High-frequency dynamic targets introduce substantial appearance variations in LiDAR scans of the same location over time, posing a major challenge for place recognition. To tackle this, we propose DyLPR, a cascaded PR framework that integrates a LiDAR depth inpainting network and a place recognition network (PTN-Net), leveraging the complementary strengths of convolutional neural networks (CNNs) and transformer architectures. Specifically, a supervised encoder–decoder combining CNNs and transformers is employed to effectively handle dynamic masks across multiple scales. A semantic auxiliary branch and a hybrid loss function are further introduced to enhance both structural consistency and texture fidelity, resulting in more accurate and realistic depth inpainting. PTN-Net employs a pyramidal convolutional backbone with parallel Transformer-NetVLAD modules to capture long-range multiscale dependencies and adaptively aggregate salient features, while context gating refines integration to improve descriptor compactness and discriminability. Extensive evaluations on the LiDAR depth inpainting dataset, constructed from benchmark SemanticKITTI and real-vehicle data, demonstrate that our method achieves competitive inpainting performance and outperforms existing approaches in place recognition under dynamic conditions. For instance, DyLPR improves Recall@1 by an absolute 5.4% over the best baseline.

Place recognition (PR) is a critical component of simultaneous localization and mapping in the fields of autonomous driving and robotics. In outdoor large-scale and complex environments, existing vision-based place recognition (VPR) methods typically rely on single-camera input, which is inherently limited by its restricted field of view and, thus, vulnerable to viewpoint variations. To effectively fill the aforementioned drawbacks, we propose VI_MCPR, a novel method that supports input from any number of cameras. This method utilizes a multibranch, weight-sharing encoder structure to encode image features from multiperspective simultaneously. The robust feature attention pooling block is then utilized to learn high-order nonlinear features and latent correlations between features, effectively mitigating the loss of key features during down-sampling. To generate a discriminative global descriptor representing the image, we designed a geometry and spatial relationship enhanced block, named graph-SE-transform (GSET), which captures the overall shape of objects in a manner similar to the human visual system. Extensive comparative experiments on the NuScenes, Argoverse 2 Sensors, and real-vehicle datasets demonstrate that VI_MCPR outperforms state-of-the-art VPR methods. Compared to the strongest representative baselines, our approach increases PR performance by approximately 6% under viewpoint variations, by approximately 6% in dynamic environments, and by approximately 8% in extreme scenarios such as adverse weather, illumination changes, and low-texture conditions.

Visual place recognition (VPR) improves the localization accuracy of agents in complex environments by extracting effective environmental representations for place matching, and it does not rely on additional high-precision, high-cost sensors or digital maps. However, current VPR research still faces limitations when simultaneously addressing the challenges of viewpoint changes and dynamic target interference, where it is not easy to obtain stable and reliable viewpoint-invariant environmental representations. To address these challenges, inspired by the human ability to recognize scenes, this paper customizes a place recognition network called VDI-Net based on multi-view images, immune to viewpoint changes and dynamic interference. Specifically, a dynamic target filtering module (DTF) is proposed to effectively filter out dynamic targets in complex environments. To tackle the challenge of viewpoint changes, a vision-surround Mamba module (VSM) is introduced to enhance the rotational invariance of features across different viewpoints. In the comparative validation of the nuScenes dataset and our real-vehicle collection dataset, the experimental results show that our proposed method achieves satisfactory performance in addressing the challenges of viewpoint changes and dynamic target interference. The proposed method outperforms current representative VPR baselines and surpasses some classical LiDAR-based and multimodal place recognition baselines.

Light detection and ranging (LiDAR) positioning has received great attention especially when satellites fail. However, the positioning accuracy is still subjected to the following. First, the LiDAR positioning accuracy is affected by the sparsity due to LiDAR beams and environment. Second, the existing methods for suppressing cumulative errors are based on ego-vehicle sensing that requires the motion of repeated paths. Moreover, the output frequency of LiDAR is low. To solve the above problems, an enhanced-LiDAR/ultrawideband (UWB)/inertial navigation system integrated positioning methodology is proposed. First, the enhanced LiDAR odometry module is designed to improve the resolution of LiDAR beams for more accurate odometry. Then, the cooperative optimization module is proposed to introduce UWB observation to suppress the accumulated error without relying on ego-vehicle sensing. Finally, the factor graph fusion module is used to fuse multisensor information dynamically and improve the output frequency. Experimental results prove the effectiveness of our methodology.

In large-scale long-term dynamic environments, high-frequency dynamic objects inevitably lead to significant changes in the appearance of the scene at the same location at different times, which is catastrophic for place recognition (PR). Therefore, how to eliminate the influence of dynamic objects to achieve robust PR has universal practical value for mobile robots and autonomous vehicles. To this end, we suggest a novel semantically consistent LiDAR PR method based on chained cascade network, called SC_LPR, which mainly consists of a LiDAR semantic image inpainting network (LSI-Net) and a semantic pyramid Transformer-based PR network (SPT-Net). Specifically, LSI-Net is a coarse-to-fine generative adversarial network (GAN) with a gated convolutional autoencoder as the backbone. To effectively address the challenges posed by variable-scale dynamic object masks, we integrate the updated Transformer block with mask attention and gated trident block into LSI-Net. Sequentially, in order to generate a discriminative global descriptor representing the point cloud, we design an encoder with pyramid Transformer block to efficiently encode long-range dependencies and global contexts between different categories in the inpainted semantic image, followed by an augmented NetVALD, a generalized VLAD (Vector of Locally Aggregated Descriptors) layer that adaptively aggregates salient local features. Last but not least, we first attempt to create a LiDAR semantic inpainting dataset, called LSI-Dataset, to effectively validate the proposed method. Experimental comparisons show that our method not only improves semantic inpainting performance by about 6%, but also improves PR performance in dynamic environments by about 8% compared to the representative optimal baseline. LSI-Dataset will be publicly available at https://github.KD.LPR.com/.

The dynamic interaction among Connected and Automated Vehicles (CAVs) is becoming increasingly complex, encompassing factors such as dynamic topology and the dynamic states of multiple CAVs. Existing cooperative control methods struggle to explicitly represent dynamic interaction, which can lead to dangerous behavior, severe congestion, and even accidents. In this paper, we propose a cooperative control methodology that aims to improve safety and efficiency in the merging zone by deeply representing dynamic interaction among multiple CAVs. Our proposed methodology, named GMA-DRL, utilizes a spatial graph convolutional encoder with a multi-head attention mechanism to explicitly represent dynamic interaction among vehicles. Furthermore, deep reinforcement learning based on Actor-Critic with temporal relation regularization is utilized to ensure the consistency of dynamic interaction and generate cooperative driving actions for multiple CAVs. The GMA-DRL is tested in a series of typical merging scenarios with dynamic interaction. Extensive experimental results show that the GMA-DRL outperforms the existing cooperative control models in term of headway, average speed and acceleration. It demonstrates that the GMA-DRL with explicitly represent dynamic interaction can improve safety and efficiency of multiple CAVs in the merging zone.

Place recognition plays a crucial role in simultaneous localization and mapping. Unfortunately, however, changes in viewpoints and conditions in large-scale environments impose tricky challenges for PR. To this end, this article specifically proposes an explicit points-of-interest driven PR method, which consists of a road segmentation module based on grid-wise patch U-transformer and a PR module based on regions of interest siamese transformer NetVLAD (RI_STV). Especially for RI_STV, in the individual dimension, it is dedicated to exploring the local topological features of nonroad regions of interest. In the spatial dimension, an improved Transformer is introduced to capture the global interactions between features of interest. In the cluster dimension, NetVLAD embedded with weighted pooling is created to perform weighted aggregation of feature clusters to generate discriminative and general descriptors. Evaluation on various datasets shows that our customized method is not only impressively competitive, but also strikes the best balance between accuracy and real-time performance.