Rearrangement: A Challenge for Embodied AI
This framework addresses the need for standardized benchmarks in Embodied AI, potentially benefiting researchers by focusing techniques and enabling model transfer, though it is incremental as it builds on existing simulation platforms.
The paper introduces a canonical task called Rearrangement to standardize research and evaluation in Embodied AI, aiming to bring physical environments into specified states using various goal specifications, and provides testbeds in simulation environments to facilitate development.
We describe a framework for research and evaluation in Embodied AI. Our proposal is based on a canonical task: Rearrangement. A standard task can focus the development of new techniques and serve as a source of trained models that can be transferred to other settings. In the rearrangement task, the goal is to bring a given physical environment into a specified state. The goal state can be specified by object poses, by images, by a description in language, or by letting the agent experience the environment in the goal state. We characterize rearrangement scenarios along different axes and describe metrics for benchmarking rearrangement performance. To facilitate research and exploration, we present experimental testbeds of rearrangement scenarios in four different simulation environments. We anticipate that other datasets will be released and new simulation platforms will be built to support training of rearrangement agents and their deployment on physical systems.