"Where am I?" Scene Retrieval with Language
This addresses the need for language-based interaction with embodied AI agents in specific locations, such as task execution or meeting points, by enabling scene retrieval from natural language queries.
The paper tackles the problem of retrieving a 3D scene graph from a collection of disjoint scenes using an open-set natural language query, presenting Text2SceneGraphMatcher, a pipeline that learns joint embeddings between text and scene graphs to determine matches, with code, models, and datasets made public.
Natural language interfaces to embodied AI are becoming more ubiquitous in our daily lives. This opens up further opportunities for language-based interaction with embodied agents, such as a user verbally instructing an agent to execute some task in a specific location. For example, "put the bowls back in the cupboard next to the fridge" or "meet me at the intersection under the red sign." As such, we need methods that interface between natural language and map representations of the environment. To this end, we explore the question of whether we can use an open-set natural language query to identify a scene represented by a 3D scene graph. We define this task as "language-based scene-retrieval" and it is closely related to "coarse-localization," but we are instead searching for a match from a collection of disjoint scenes and not necessarily a large-scale continuous map. We present Text2SceneGraphMatcher, a "scene-retrieval" pipeline that learns joint embeddings between text descriptions and scene graphs to determine if they are a match. The code, trained models, and datasets will be made public.