Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directions

TL;DR

This survey reviews recent advances in semantic mapping for indoor embodied AI, highlighting structural representations, challenges like high memory demands, and future directions towards open-vocabulary, queryable maps.

Contribution

It provides a comprehensive categorization and analysis of semantic map-building approaches in indoor embodied AI, emphasizing current challenges and future research directions.

Findings

Field is moving towards open-vocabulary, queryable maps

High memory demands and computational inefficiency are key challenges

Semantic mapping approaches are categorized by structure and information type

Abstract

Intelligent embodied agents (e.g. robots) need to perform complex semantic tasks in unfamiliar environments. Among many skills that the agents need to possess, building and maintaining a semantic map of the environment is most crucial in long-horizon tasks. A semantic map captures information about the environment in a structured way, allowing the agent to reference it for advanced reasoning throughout the task. While existing surveys in embodied AI focus on general advancements or specific tasks like navigation and manipulation, this paper provides a comprehensive review of semantic map-building approaches in embodied AI, specifically for indoor navigation. We categorize these approaches based on their structural representation (spatial grids, topological graphs, dense point-clouds or hybrid maps) and the type of information they encode (implicit features or explicit environmental data). We also explore the strengths and limitations of the map building techniques, highlight current challenges, and propose future research directions. We identify that the field is moving towards developing open-vocabulary, queryable, task-agnostic map representations, while high memory demands and computational inefficiency still remaining to be open challenges. This survey aims to guide current and future researchers in advancing semantic mapping techniques for embodied AI systems.