Cross-modality registration between 2D images and 3D point clouds is an important task in autonomous driving and robotics. Existing methods predict the correspondence between images and point clouds by matching patterns of pixel and point features learned by deep neural networks. However, due to the significant differences in their representation and feature processing, the feature spaces are vastly different. The insufficient feature interaction between image and point cloud branches leads to a lack of information necessary for relational reasoning, which is crucial for establishing the correspondence between pixels and points. To address these problems, we propose a Cross-Modality Relation Module (CMRM) that leverages the relations between different levels of features from images and point clouds. This module facilitates rich information exchange between the feature extractor branches corresponding to the two modalities. Additionally, we introduce a Relation-Aware Fusion Module (RAFM) that effectively integrates multimodal features and their relations. The experimental results on KITTI dataset show improvements over the state-of-the-art methods. The code will be publicly available at https://github.com/JLUrob/RelaI2P.

3D object detection from a Bird’s Eye View (BEV) has emerged as a novel perception paradigm for autonomous driving scenarios. While most current 3D object detection methods still rely on the conventional Cartesian coordinates, they fail to align with the non-aligned coordinate system inherent in image geometry. The Polar coordinates, on the other hand, better fit with the geometric shape corresponding to the perception of cameras. However, transforming between coordinate systems introduces distortions in the perception information, resulting in issues such as “Weak Adaptability to Heatmap Distribution” and “Offset in the Center Point of the Bounding Box.” To address these challenges, this paper proposes a cutting-edge 3D object detection model named PolarBEVU, which leverages the bird’s-eye view under the Polar coordinates along with multi-camera unprojection. The model introduces an innovative “Deformable Uniform Heatmap Distribution” method that adjusts heatmap computations based on box shapes, generating high-quality heatmaps and effectively resolving the issue of “Weak Adaptability to Heatmap Distribution.” Moreover, the model incorporates the concept of “Dynamic High-risk Regression Region” to enhance the accuracy and robustness of the center point regression at the bounding box, thus mitigating the issue of “Offset in the Center Point of the Bounding Box.” In extensive experiments on the nuScenes dataset, PolarBEVU achieves impressive results with 49.9% mAP and 57.4% NDS on the test set, surpassing other comparative approaches and reaching the state-of-the-art (SOTA) performance among methods utilizing Polar coordinates. This clearly demonstrates the efficacy and superiority of PolarBEVU. In addition, the model is successfully deployed on Nvidia Jetson AGX Orin, showcasing real-time inference speeds of 31.42ms. These findings affirm PolarBEVU’s potential for practical applications. Code is available athttps://github.com/JLUrob/PolarBEVU.

Place recognition is a fundamental task in robotics, enabling loop closure detection in simultaneous localization and mapping (SLAM), and re-localization on prior maps. Current range image-based networks use single-column convolution to maintain feature invariance to shifts in image columns caused by light detection and ranging (LiDAR) viewpoint change. However, this raises the issues such as “restricted receptive fields” and “excessive focus on local regions”, degrading the performance of networks, especially in scenarios with movable objects. In this paper, a lightweight circular convolutional Transformer network named CCTNet is proposed, which aims to boost performance by capturing structural information in point clouds and facilitating cross-dimensional interaction of spatial and channel information. Initially, a Circular Convolution Module (CCM) is introduced, expanding the network’s perceptual field while maintaining feature consistency across varying LiDAR perspectives. Then, a Range Transformer Module (RTM) is proposed, which enhances place recognition accuracy in scenarios with movable objects by employing a combination of channel and spatial attention mechanisms. Furthermore, we propose an overlap-based loss function, transforming the place recognition task from a binary loop closure classification into a regression problem linked to the overlap between LiDAR frames. Through extensive experiments on the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) and Ford Campus datasets, CCTNet surpasses comparable methods, achieving Recall@1 of 0.924 and 0.965, and Recall@1% of 0.990 and 0.993 on the test set, showcasing superior performance. Results on the self-collected dataset further demonstrate the proposed method’s potential for practical implementation in complex scenarios to handle movable objects, showing improved generalization across various datasets.

Global localization is a challenging task for intelligent robots, as its accuracy directly contributes to the performance of downstream navigation and planning tasks. However, existing literature focus more on the place retrieval and the success rate of localization, with limited attention given to the metrics of position estimation. In this paper, a single-shot global LiDAR localization method is proposed with the ultimate goal of achieving high position accuracy, inspired by the positioning approach of multi-constellation localization systems. Initially, we perform coarse localization using global descriptors and select observation points along with their corresponding coordinates based on the obtained coarse localization results. Coordinates can be acquired from a pre-built map, GNSS, or other devices. Then, a lightweight LiDAR odometry method is designed to estimate the distance between the retrieved data and the observation points. Ultimately, the localization problem is transformed into an optimization problem of solving a system of multiple sphere equations. The experimental results on the KITTI dataset and the self-collected dataset demonstrate that our method achieves an average localization error (including errors in the z-axis) of 0.89 meters. In addition, it achieves retrieval efficiency of 0.357 s per frame on the former dataset and 0.214 s per frame on the latter one. Code and data are available at https://github.com/jlurobot/multi-constellation-localization.

In independent component analysis (ICA) and its diverse algorithms, uniqueness is the most essential requirement and rationality problem compared with performances of existence, stability and convergence. For ICA’s maximum non-Gaussianity estimation (MNE), many achievements have been made in recent twenty years based on uniqueness assumption, which has been taken for granted all along except for some intuitive interpretation. From the perspective of constrained cost function optimization, the paper is to provide a mathematical proof for uniqueness principle in MNE. The research focuses on skewless assumption and kurtosis-based cost function with basic linear ICA model. The relationship between the Kuhn–Tucker (K–T) points of cost function and the local maxima of non-Gaussianity are derived with the help of constrained optimization theory, and then a conclusion is drawn that there is a one-to-one correspondence between independent components and the local maxima, i.e. maximum non-Gaussianity is the sufficient and necessary condition for independent sources recovery. Moreover, the result also leads to an alternative and straightforward approach to the proof of Xu’ one-bit-matching conjecture for the availability of multi-unit approaches.