Accurate odometry is crucial for mapping and localization of autonomous vehicles in unknown environment. Deep neural networks have shown significant promise in self-supervised odometry, enabling pose estimation from consecutive sensor inputs. However, existing self-supervised visual odometry methods face scale ambiguity issue due to the inaccuracy of relative depth estimation, and self-supervised LiDAR odometry methods suffer from sparse data and the difficulty of correspondence searching. To address these challenges, we propose Self-FO, a self-supervised multi-sensor fusion odometry framework that effectively integrates image and point cloud data and overcomes the limitations of single-sensor methods. First, we utilize the inferred depth map as the fusion medium for image and point cloud, and realize multi-layer visual-LiDAR feature extraction and fusion through a novel homogeneous and heterogeneous channel exchange strategies. Then, we introduce a feature alignment and pose refinement module to fine-tune the coarse pose. By leveraging 2D-3D correspondences and a cross-modal attention mechanism, this module guides the image and point cloud features to focus on consistent scene-level observations and aligns features adaptively, significantly improving the accuracy of correspondence searching and enhancing the robustness and consistency of multimodal feature representations. Extensive experiments on KITTI and KITTI-360 dataset demonstrate that Self-FO outperforms existing learning-based odometry methods, delivering superior performance and scalability.

Segmentation of micro-adhesive spots in high-power laser packaging is challenged by morphological variability, complex backgrounds, and blurred edges, causing traditional models to fail from “feature dilution.” Inspired by physical optics knowledge, we propose a scattering neural representation framework guided by Rayleigh scattering theory. We first pretrain a denoising diffusion model, using light scattering properties, including wavelength, scattering angle, and particle number density as an inductive bias to generate high signal-to-noise ratio target features while suppressing background clutter. Subsequently, three synergistic attention modules, including an adaptive dual-attention module, an edge attention module, and a small object enhancement module, refine target features by dynamically expanding the receptive field, sharpening boundaries, and enhancing microtarget responses. Extensive experiments on proprietary and public datasets demonstrate that our model significantly outperforms state-of-the-art methods in precise segmentation and background interference suppression. This work translates physical insights into architectural advantages, establishing an efficient and interpretable paradigm for addressing the persistent challenge of industrial small object segmentation.

Radiation therapyis one of the primary treatment modalities for head and neck (H&N) cancer in clinical practice, aiming to deliver sufficient dose to Planning Target Volume (PTV) while protecting surrounding Organs at Risk (OAR) from or minimizing exposure to radiation. Quantitative dose prediction of various tissues and organs is a prerequisite for implementing intelligent precision radiotherapy. In order to improve dose prediction accuracy, we propose a generative adversarial network CPFTransGAN based on Cross Perception Fusion Transformer (CPF Transformer). Specifically, we design a CPF Transformer module through deeply integrating CNN and Transformer. Using the CPF Transformer as basic unit, we constructed a generator with four-stage encoding-decoding structure called CPFTransGenerator. An adaptive weight loss is used to train the discriminator to alleviate the issues of imbalance training in adversarial learning. To further improve the prediction accuracy, a multiscale cross-window encoding network is designed, which can constrain the differences between predicted dose and the reference one at different granularity levels by calculating feature losses between them at different scales. The proposed method is evaluated on two public head and neck cancer datasets and a local clinical dataset. Extensive experiments demonstrate the superior performance of our method compared with the state-of-the-art ones.

CNNs have demonstrated superior performance in medical image segmentation. To overcome the limitation of only using local receptive field, previous work has attempted to integrate Transformers into convolutional network components such as encoders, decoders, or skip connections. However, these methods can only establish long-distance dependencies for some specific patterns and usually neglect the loss of fine-grained details during downsampling in multi-scale feature extraction. To address the issues, we present a novel hybrid Transformer network called FocalTransNet. Specifically, we construct a focal-enhanced (FE) Transformer module by introducing dense cross-connections into a CNN-Transformer dual-path structure and deploy the FE Transformer throughout the entire encoder. Different from existing hybrid networks that employ embedding or stacking strategies, the proposed model allows for a comprehensive extraction and deep fusion of both local and global features at different scales. Besides, we propose a symmetric patch merging (SPM) module for downsampling, which can retain the fine-grained details by establishing a specific information compensation mechanism. We evaluated the proposed method on four different medical image segmentation benchmarks. The proposed method outperforms previous state-of-the-art convolutional networks, Transformers, and hybrid networks. The code for FocalTransNet is publicly available at https://github.com/nemanjajoe/FocalTransNet.

Point cloud completion recovers the complete point clouds from partial ones, providing numerous point cloud information for downstream tasks such as 3-D reconstruction and target detection. However, previous methods usually suffer from unstructured prediction of points in local regions and the discrete nature of the point cloud. To resolve these problems, we propose a point cloud completion network called TPDC. Representing the point cloud as a set of unordered features of points with local geometric information, we devise a Triangular Pyramid Extractor (TPE), using the simplest 3-D structure-a triangular pyramid-to convert the point cloud to a sequence of local geometric information. Our insight of revealing local geometric information in a complex environment is to design a Divide-and-Conquer Splitting Module in a Divide-and-Conquer Splitting Decoder (DCSD) to learn point-splitting patterns that can fit local regions the best. This module employs the Divide-and-Conquer approach to parallelly handle tasks related to fitting ground-truth values to base points and predicting the displacement of split points. This approach aims to make the base points align more closely with the ground-truth values while also forecasting the displacement of split points relative to the base points. Furthermore, we propose a more realistic and challenging benchmark, ShapeNetMask, with more random point cloud input, more complex random item occlusion, and more realistic random environmental perturbations. The results show that our method outperforms both widely used benchmarks as well as the new benchmark.

Inspired by psychological insights into individual behavior, we propose a novel cognition-oriented multiagent reinforcement learning (CORL) framework. CORL equips agents with two distinct types of cognition-situational and self-cognition-derived from local observations. To enhance the informativeness and precision of these cognition types, we introduce two information-theoretical regularizers: one to align situational cognition with the global state and the other to align self-cognition with each agent's identity for improved role differentiation and team coordination. In addition, the centralized training and decentralized execution framework is adopted to train the policy network. Our simulations demonstrate that CORL effectively harnesses local observations for enriched cooperation, leading to pronounced performance improvements, particularly in challenging tasks.

In this article, a neural network (NN)-based robust guaranteed cost control design is proposed for image-based visual servoing (IBVS) control of quadrotors. According to the dynamics of three subsystems (yaw, height, and lateral subsystems) derived from the quadrotor IBVS dynamic model, the main control design is to solve the robust control problem for the time-varying lateral subsystem with angle constraints and uncertain disturbances. Considering the system dynamics, a two-loop structure is conducted. The outer loop uses the linear quadratic regulator to solve the Riccati equation for the lateral image feature system, and the inner loop adopts the optimal robust guaranteed cost control to solve the lateral velocity system. For the lateral velocity system, the optimal robust control problem is transformed to solve the modified Hamilton-Jacobi-Bellman equation of the corresponding optimal control problem utilizing adaptive dynamic programming. The implementation is accomplished with the time-varying NN and the designed estimated weight update law. In addition, the stability and effectiveness are proved by the theoretic proof and simulations.

Liver tumor segmentation plays an essential role in diagnosis and treatment of hepatocellular carcinoma or metastasis. However, accurate and automatic tumor segmentation remains a challenging task, owing to vague boundaries and large variations in shapes, sizes, and locations of liver tumors. In this paper, we propose a novel hybrid end-to-end network, called TD-Net, which incorporates Transformer and direction information into convolution network to segment liver tumor from CT images automatically. The proposed TD-Net is composed of a shared encoder, two decoding branches, four skip connections, and a direction guidance block. The shared encoder is utilized to extract multi-level feature information, and the two decoding branches are respectively designed to produce initial segmentation map and direction information. To preserve spatial information, four skip connections are used to concatenate each encoder layer and its corresponding decoder layer, and in the fourth skip connection a Transformer module is constructed to extract global context. Furthermore, a direction guidance block is well-designed to rectify feature maps to further improve segmentation accuracy. Extensive experiments conducted on public LiTS and 3DIRCADb datasets validate that the proposed TD-Net can effectively segment liver tumor from CT images in an end-to-end manner and its segmentation accuracy surpasses those of many existing methods.