Multi-Floor Exploration for Ground Robots via an Incremental Reachable Graph and Structural Priors

2026-05-22

AI Summary

This work addresses the limitations of conventional 2D/2.5D maps in representing vertically overlapping traversable areas—such as stairs and ramps—during autonomous multi-floor exploration by ground robots. To overcome this, the authors propose an incremental reachability graph representation that integrates cross-floor structural priors. By projecting already-explored regions, the method initializes hypothesis graphs for target floors and employs a hierarchical planner that jointly reasons over confirmed and hypothesized structures to enable efficient exploration. This approach preserves potential connectivity under sparse observations and transcends the constraints of single-floor mapping. Extensive simulations and real-robot experiments demonstrate that the system outperforms baseline methods in exploration efficiency, map completeness, real-time performance, and practical feasibility.

Abstract

Autonomous exploration of multi-floor buildings remains challenging for ground robots because conventional 2D and 2.5D maps cannot represent overlapping traversable surfaces such as stairs, ramps, and multiple reachable elevations. This letter presents a multi-floor exploration framework based on an incremental reachable graph. Built as a sparse graph over reachable support surfaces, the graph preserves potentially valid connectivity through tentative graph elements under sparse observations and enables stable, physically reachable frontier detection. To guide exploration beyond the currently mapped floor, we project task-zone priors from an explored floor to initialize a hypothetical graph on the target floor and reconcile it incrementally with incoming observations. A hierarchical planner then jointly reasons over confirmed and hypothetical structures for global guidance. In simulation, the proposed method demonstrates improved exploration efficiency and mapping completeness compared to evaluated baselines. Furthermore, onboard real-world experiments validate its practical feasibility and real-time performance.

Problem

• multi-floor exploration
• ground robots
• reachable surfaces
• autonomous exploration
• overlapping traversable surfaces

Innovation

• incremental reachable graph
• multi-floor exploration
• structural priors
• frontier detection
• hierarchical planning