LiDAR simultaneously localization and mapping (SLAM), which provides accurate pose estimation and map construction, has a broad range of applications in autonomous driving. However, in some complex scenarios, such as degraded environments, SLAM performance is not up to the requirements of an autonomous driving system. To aim at the above-mentioned problems, we propose an accurate and robust LiDAR SLAM method. First, in order to avoid the uncertainty of LiDAR viewpoint variation, an angle-based feature extraction method is proposed based on the equiangular distribution property of the point cloud. Second, in view of the fact that odometry errors accumulate, we constructed a fixed-lag smoothing to jointly optimize the poses of multiple keyframes. In addition, to improve the environmental representation of point cloud maps within a sliding window, we maintain two types of abstract voxel maps. Finally, a voxel-based feature matching method based on voxel geometry constraints is proposed for refinement of the pose transformation within a sliding window. The performance and efficiency of the proposed method are evaluated on the public KITTI, Mulran, The Newer College dataset benchmarks and the dataset collected by our sensor system. The experimental results show that accurate feature extraction, efficient voxel feature matching, and consistent fixed-lag smoothing help our LiDAR SLAM method achieve better performance in multiple spatially and temporally large-scale scenarios compared to other existing state-of-the-art methods.

The online calibration of 4D millimeter-wave radar and camera is crucial for advancing perception and SLAM technologies in complex environments. It eliminates the reliance on manual labeling, offering real-time and convenience. However, the sparse nature of 4D radar point clouds presents challenges in establishing correspondences with camera images. This letter proposes an online 4D radar-camera online calibration method (4DRC-OC) that utilizes unified depth map representations for auxiliary training, ensuring feature alignment and modal unification between the two sensors. Due to the limited useful information within sparse depth maps, 4DRC-OC uses dynamic convolution to adaptively capture detailed features. Furthermore, this letter designs a correlation module based on channel-wise fusion (CMCF) that computes correlations between error depth maps and RGB-derived depth maps, thereby enhancing features to facilitate extrinsic parameter regression. Experimental results on the Dual-Radar dataset validate the superiority of the proposed approach in extrinsic calibration.

LiDAR-based simultaneous localization and mapping (SLAM) is crucial for achieving accurate pose estimation and map generation, thus serving as a foundational technology in the advancement of autonomous driving systems. In this letter, we introduce an accurate and robust feature-based LiDAR odometry method. Initially, we propose a feature extraction method centered on local extreme points, which capitalizes on the structural characteristics of local regions in LiDAR scans. Secondly, we purpose a multi-metric feature association approach for keyframe registration. This method leverages sparse and abstract geometric primitives to improve the accuracy and speed of keyframe matching. Additionally, Considering the varying impact of different metric features on pose constraints, an constraint contribution selection method is introduced to identify the most valuable features within the multi-metric feature set. Finally, the performance and efficiency of the proposed method are evaluated on the public KITTI, M2DGR, and The Newer College dataset, as well as our collected campus dataset. Experimental results demonstrate that the proposed method exhibits comparable performance compared to state-of-the-art LiDAR odometry methods across various scenarios.

Point cloud registration is a fundamental task in various intelligence applications, including simultaneous localization and mapping as well as scene reconstruction. However, in large-scale scenes, the majority of point clouds exhibit partial overlap, posing a significant challenge to the registration process. This study introduces a registration network, named OKR-Net, specifically designed to efficiently align partially overlapping point clouds. The OKR-Net comprises two innovative modules: a joint estimation module adept at identifying the keypoints within the overlapping region; and a coarse-to-fine registration module designed to aggregate the overlap and descriptor information, thereby reducing the outliers and yielding robust corresponding point pairs. In addition, an overlap labeling method for generated keypoints is introduced. The efficiency of the proposed registration network is validated utilizing two large-scale outdoor datasets: KITTI and NuScenes. The results demonstrate that the proposed method outperforms existing global registration methods, encompassing both classical and learning-based methods in real-world scenarios.

Light Detection and Ranging(LiDAR)-inertial simultaneous localization and mapping (SLAM) is a critical component in multi-sensor autonomous navigation systems, providing both accurate pose estimation and detailed environmental understanding. Despite its importance, existing optimization-based LiDAR-inertial SLAM methods often face key limitations: unreliable feature extraction, sensitivity to noise and sparsity, and the inclusion of redundant or low-quality feature correspondences. These weaknesses hinder their performance in complex or dynamic environments and fail to meet the reliability requirements of autonomous systems. To overcome these challenges, we propose a novel and accurate LiDAR-inertial SLAM framework with three major contributions. First, we employ a robust multi-category feature extraction method based on principal component analysis (PCA), which effectively filters out noisy and weakly structured points, ensuring stable feature representation. Second, to suppress outlier correspondences and enhance pose estimation reliability, we introduce a coarse-to-fine two-stage feature correspondence selection strategy that evaluates geometric consistency and structural contribution. Third, we develop an adaptive weighted pose estimation scheme that considers both distance and directional consistency, improving the robustness of feature matching under varying scene conditions. These components are jointly optimized within a sliding-window-based factor graph, integrating LiDAR feature factors, IMU pre-integration, and loop closure constraints. Extensive experiments on public datasets (KITTI, M2DGR) and a custom-collected dataset validate the proposed method’s effectiveness. Results show that our system consistently outperforms state-of-the-art approaches in accuracy and robustness, particularly in scenes with sparse structure, motion distortion, and dynamic interference, demonstrating its suitability for reliable real-world deployment.

Modern millimeter-wave (mmWave) radar heat map-based object detection techniques have shown significant potential. However, radar heat maps still pose challenges for fine-grained object differentiation, and fusing camera maps with radar heat maps remains challenging. This paper proposes a multi-sensor radar object segmentation (ROS) method that fuses radar range-angle (RA) heat maps with camera RGB maps, leveraging the advantages of camera sensors for extracting semantic information and mmWave radar for extracting object position information. A method for mapping RGB to the RA coordinate system (RMTR) is proposed, eliminating the need for additional training branches and sensor calibration. A Transformer is utilized to predict the range and angle matrices of each object separately from a global perspective. These matrices then undergo an element-wise multiplication (Hadamard product) operation to generate the final pseudo-RA map. For the fusion method, this paper introduces the cross-attention fusion module (CAF), which uses the cross-attention mechanism to achieve more efficient fusion by treating the pseudo-RA feature map as the Query and the RA feature map as the Key and Value. Extensive experiments show that the proposed method achieves state-of-the-art (SOTA) performance on the CRUW and CARRADA datasets, with fewer parameters and reduced computational complexity. Our code for RC-ROSNet is available at https://github.com/Zhuanglong2/RCROSNet.