An Atlas framework for scalable mapping

TLDR

This paper introduces Atlas, a hybrid metrical/topological SLAM framework that enables efficient mapping of large‑scale environments. Atlas represents a graph of coordinate frames, with each vertex a local frame and edges encoding transformations; each frame builds a local map with pose and uncertainty, uncertainties modeled per frame, and entity probabilities in arbitrary frames are computed via Dijkstra shortest‑path traversal, while loop closure is achieved through an efficient map‑matching algorithm. We demonstrate real‑time operation of Atlas in a large indoor structured environment covering a 2.2 km path with multiple nested loops using laser or ultrasonic ranging sensors.

Abstract

This paper describes Atlas, a hybrid metrical/topological approach to SLAM that achieves efficient mapping of large-scale environments. The representation is a graph of coordinate frames, with each vertex in the graph representing a local frame, and each edge representing the transformation between adjacent frames. In each frame, we build a map that captures the local environment and the current robot pose along with the uncertainties of each. Each map's uncertainties are modeled with respect to its own frame. Probabilities of entities with respect to arbitrary frames are generated by following a path formed by the edges between adjacent frames, computed via Dijkstra's shortest path algorithm. Loop closing is achieved via an efficient map matching algorithm. We demonstrate the technique running in real-time in a large indoor structured environment (2.2 km path length) with multiple nested loops using laser or ultrasonic ranging sensors.