Retrospectives on the Embodied AI Workshop
This retrospective provides a synthesis of progress in Embodied AI for researchers, but it is incremental as it reviews existing work without introducing new methods or results.
The paper analyzes the state of Embodied AI research by reviewing 13 challenges from a workshop, focusing on visual navigation, rearrangement, and embodied vision-and-language, and discusses datasets, metrics, and model performance to identify common approaches and future directions.
We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.