PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency

Abstract

Accurate and robust localization and mapping are essential components for most autonomous robots. In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact point-based implicit neural map representation. Taking range measurements as input, our approach alternates between incremental learning of the local implicit signed distance field and the pose estimation given the current local map using a correspondence-free, point-to-implicit model registration. Our implicit map is based on sparse optimizable neural points, which are inherently elastic and deformable with the global pose adjustment when closing a loop. Loops are also detected using the neural point features. Extensive experiments validate that PIN-SLAM is robust to various environments and versatile to different range sensors such as LiDAR and RGB-D cameras. PIN-SLAM achieves pose estimation accuracy better or on par with the state-of-the-art LiDAR odometry or SLAM systems and outperforms the recent neural implicit SLAM approaches while maintaining a more consistent, and highly compact implicit map that can be reconstructed as accurate and complete meshes. Finally, thanks to the voxel hashing for efficient neural points indexing and the fast implicit map-based registration without closest point association, PIN-SLAM can run at the sensor frame rate on a moderate GPU. Codes will be available at: https://github.com/PRBonn/PIN_SLAM.

20 pages

References in corpus (12)

• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
• KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way
• SuMa++: Efficient LiDAR-based Semantic SLAM
• The Replica Dataset: A Digital Replica of Indoor Spaces
• Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation
• OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition
• The Hilti SLAM Challenge Dataset
• LOCUS 2.0: Robust and Computationally Efficient Lidar Odometry for Real-Time Underground 3D Mapping
• Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps
• Dynablox: Real-time Detection of Diverse Dynamic Objects in Complex Environments
• PyPose: A Library for Robot Learning with Physics-based Optimization
• IR-MCL: Implicit Representation-Based Online Global Localization

Cited by in corpus (8)

• Tracking and Mapping in Medical Computer Vision: A Review
• Benchmarking Neural Radiance Fields for Autonomous Robots: An Overview
• HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
• HiMo: High-Speed Objects Motion Compensation in Point Clouds
• RadaRays: Real-time Simulation of Rotating FMCW Radar for Mobile Robotics via Hardware-accelerated Ray Tracing
• From Underground Mines to Offices: A Versatile and Robust Framework for Range-Inertial SLAM
• Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids
• 2Fast-2Lamaa: Large-Scale Lidar-Inertial Localization and Mapping with Continuous Distance Fields