Corpus ID: 221370597

AllenAct: A Framework for Embodied AI Research

@article{Weihs2020AllenActAF,
  title={AllenAct: A Framework for Embodied AI Research},
  author={Luca Weihs and J. Salvador and Klemen Kotar and Unnat Jain and Kuo-Hao Zeng and R. Mottaghi and Aniruddha Kembhavi},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.12760}
}
  • Luca Weihs, J. Salvador, +4 authors Aniruddha Kembhavi
  • Published 2020
  • Computer Science
  • ArXiv
  • The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with the advent of deep reinforcement learning and increased interest from the computer vision, NLP, and robotics communities. This growth has been facilitated by the creation of a large number of simulated environments (such as AI2-THOR, Habitat and CARLA), tasks (like point navigation, instruction following, and embodied… CONTINUE READING

    Figures and Tables from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 63 REFERENCES
    RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
    5
    Embodied Question Answering
    215
    Gibson Env: Real-World Perception for Embodied Agents
    154
    Unity: A General Platform for Intelligent Agents
    142
    Habitat: A Platform for Embodied AI Research
    128
    Visual Semantic Planning Using Deep Successor Representations
    73
    ViZDoom: A Doom-based AI research platform for visual reinforcement learning
    392