Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion

Abstract

Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by introducing object navigation targets for EmBERT training. We achieve competitive performance on the ALFRED benchmark, and EmBERT marks the first transformer-based model to successfully handle the long-horizon, dense, multi-modal histories of ALFRED, and the first ALFRED model to utilize object-centric navigation targets.

Accepted at Novel Ideas in Learning-to-Learn through Interaction (NILLI) workshop @ EMNLP 2021

References in corpus (11)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Learning Transferable Visual Models From Natural Language Supervision
• How multilingual is Multilingual BERT?
• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• Rearrangement: A Challenge for Embodied AI
• Imitating Interactive Intelligence
• A Recurrent Vision-and-Language BERT for Navigation
• Sim-to-Real Transfer for Vision-and-Language Navigation
• Are We There Yet? Learning to Localize in Embodied Instruction Following
• Modular Framework for Visuomotor Language Grounding
• The Amazing Race TM: Robot Edition