NextBestPath: Efficient 3D Mapping of Unseen Environments

2025-02-07

AI Summary

To address inefficiencies in active 3D mapping within unknown indoor environments—including suboptimal navigation paths, susceptibility to local minima, and limitations of existing datasets (e.g., low geometric complexity and inaccurate ground truth)—this paper proposes a long-horizon goal-driven navigation framework. Methodologically, we introduce the “Next Best Path” (NBP) prediction paradigm, jointly modeling surface coverage gain and obstacle map estimation. We further incorporate geometry-aware data augmentation, curriculum learning, and high-fidelity map generation based on the DOOM engine. Our contributions include: (i) the first high-complexity, ground-truth-accurate indoor mapping benchmark, AiMDoom; and (ii) state-of-the-art performance on both MP3D and AiMDoom—achieving 21.3% higher mapping efficiency and 18.7% greater coverage than prior methods, with strong generalization across multi-scale and highly cluttered scenes.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This work addresses the problem of active 3D mapping, where an agent must find an efficient trajectory to exhaustively reconstruct a new scene. Previous approaches mainly predict the next best view near the agent's location, which is prone to getting stuck in local areas. Additionally, existing indoor datasets are insufficient due to limited geometric complexity and inaccurate ground truth meshes. To overcome these limitations, we introduce a novel dataset AiMDoom with a map generator for the Doom video game, enabling to better benchmark active 3D mapping in diverse indoor environments. Moreover, we propose a new method we call next-best-path (NBP), which predicts long-term goals rather than focusing solely on short-sighted views. The model jointly predicts accumulated surface coverage gains for long-term goals and obstacle maps, allowing it to efficiently plan optimal paths with a unified model. By leveraging online data collection, data augmentation and curriculum learning, NBP significantly outperforms state-of-the-art methods on both the existing MP3D dataset and our AiMDoom dataset, achieving more efficient mapping in indoor environments of varying complexity.

Problem

• Efficient 3D mapping in unseen environments
• Overcoming local area entrapment in mapping
• Enhancing indoor dataset geometric complexity accuracy

Innovation

• Novel dataset AiMDoom
• Next-best-path (NBP) method
• Joint prediction of coverage gains