The perception systems of autonomous vehicles face significant challenges under adverse conditions, with issues such as obscured objects and false detections due to environmental noise. Traditional approaches, which typically focus on noise removal, often fall short in such scenarios. Addressing the lack of diverse adverse weather data in existing automotive datasets, we propose a novel data augmentation method that integrates realistically simulated adverse weather effects into clear condition datasets. This method not only addresses the scarcity of data but also effectively bridges domain gaps between different driving environments. Our approach centers on a conditional generative model that uses segmentation maps as a guiding mechanism to ensure the authentic generation of adverse effects, which greatly enhances the robustness of perception and object detection systems in autonomous vehicles, operating under varied and challenging conditions. Besides the capability of accurately and naturally recreating over 90% of the adverse effects, we demonstrate that this model significantly improves the performance and accuracy of deep learning algorithms for autonomous driving, particularly in adverse weather scenarios. In the experiments employing our augmented approach, we achieved a 2.46% raise in the 3D average precision, a marked enhancement in detection accuracy and system reliability, substantiating the model’s efficacy with quantifiable improvements in 3D object detection compared to models without augmentation. This work not only serves as an enhancement of autonomous vehicle perception systems under adverse conditions but also marked an advancement in deep learning models in adverse condition research.

LiDAR point clouds are significantly impacted by snow in driving scenarios, introducing scattered noise points and phantom objects, thereby compromising the perception capabilities of autonomous driving systems. Current effective methods for removing snow from point clouds largely rely on outlier filters, which mechanically eliminate isolated points. This research proposes a novel translation model for LiDAR point clouds, the ‘L-DIG’ (LiDAR depth images GAN), built upon refined generative adversarial networks (GANs). This model not only has the capacity to reduce snow noise from point clouds, but it also can artificially synthesize snow points onto clear data. The model is trained using depth image representations of point clouds derived from unpaired datasets, complemented by customized loss functions for depth images to ensure scale and structure consistencies. To amplify the efficacy of snow capture, particularly in the region surrounding the ego vehicle, we have developed a pixel-attention discriminator that operates without downsampling convolutional layers. Concurrently, the other discriminator equipped with two-step downsampling convolutional layers has been engineered to effectively handle snow clusters. This dual-discriminator approach ensures robust and comprehensive performance in tackling diverse snow conditions. The proposed model displays a superior ability to capture snow and object features within LiDAR point clouds. A 3D clustering algorithm is employed to adaptively evaluate different levels of snow conditions, including scattered snowfall and snow swirls. Experimental findings demonstrate an evident de-snowing effect, and the ability to synthesize snow effects.

Transformer-based models have gained popularity in the field of natural language processing (NLP) and are extensively utilized in computer vision tasks and multi-modal models such as GPT4. This paper presents a novel method to enhance the explainability of transformer-based image classification models. Our method aims to improve trust in classification results and empower users to gain a deeper understanding of the model for downstream tasks by providing visualizations of class-specific maps. We introduce two modules: the “Relationship Weighted Out” and the “Cut” modules. The “Relationship Weighted Out” module focuses on extracting class-specific information from intermediate layers, enabling us to highlight relevant features. Additionally, the “Cut” module performs fine-grained feature decomposition, taking into account factors such as position, texture, and color. By integrating these modules, we generate dense class-specific visual explainability maps. We validate our method with extensive qualitative and quantitative experiments on the ImageNet dataset. Furthermore, we conduct a large number of experiments on the LRN dataset, which is specifically designed for automatic driving danger alerts, to evaluate the explainability of our method in scenarios with complex backgrounds. The results demonstrate a significant improvement over previous methods. Moreover, we conduct ablation experiments to validate the effectiveness of each module. Through these experiments, we are able to confirm the respective contributions of each module, thus solidifying the overall effectiveness of our proposed approach.

The accurate prediction of vehicle behavior is crucial for autonomous driving systems, impacting their safety and efficiency in complex urban environments. To address the challenge of multi-agent trajectory prediction, we propose a novel model integrating multiple input modalities, including historical trajectories, map data, vehicle features, and interaction information. Our approach employs a Conditional Variational Autoencoder (CVAE) framework with a decoder that predicts control actions using the Gaussian Mixture Model (GMM) and then converts these actions into dynamically feasible trajectories through a bicycle model. Evaluated on the nuScenes dataset, the model achieves great performance across key metrics, including minADE₅ of 1.26 and minFDE₅ of 2.85, demonstrating robust performance across various vehicle types and prediction horizons. These results indicate that integrating multiple data sources, physical models, and probabilistic methods significantly improves trajectory prediction accuracy and reliability for autonomous driving. Our approach generates diverse yet realistic predictions, capturing the multimodal nature of future outcomes while adhering to Physical Constraints and vehicle dynamics.

Traffic accidents frequently lead to fatal injuries, claiming millions of lives every year. To mitigate driving hazards and ensure personal safety, it is crucial to assist vehicles in anticipating the objects in the traffic scene (treated here as important objects) which may pose a threat during the driving task. Previous research on important object detection primarily assessed the importance of individual participants, treating them as independent entities and frequently neglecting the interconnections among these participants. Unfortunately, this approach has proven less effective in detecting important objects in complex scenarios. In this work, we introduce Driving scene Relationship Understanding transformer (DRUformer), designed to enhance the important object detection task. The DRUformer is a transformer-based multi-modal important object detection model that takes into account the relationships between all the participants in the driving scenario. Recognizing that driving intention also significantly affects the detection of important objects during driving, we have incorporated a module for embedding driving intention. To assess the performance of our approach, we conducted comparative experiments on the DRAMA dataset, comparing our model against other state-of-the-art (SOTA) models. The results demonstrated a noteworthy 16.2% improvement in mIoU and a substantial 12.3% boost in ACC compared to SOTA methods. Furthermore, we conducted a qualitative analysis of our model’s ability to detect important objects across different road scenarios and classes, highlighting its effectiveness in diverse contexts. Finally, we conducted various ablation studies to assess the efficiency of the proposed modules in our DRUformer model. Through extensive experimentation, it has been demonstrated that our model performs exceptionally well in the task of driving scene important object localization. The code is publicly available on the following link: https://github.com/oniu-uin0/DRUformer