TravExplorer: Cross-Floor Embodied Exploration via Traversability-Aware 3-D Planning

TL;DR

TravExplorer is a novel cross-floor exploration framework that combines semantic guidance with traversability-aware 3-D planning, enabling robots to navigate multi-level indoor environments effectively.

Contribution

It introduces a unified volumetric map, a traversability-aware hierarchical planner, and a semantic-reasoning module for cross-floor embodied exploration in complex indoor spaces.

Findings

Outperforms existing ObjectNav baselines in simulated environments.

Successfully conducts real-world cross-floor navigation without prior maps.

Demonstrates robustness in both simulated and real indoor environments.

Abstract

Zero-shot Object Navigation (ZSON) has shown promise for open-vocabulary target search in unseen environments, yet most existing systems remain tied to planar representations and single-floor assumptions. These assumptions become inadequate in real buildings, where navigation involves floors, stairs, landings, and vertically overlapping spaces. This article presents TravExplorer, a cross-floor embodied exploration framework that couples zero-shot semantic guidance with traversability-aware 3-D planning. TravExplorer maintains a unified volumetric map that distinguishes occupied structures from robot-reachable support surfaces and extracts traversable frontiers from connected support surfaces, including floors, stairs, and landings. A FOV-aware active perception strategy further resolves incomplete observations during cross-floor traversal. To reduce semantic-reasoning latency, a lightweight guidance module aligns a probabilistic instance map from online open-vocabulary segmentation with a spatial value map from fast image-to-text matching. Based on these geometric and semantic memories, a hierarchical planner performs target-aware frontier touring over object hypotheses, traversable frontiers, and stair landmarks, and generates executable cross-floor motions through foothold-guided 3-D search and vertically constrained local trajectory optimization. Experiments over 4,195 simulated episodes on HM3D and MP3D demonstrate consistent advantages over representative ObjectNav baselines. Fifty real-world trials on a Unitree Go2 further validate open-vocabulary target search across single-floor and cross-floor indoor environments without prior maps or human intervention. The code will be released at https://github.com/wuyi2121/TravExplorer.