Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion
This addresses the problem of language-guided visual task completion for robots in home and office environments, representing an incremental advance by adapting object-centric navigation methods to this benchmark.
The authors tackled the challenge of grounding language instructions in visual observations for robots performing tasks, by presenting Embodied BERT (EmBERT), a transformer-based model that achieved competitive performance on the ALFRED benchmark.
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.