Where Are You? Localization from Embodied Dialog

Abstract

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% success at identifying the Observer's location within 3m in unseen buildings, vs. 70.4% for human Locators.

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Chasing Ghosts: Instruction Following as Bayesian State Tracking
• Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
• Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight
• Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View
• Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor Data