A Submodular-Based Autonomous Exploration for Multi-Room Indoor Scenes Reconstruction

Yongwei Miao, Haipeng Wang, Ran Fan, Fuchang Liu

Abstract: To autonomously explore and densely recover an unknown indoor scene is a nontrivial task in 3D scene reconstruction. It is challenging for scenes composed of compact and complicated interconnected rooms with no priors. To address this issue, we aim to use autonomous scanning, reconstruct multi-room scenes, and produce a complete reconstruction in as few scans as possible. With a progressive discrete motion planning module, we introduce submodular-based planning for automated scanning scenarios to efficiently guide the active scanning by Next-Best-View until marginal gains diminish. The submodular-based planning gives an approximately optimal solution of “Next-Best-View” which is NP-hard in case of no prior knowledge. Experiments show that our method can improve scanning efficiency significantly for multi-room scenes while maintaining reconstruction errors.