With the fast-developing deep learning models in the field of autonomous driving, the research on the uncertainty estimation of deep learning models has also prevailed. Herein, a pyramid Bayesian deep learning method is proposed for the model uncertainty evaluation of semantic segmentation. Semantic segmentation is one of the most important perception problems in understanding visual scene, which is critical for autonomous driving. This study to optimize Bayesian SegNet for uncertainty evaluation. This paper first simplifies the network structure of Bayesian SegNet by reducing the number of MC-Dropout layer and then introduces the pyramid pooling module to improve the performance of Bayesian SegNet. mIoU and mPAvPU are used as evaluation matrics to test the proposed method on the public Cityscapes dataset. The experimental results show that the proposed method improves the sampling effect of the Bayesian SegNet, shortens the sampling time, and improves the network performance.

Vision-based localization techniques and detection technologies are key algorithms for the localization and navigation of unmanned vehicles. Especially in scenarios where GPS signals are missing, Simultaneous Localization and Mapping (SLAM) techniques that rely on vision, inertial navigation system (INS) and other sensors have important applications. Among them, vision combined with the IMU SLAM system has the advantage of realistic scale, which is lacking in monocular vision and computational power compared to multi-visual vision, so it is suitable for application in an unmanned vehicle system. In this paper, we propose a fusion localization algorithm that combines a visual-inertial SLAM system and map road information, processing road information in a map under structured roads, and detecting lane lines and locating its local position by a monocular camera, applying a strategy of position prediction and update for map-SLAM fusion localization. It solves the problem of accumulating errors in a pure SLAM system without loopback and provides accurate global-local positioning results for unmanned vehicle positioning and navigation.

The advancement of autonomous driving technologies necessitates the development of sophisticated object detection systems capable of integrating heterogeneous sensor data to overcome the inherent limitations of unimodal approaches. While multi-modal fusion strategies offer promising solutions, they confront significant challenges such as data alignment complexities in early fusion and computational burdens coupled with overfitting risks in deep fusion methodologies. To address these issues, we propose a Multi-modal Multi-class Late Fusion (MMLF) framework that operates at the decision level. This late-fusion strategy preserves the architectural integrity of individual detectors and facilitates the flexible integration of diverse modalities. A key innovation of our approach is the incorporation of an evidence-theoretic uncertainty quantification mechanism, based on Dempster-Shafer theory, which provides a mathematically grounded confidence measure. Comprehensive offline evaluations on the KITTI benchmark dataset demonstrate the effectiveness of our framework, showing substantial performance improvements across multiple metrics (including 2D detection, 3D detection, and bird’s-eye view tasks) while simultaneously achieving significant reductions in uncertainty estimates—by approximately 77% for cars, 76% for pedestrians, and 67% for cyclists. These results collectively enhance both the reliability and interpretability of object detection outcomes. This work provides a versatile and scalable solution for multi-modal object detection that effectively addresses critical challenges in autonomous driving applications.

Brain-computer interfaces (BCIs) establish a direct communication pathway between the brain and external devices and have been widely applied in upper limb rehabilitation for hemiplegic patients. However, significant individual variability in motor imagery electroencephalogram (MI-EEG) signals leads to poor generalization performance of MI-based BCI decoding methods to new patients. This paper proposes a Multi-scale Frequency domain Feature-based Dynamic graph Attention Network (MFF-DANet) for upper limb MI decoding in hemiplegic patients. MFF-DANet employs convolutional kernels of various scales to extract feature information across multiple frequency bands, followed by a channel attention-based average pooling operation to retain the most critical frequency domain features. Additionally, MFF-DANet integrates a graph attention convolutional network to capture spatial topological features across different electrode channels, utilizing electrode positions as prior knowledge to construct and update the graph adjacency matrix. We validated the performance of MFF-DANet on the public PhysioNet dataset, achieving optimal decoding accuracies of 61.6% for within-subject case and 52.7% for cross-subject case. t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization of the features demonstrates the effectiveness of each designed module, and visualization of the adjacency matrix indicates that the extracted spatial topological features have physiological interpretability.

The advancement of autonomous driving technologies necessitates the development of sophisticated object detection systems capable of integrating heterogeneous sensor data to overcome the inherent limitations of unimodal approaches. While multi-modal fusion strategies offer promising solutions, they confront significant challenges including data alignment complexities in early fusion and computational burdens coupled with overfitting risks in deep fusion methodologies. We propose a Multi-modal Multi-class Late Fusion (MMLF) framework that operates at the decision level. This design preserves the architectural integrity of individual detectors and facilitates the flexible integration of diverse modalities. A key innovation of our approach is the incorporation of an evidence-theoretic uncertainty quantification mechanism, built upon Dempster-Shafer theory, which provides a mathematically grounded measure of confidence and significantly enhances the reliability and interpretability of the detection outcomes. Comprehensive experimental evaluation on the KITTI benchmark dataset demonstrates that our method achieves substantial performance improvements across multiple metrics, including 2D detection, 3D localization, and bird’s-eye view tasks. The framework reduces uncertainty estimates across different object categories. This work provides a versatile and scalable solution for multi-modal object detection that effectively addresses critical challenges in autonomous driving applications.

In the field of autonomous driving, there have been many excellent perception models for object detection, semantic segmentation, and other tasks, but how can we effectively use the perception models for vehicle planning? Traditional autonomous vehicle trajectory prediction methods not only need to obey traffic rules to avoid collisions, but also need to follow the prescribed route to reach the destination. In this paper, we propose a Transformer-based trajectory prediction network for end-to-end autonomous driving without rules called Target-point Attention Transformer network (TAT). We use the attention mechanism to realize the interaction between the predicted trajectory and the perception features as well as target-points. We demonstrate that our proposed method outperforms existing conditional imitation learning and GRU-based methods, significantly reducing the occurrence of accidents and improving route completion. We evaluate our approach in complex closed loop driving scenarios in cities using the CARLA simulator and achieve state-of-the-art performance.