{"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/a-tale-of-two-draggns-a-hybrid-approach-for","title":"A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions","arxiv_id":"1707.08668","date":"2017-07-26","proceeding":"WS 2017 8","authors":["Siddharth Karamcheti","Edward C. Williams","Dilip Arumugam","Mina Rhee","Nakul Gopalan","Lawson L. S. Wong","Stefanie Tellex"],"abstract":"Robots operating alongside humans in diverse, stochastic environments must be\nable to accurately interpret natural language commands. These instructions\noften fall into one of two categories: those that specify a goal condition or\ntarget state, and those that specify explicit actions, or how to perform a\ngiven task. Recent approaches have used reward functions as a semantic\nrepresentation of goal-based commands, which allows for the use of a\nstate-of-the-art planner to find a policy for the given task. However, these\nreward functions cannot be directly used to represent action-oriented commands.\nWe introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding\nNetwork (DRAGGN), for task grounding and execution that handles natural\nlanguage from either category as input, and generalizes to unseen environments.\nOur robot-simulation results demonstrate that a system successfully\ninterpreting both goal-oriented and action-oriented task specifications brings\nus closer to robust natural language understanding for human-robot interaction.","url_abs":"http://arxiv.org/abs/1707.08668v1","url_pdf":"http://arxiv.org/pdf/1707.08668v1.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":"a-tale-of-two-draggns-a-hybrid-approach-for","repo_url":"https://github.com/siddk/glamdp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.08668","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}