GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes

TL;DR

The paper introduces GLEAM, a novel exploration policy for mobile robots that generalizes well across diverse 3D indoor environments, supported by a new large-scale benchmark, GLEAM-Bench.

Contribution

It presents GLEAM, a unified exploration policy leveraging semantic representations and randomized strategies, and introduces GLEAM-Bench, the first large-scale benchmark for this task.

Findings

Achieves 66.50% coverage on unseen scenes

Outperforms state-of-the-art methods in mapping accuracy

Demonstrates strong generalization across diverse environments

Abstract

Generalizable active mapping in complex unknown environments remains a critical challenge for mobile robots. Existing methods, constrained by insufficient training data and conservative exploration strategies, exhibit limited generalizability across scenes with diverse layouts and complex connectivity. To enable scalable training and reliable evaluation, we introduce GLEAM-Bench, the first large-scale benchmark designed for generalizable active mapping with 1,152 diverse 3D scenes from synthetic and real-scan datasets. Building upon this foundation, we propose GLEAM, a unified generalizable exploration policy for active mapping. Its superior generalizability comes mainly from our semantic representations, long-term navigable goals, and randomized strategies. It significantly outperforms state-of-the-art methods, achieving 66.50% coverage (+9.49%) with efficient trajectories and improved mapping accuracy on 128 unseen complex scenes. Project page: https://xiao-chen.tech/gleam/.