Two Body Problem: Collaborative Visual Task Completion

@article{Jain2019TwoBP,
  title={Two Body Problem: Collaborative Visual Task Completion},
  author={Unnat Jain and Luca Weihs and Eric Kolve and M. Rastegari and S. Lazebnik and Ali Farhadi and Alexander G. Schwing and Aniruddha Kembhavi},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={6682-6692}
}
  • Unnat Jain, Luca Weihs, +5 authors Aniruddha Kembhavi
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration has often been studied in the context of simple grid worlds. We argue that there are inherently visual aspects to collaboration which should be studied in visually rich environments. A key element in collaboration is communication that can be either explicit, through messages, or implicit, through perception of the… CONTINUE READING
    When2com: Multi-Agent Perception via Communication Graph Grouping
    1
    Visual Hide and Seek
    2
    SoundSpaces: Audio-Visual Navigation in 3D Environments
    2
    Learning About Objects by Learning to Interact with Them
    1
    AllenAct: A Framework for Embodied AI Research
    Bridging the Imitation Gap by Adaptive Insubordination
    1
    A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
    2
    Audio-Visual Embodied Navigation
    8

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 97 REFERENCES
    Visual Semantic Planning Using Deep Successor Representations
    73
    Cognitive Mapping and Planning for Visual Navigation
    296
    Target-driven visual navigation in indoor scenes using deep reinforcement learning
    620
    Playing Doom with SLAM-Augmented Deep Reinforcement Learning
    45
    IQA: Visual Question Answering in Interactive Environments
    133
    Learning to Navigate in Complex Environments
    436
    Control of Memory, Active Perception, and Action in Minecraft
    175
    TarMAC: Targeted Multi-Agent Communication
    46