GLEAM：面向复杂三维室内场景主动建图的通用探索策略学习

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

May 26, 2025

作者: Xiao Chen, Tai Wang, Quanyi Li, Tao Huang, Jiangmiao Pang, Tianfan Xue

cs.AI

摘要

在复杂未知环境中实现可推广的主动地图构建，仍是移动机器人面临的一项关键挑战。现有方法受限于训练数据不足及探索策略保守，在布局多样、连通性复杂的场景中表现出有限的泛化能力。为支持可扩展的训练与可靠的评估，我们引入了GLEAM-Bench，这是首个专为可推广主动地图构建设计的大规模基准测试，包含来自合成与真实扫描数据集的1,152个多样化三维场景。在此基础上，我们提出了GLEAM，一种统一的主动地图构建可推广探索策略。其卓越的泛化能力主要源于我们的语义表示、长期可达目标及随机化策略。在128个未见过的复杂场景上，GLEAM显著超越了现有最先进方法，实现了66.50%的覆盖率（提升9.49%），同时保持了高效的轨迹规划并提升了地图构建精度。项目页面：https://xiao-chen.tech/gleam/。

English

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/.