%0 Conference Proceedings %T A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions %A Karamcheti, Siddharth %A Williams, Edward Clem %A Arumugam, Dilip %A Rhee, Mina %A Gopalan, Nakul %A Wong, Lawson L.S. %A Tellex, Stefanie %Y Bansal, Mohit %Y Matuszek, Cynthia %Y Andreas, Jacob %Y Artzi, Yoav %Y Bisk, Yonatan %S Proceedings of the First Workshop on Language Grounding for Robotics %D 2017 %8 August %I Association for Computational Linguistics %C Vancouver, Canada %F karamcheti-etal-2017-tale %X Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two categories: those that specify a goal condition or target state, and those that specify explicit actions, or how to perform a given task. Recent approaches have used reward functions as a semantic representation of goal-based commands, which allows for the use of a state-of-the-art planner to find a policy for the given task. However, these reward functions cannot be directly used to represent action-oriented commands. We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes to unseen environments. Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot interaction. %R 10.18653/v1/W17-2809 %U https://aclanthology.org/W17-2809 %U https://doi.org/10.18653/v1/W17-2809 %P 67-75