Performing collaborative semantic mapping is a critical challenge for cooperative robots to enhance their comprehensive contextual understanding of the surroundings. This article bridges the gap between the advances in collaborative geometry mapping that relies on pure geometry information fusion, and single robot semantic mapping that focuses on integrating continuous raw sensor data. In this article, a novel hierarchical collaborative probabilistic semantic mapping framework is proposed, where the problem is formulated in a distributed setting. The key novelty of this work is the modeling of the hierarchical semantic map fusion framework and its mathematical derivation of its probability decomposition. At the single robot level, the semantic point cloud is obtained by combining information from heterogeneous sensors and used to generate local semantic maps. At the collaborative robots level, local maps are shared among robots for global semantic map fusion. Since the voxel correspondence is unknown between local maps, an expectation-maximization approach is proposed to estimate the hidden data association. Then, Bayesian rule is applied to perform semantic and occupancy probability update. Experimental results on the unmanned aerial vehicle and the unmanned ground vehicle platforms show the high quality of global semantic maps, demonstrating the accuracy and utility in practical missions.

Repetitive or ambiguous environment, where structures are highly similar and distinct geometric features are not sufficient, is one of the critical and challenging scenarios for mobile robots to perform global localization or simultaneous localization and mapping (SLAM) tasks. The robots are easy to get lost or mismatched to wrong places in such environments. The existing solutions either rely heavily on pre-installed infrastructures which are inflexible and expensive or rely on single sensor-based global localization methods whose initialization module is not capable enough to provide distinctive information. Thus, this article proposes a hierarchical probabilistic framework that addresses the problem of infrastructure-free mobile robot global localization in GPS-challenged repetitive environments by leveraging both the measured magnetic field (MF) and Light Detection and Ranging (LiDAR) information. The proposed hierarchical system mainly consists of: 1) coarse localization: MF-based localization and 2) fine localization: LiDAR-based localization (LBL). The ambient MF functions as a substitute for the GPS signal, which is considered not available or severely challenged in indoor/semi-indoor local environments. Based on the pre-built MF database, multiple coarse candidate robot poses can first be determined by the proposed initial pose estimation algorithm, which incorporates multivariate Gaussian observation model and random sample consensus (RANSAC) algorithm. Then, using the obtained multiple candidate poses as initialization, the robot can be localized more accurately by LiDAR-based fine localization. Extensive real-world experiments demonstrate that the proposed system achieves over 95% localization success rate and takes less than 2.0-m average traveling distance to localize the mobile robot.

In recent years, LiDAR-based localization and mapping methods have achieved significant progress thanks to their reliable and real-time localization capability. Considering single LiDAR odometry often faces hardware failures and degeneracy in practical scenarios, Multi-LiDAR Odometry (MLO), as an emerging technology, is studied to enhance the performance of LiDAR-based localization and mapping systems. However, MLO can suffer from high computational complexity introduced by dense point clouds that are fused from multiple LiDARs, and the continuous-time measurement characteristic is constantly neglected by existing LiDAR odometry. This motivates us to develop a Continuous-Time and Efficient MLO, namely CTE-MLO, which can achieve accurate and real-time estimation using multi-LiDAR measurements through a continuous-time perspective. In this paper, the Gaussian process estimation is naturally combined with the Kalman filter, which enables each LiDAR point in a point stream to query the corresponding continuous-time trajectory using its time instants. A decentralized multi-LiDAR synchronization scheme is also devised to combine points from separate LiDARs into a single point cloud without the primary LiDAR assignment. Moreover, with the aim of improving the real-time performance of MLO without sacrificing robustness, a point cloud sampling strategy is designed with the consideration of localizability. To this end, CTE-MLO integrates synchronization, localizability-aware sampling, continuous-time estimation, and voxel map management within a Kalman filter framework, which can achieve high accuracy and robust continuous-time estimation within only a few linear iterations. The effectiveness of the proposed method is demonstrated through various scenarios, including public datasets and real-world applications. Exhaustive benchmarks on public dataset show that CTE-MLO is demonstratively competitive compared to other State-of-the-art (SOTA) methods in accuracy, robustness, and efficiency. Furthermore, CTE-MLO has undergone comprehensive validation across various scenarios (such as port, campus, and forest) and on diverse platforms (a full-size truck, an autonomous sweeper, and an agile Micro Aerial Vehicle (MAV)), covering a total test area exceeding 3.6km2, which affirm the applicability of CTE-MLO in industrial and field scenarios. A demonstration video is available at https://youtu.be/Q29PGPitHUI, and the code is also available at https://github.com/shenhm516/CTE-MLO to benefit the community.

Accurate global localization and tracking are essential ingredients for autonomous mobile robots (AMRs) operating in enclosed or partially enclosed repetitive environments (e.g., office corridors, industrial warehouses, and transportation centers). In such degenerated challenging environments, global navigation satellite system signals are unreliable or severely degraded. Existing infrastructure-based (e.g., beacons/QR codes-based) solutions suffer from inflexibility and high maintenance costs, while traditional geometric feature-based LiDAR/visual localization technologies may fail due to highly similar structures. The ambient magnetic field (MF) has shown its omnipresence and high distinctiveness at different location, which makes it gradually adopted for infrastructure-free AMR localization applications. Currently, existing MF-based localization methods are partly based on 3-D MF vector matching or MF sequential matching, which typically suffer from the orientation-dependency and similar-sequential-route limitations, respectively. To address the aforementioned challenges, this article proposes a novel probabilistic Magnetic-lead Global Localization and Tracking (MGLT) framework using the proposed rotation-invariant Magnetic-Horizontal, Vertical, and Total intensity (M-HVT) descriptor and 2-D laser scans for AMRs operating in repetitive environments. The proposed framework mainly consists of: 1) Two-step Initialization: Laser range and MF sequence-based matching; and 2) MF-based Pose Tracking: recursive multidimensional MF sequence-based matching. Extensive simulations and real-world experimental results validate that the proposed framework outperforms SOTA MF-based localization baselines in both global localization convergence and tracking accuracy.

Multisession mapping is becoming increasingly crucial for a wide range of applications in robotics and autonomous systems, including surveying, map updating, and multiagent collaboration. However, current solutions either rely on the matching of elementary geometric or semantic features, which typically leads to failure in GNSS-challenged degenerated environments with repetitive features (e.g., office/hotel/hospital long corridors, warehouses, gardens, tunnels, and underground facilities); or rely on a good prior estimate/input of the initial transformation matrices of multiple single-session maps, which may not always be obtainable. Characterized by its omnipresence and distinct variability across different locations, the ambient magnetic field is well-suited for estimating the initial transformation matrix regardless of the geometric features. Therefore, we present Mag-MM, a novel probabilistic framework for magnetic-enhanced multisession mapping that addresses the aforementioned challenges. The proposed framework aims to estimate the transformation matrices of maps from multiple single sessions, and to build consistent and accurate global maps in repetitive environments. Our framework introduces three key innovations: A comprehensive probabilistic framework that addresses the problem of multisession mapping in repetitive environments; a particle swarm optimization (PSO)-based magnetic data association strategy to autonomously determine the initial estimate of the transformation matrices; a magnetic fingerprint correspondences-based algorithm to delimit the overlapping regions for data redundancy reduction and efficiency improvement. Results of simulations and real practical missions show the significantly enhanced mapping consistency and accuracy over the baselines.

LiDAR-based Global Localization (LGL) is an essential ingredient for autonomous robots. However, existing LGL methods typically consider only partial information (e.g., geometric features) from LiDAR observations or are designed for homogeneous LiDAR sensors, overlooking the uniformity in LGL. In this work, a uniform LGL method is proposed, termed UniLGL, which simultaneously achieves spatial and material uniformity, as well as sensor-type uniformity. The key idea of the proposed method is to encode the complete point cloud, which contains both geometric and material information, into a pair of Bird's Eye View (BEV) images (i.e., a spatial BEV image and an intensity BEV image), thereby transforming the LGL problem into a cascaded LiDAR Place Recognition (LPR) and pose estimation problem from the perspective of image fusion. An end-to-end multi-BEV fusion network is designed to extract uniform features, equipping UniLGL with spatial and material uniformity. To ensure robust LGL across heterogeneous LiDAR sensors, a viewpoint invariance hypothesis is introduced, which replaces the conventional translation equivariance assumption commonly used in existing LPR networks and supervises UniLGL to achieve sensor type uniformity in both global descriptors and local feature representations. Moreover, UniLGL introduces a pipeline that leverages a pre-trained single-image Vision Foundation Model (VFM) for feature extraction to enhance the multi-BEV fusion LPR network, enabling strong generalization with only a few LiDAR data for fine-tuning. Finally, based on the mapping between local features on the 2D BEV image and the point cloud, a robust global pose estimator is derived that determines the global minimum of the global pose on $\text{SE}(3)$ without requiring additional registration. To validate the effectiveness of the proposed uniform LGL, extensive benchmarks are conducted in real-world environments, and the results show that the proposed UniLGL is demonstratively competitive compared to other State-of-the-Art (SOTA) LGL methods. Furthermore, UniLGL has been deployed on diverse platforms, including full-size trucks and agile Micro Aerial Vehicles (MAVs), to enable high-precision localization and mapping as well as multi-MAV collaborative exploration in port and forest environments, demonstrating the applicability of UniLGL in industrial and field scenarios. The code will be released at https://github.com/shenhm516/UniLGL.