Corpus ID: 208617407

ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

@article{Shridhar2019ALFREDAB,
  title={ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks},
  author={Mohit Shridhar and Jesse Thomason and Daniel Gordon and Yonatan Bisk and Winson Han and Roozbeh Mottaghi and Luke Zettlemoyer and Dieter Fox},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.01734}
}
  • Mohit Shridhar, Jesse Thomason, +5 authors Dieter Fox
  • Published in ArXiv 2019
  • Computer Science
  • We present ALFRED (Action Learning From Realistic Environments and Directives), a benchmark for learning a mapping from natural language instructions and egocentric vision to sequences of actions for household tasks. Long composition rollouts with non-reversible state changes are among the phenomena we include to shrink the gap between research benchmarks and real-world applications. ALFRED consists of expert demonstrations in interactive visual environments for 25k natural language directives… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-3 OF 3 CITATIONS

    Experience Grounds Language

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Grounding Language in Play

    VIEW 3 EXCERPTS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 58 REFERENCES

    Self-Monitoring Navigation Agent via Auxiliary Progress Estimation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    VirtualHome: Simulating Household Activities Via Programs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    6-DOF GraspNet: Variational Grasp Generation for Object Manipulation

    VIEW 2 EXCERPTS

    Cross-Task Weakly Supervised Learning From Instructional Videos

    Embodied Question Answering in Photorealistic Environments With Point Cloud Perception

    VIEW 2 EXCERPTS

    Habitat: A Platform for Embodied AI Research