Housekeep: Tidying Virtual Households using Commonsense Reasoning
This addresses the problem of commonsense reasoning for embodied AI in domestic settings, though it is incremental as it builds on existing methods for planning and navigation.
The authors introduced Housekeep, a benchmark for evaluating commonsense reasoning in embodied AI by requiring an agent to tidy virtual households based on human preferences, and proposed a modular baseline using a fine-tuned LLM that generalizes to unseen objects and environments.
We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/