to execute tasks in a simulated household\nenvironment. Our VirtualHome simulator allows us to create a large activity\nvideo dataset with rich ground-truth, enabling training and testing of video\nunderstanding models. We further showcase examples of our agent performing\ntasks in our VirtualHome based on language descriptions.","url_abs":"http://arxiv.org/abs/1806.07011v1","url_pdf":"http://arxiv.org/pdf/1806.07011v1.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":"virtualhome-simulating-household-activities","repo_url":"https://github.com/StanfordHCI/virtualhome","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"virtualhome-simulating-household-activities","repo_url":"https://github.com/gt-rail/rail_tasksim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"virtualhome-simulating-household-activities","repo_url":"https://github.com/huangwl18/language-planner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"virtualhome-simulating-household-activities","repo_url":"https://github.com/xavierpuigf/virtualhome","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}