NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Abstract

Simultaneously odometry and mapping using LiDAR data is an important task for mobile systems to achieve full autonomy in large-scale environments. However, most existing LiDAR-based methods prioritize tracking quality over reconstruction quality. Although the recently developed neural radiance fields (NeRF) have shown promising advances in implicit reconstruction for indoor environments, the problem of simultaneous odometry and mapping for large-scale scenarios using incremental LiDAR data remains unexplored. To bridge this gap, in this paper, we propose a novel NeRF-based LiDAR odometry and mapping approach, NeRF-LOAM, consisting of three modules neural odometry, neural mapping, and mesh reconstruction. All these modules utilize our proposed neural signed distance function, which separates LiDAR points into ground and non-ground points to reduce Z-axis drift, optimizes odometry and voxel embeddings concurrently, and in the end generates dense smooth mesh maps of the environment. Moreover, this joint optimization allows our NeRF-LOAM to be pre-trained free and exhibit strong generalization abilities when applied to different environments. Extensive evaluations on three publicly available datasets demonstrate that our approach achieves state-of-the-art odometry and mapping performance, as well as a strong generalization in large-scale environments utilizing LiDAR data. Furthermore, we perform multiple ablation studies to validate the effectiveness of our network design. The implementation of our approach will be made available at https: //github.com/JunyuanDeng/NeRF-LOAM .

Standard Datasets for Autonomous Navigation and Mapping: A Full-Stack Construction Methodology

“…In this phase, ANM aims to achieve key technological breakthroughs and advancements through massive amounts of standard datasets [2], [52]. The community is experiencing thorough refinement and modularization of traditional methods, maturation of deep learning approaches [2], [52], and breakthrough of novel frameworks (e.g., NeRF-based localization [53] and mapping [54]). During this stage, datasets must be high-quality, all-rounded, and possess significant scale for training, testing, and improvement [52], [55].…”

RSS-LIWOM: Rotating Solid-State LiDAR for Robust LiDAR-Inertial-Wheel Odometry and Mapping

“…Building upon this method, Zhang et al [16] added point-to-edge matching and developed LOAM, a LiDAR odometry and mapping framework, in 2014. After that, many works have been proposed for LOAM, such as LeGO-LOAM [17], LOAM-Livox [18] and methods using semantic information [19,20], deep learning networks [21][22][23], or the most recent neural rendering techniques [24]. Current methods also allow loop closure detection and position correction by comparing the current frame with the keyframe [16,25] or combining with deep learning [20,[26][27][28].…”