pith. sign in

arxiv: 2108.04927 · v2 · pith:PRIUXRLVnew · submitted 2021-08-10 · 💻 cs.CV · cs.AI· cs.CL· cs.LG

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

classification 💻 cs.CV cs.AIcs.CLcs.LG
keywords alfredmodelcompletionembertembodiedlanguage-guidednavigationtask
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

    cs.RO 2022-04 accept novelty 7.0

    SayCan combines an LLM's high-level semantic knowledge with robot skill value functions to select only feasible actions, enabling completion of abstract natural-language instructions on a real mobile manipulator.

  2. Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    GASP injects geometric priors into VLMs via a deep-supervised correspondence head trained on video point correspondences and depth consistency, raising internal matching accuracy and delivering gains on spatial benchm...

  3. Inner Monologue: Embodied Reasoning through Planning with Language Models

    cs.RO 2022-07 unverdicted novelty 6.0

    LLMs form an inner monologue from closed-loop language feedback to improve high-level instruction completion in simulated and real robotic rearrangement and kitchen manipulation tasks.

  4. RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following

    cs.RO 2026-05 unverdicted novelty 5.0

    RePlan-Bot achieves state-of-the-art results on the ALFRED benchmark for embodied instruction following by integrating LLM-based auditing, commonsense map search, and ViT action correction.