Where Are You? Localization from Embodied Dialog

11/16/2020
by   Meera Hahn, et al.
14

We present Where Are You? (WAY), a dataset of  6k dialogs in which two humans – an Observer and a Locator – complete a cooperative localization task. The Observer is spawned at random in a 3D environment and can navigate from first-person views while answering questions from the Locator. The Locator must localize the Observer in a detailed top-down map by asking questions and giving instructions. Based on this dataset, we define three challenging tasks: Localization from Embodied Dialog or LED (localizing the Observer from dialog history), Embodied Visual Dialog (modeling the Observer), and Cooperative Localization (modeling both agents). In this paper, we focus on the LED task – providing a strong baseline model with detailed ablations characterizing both dataset biases and the importance of various modeling choices. Our best model achieves 32.7 unseen buildings, vs. 70.4

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset