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

Alessandro Suglia, Qiaozi Gao, Jesse Thomason, Govind Thattai, Gaurav S. Sukhatme

Research output: Working paperPreprint


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.
Original languageEnglish
Publication statusPublished - 10 Aug 2021


  • cs.CV
  • cs.AI
  • cs.CL
  • cs.LG


Dive into the research topics of 'Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion'. Together they form a unique fingerprint.

Cite this