Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities. However, the interdependencies among modalities increase the susceptibility of multimodal models to adversarial attacks. Existing methods mainly focus on attacks on specific modalities or indiscriminately attack all modalities. In this paper, we find that these approaches ignore the differences between modalities in their contribution to final robustness, resulting in suboptimal robustness performance. To bridge this gap, we introduce Vulnerability-Aware Robust Multimodal Adversarial Training (VARMAT), a probe-in-training adversarial training method that improves multimodal robustness by identifying the vulnerability of each modality. To be specific, VARMAT first explicitly quantifies the vulnerability of each modality, grounded in a first-order approximation of the attack objective (Probe). Then, we propose a targeted regularization term that penalizes modalities with high vulnerability, guiding robust learning while maintaining task accuracy (Training). We demonstrate the enhanced robustness of our method across multiple multimodal datasets involving diverse modalities. Finally, we achieve {12.73%, 22.21%, 11.19%} robustness improvement on three multimodal datasets, revealing a significant blind spot in multimodal adversarial training.

Imitation learning based planning tasks on the nuPlan dataset have gained great interest due to their potential to generate human-like driving behaviors. However, open-loop training on the nuPlan dataset tends to cause causal confusion during closed-loop testing, and the dataset also presents a longtail distribution of scenarios. These issues introduce challenges for imitation learning. To tackle these problems, we introduce CAFE-AD, a Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving method, designed to enhance feature representation across various scenario types. We develop an adaptive feature pruning module that ranks feature importance to capture the most relevant information while reducing the interference of noisy information during training. Moreover, we propose a cross-scenario feature interpolation module that enhances scenario information to introduce diversity, enabling the network to alleviate overfitting in dominant scenarios. We evaluate our method CAFEAD, on the challenging public nuPlan Test14-Hard closed-loop simulation benchmark. The results demonstrate that CAFEAD outperforms state-of-the-art methods including rule-based and hybrid planners, and exhibits the potential in mitigating the impact of long-tail distribution within the dataset. Additionally, we further validate its effectiveness in real-world environments. The code and models will be made available at https://github.com/AlniyatRui/CAFE-AD.

Integrating large language models (LLMs) into autonomous driving motion planning has recently emerged as a promising direction, offering enhanced interpretability, better controllability, and improved generalization in rare and long-tail scenarios. However, existing methods often rely on abstracted perception or map-based inputs, missing crucial visual context, such as fine-grained road cues, accident aftermath, or unexpected obstacles, which are essential for robust decision-making in complex driving environments. To bridge this gap, we propose VLMPlanner, a hybrid framework that combines a learning-based real-time planner with a vision-language model (VLM) capable of reasoning over raw images. The VLM processes multi-view images to capture rich, detailed visual information and leverages its common-sense reasoning capabilities to guide the real-time planner in generating robust and safe trajectories. Furthermore, we develop the Context-Adaptive Inference Gate (CAI-Gate) mechanism that enables the VLM to mimic human driving behavior by dynamically adjusting its inference frequency based on scene complexity, thereby achieving an optimal balance between planning performance and computational efficiency. We evaluate our approach on the large-scale, challenging nuPlan benchmark, with comprehensive experimental results demonstrating superior planning performance in scenarios with intricate road conditions and dynamic elements.

In the field of simultaneous localization and mapping (SLAM), map-based localization has been widely used in autonomous driving, particularly for all-speed and all-road adaptive cruise, automatic parking, and other high-level functions. As a result, LiDAR sensors are frequently used in visual-based SLAM to improve the overall accuracy of ego-motion estimation and environment reconstruction. In this article, a novel tightly coupled monocular hybrid visual LiDAR SLAM (HVL-SLAM), which utilizes both visual and LiDAR measurements in tracking and mapping. First, the proposed method reduces the 3-D uncertainty of features by employing object segmentation and Delaunay triangulation. The motion between adjacent frames is then estimated using a hybrid tracking module that minimizes photometric and reprojection error. Finally, a joint optimization method for refining the pose is proposed, which incorporates visual and LiDAR measurements into optimization with dynamic weights, resulting in higher positioning accuracy and robustness. The experiments on the public KITTI odometry benchmark and real-world outdoor datasets demonstrate that HVL-SLAM outperforms state-of-the-art approaches in terms of pose estimation and mapping performance. The code is released to the community. Code available athttps://github.com/kinggreat24/hvl_slam.

This article presents a transformer and convolutional neural network (CNN) hybrid deep neural network for semantic segmentation of very high resolution (VHR) remote sensing imagery. The model follows an encoder–decoder structure. The encoder module uses a new universal backbone Swin transformer to extract features to achieve better long-range spatial dependencies modeling. The decoder module draws on some effective blocks and successful strategies of CNN-based models in remote sensing image segmentation. In the middle of the framework, an atrous spatial pyramid pooling block based on depthwise separable convolution (SASPP) is applied to obtain a multiscale context. A U-shaped decoder is used to gradually restore the size of the feature maps. Three skip connections are built between the encoder and decoder feature maps of the same size to maintain the transmission of local details and enhance the communication of multiscale features. A squeeze-and-excitation (SE) channel attention block is added before segmentation for feature augmentation. An auxiliary boundary detection branch is combined to provide edge constraints for semantic segmentation. Extensive ablation experiments were conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam benchmarks to test the effectiveness of multiple components of the network. At the same time, the proposed method is compared with the current state-of-the-art methods on the two benchmarks. The proposed hybrid network achieved the second highest overall accuracy (OA) on both the Potsdam and Vaihingen benchmarks (code and models are available athttps://github.com/zq7734509/mmsegmentation-multilayer).