With the continued development of artificial intelligence technology, unmanned surface vehicles (USVs) have attracted the attention of countless domestic and international specialists and academics. In particular, path planning is a core technique for the autonomy and intelligence process of USVs. The current literature reviews on USV path planning focus on the latest global and local path optimization algorithms. Almost all algorithms are optimized by concerning metrics such as path length, smoothness, and convergence speed. However, they also simulate environmental conditions at sea and do not consider the effects of sea factors, such as wind, waves, and currents. Therefore, this paper reviews the current algorithms and latest research results of USV path planning in terms of global path planning, local path planning, hazard avoidance with an approximate response, and path planning under clustering. Then, by classifying USV path planning, the advantages and disadvantages of different research methods and the entry points for improving various algorithms are summarized. Among them, the papers which use kinematic and dynamical equations to consider the ship’s trajectory motion planning for actual sea environments are reviewed. Faced with multiple moving obstacles, the literature related to multi-objective task assignment methods for path planning of USV swarms is reviewed. Therefore, the main contribution of this work is that it broadens the horizon of USV path planning and proposes future directions and research priorities for USV path planning based on existing technologies and trends.

The primary objective of this study is to investigate maritime collision avoidance and trajectory planning in the presence of dynamic and static obstacles during navigation. Adhering to safety regulations is crucial when executing ship collision avoidance tasks. To address this issue, we propose an optimized APF-ACO algorithm for collision avoidance and path planning. First, a ship collision avoidance constraint model is constructed based on COLREGs to enhance the safety and applicability of the algorithm. Then, by introducing factors such as velocity, position, and shape parameters, the traditional APF method is optimized, creating a dynamic APF gradient for collision avoidance decision making in the face of dynamic obstacles. Furthermore, the optimized APF method is integrated with the ant colony optimization algorithm, the latter modified to overcome the inherent local optimality issues in the APF method. Ultimately, validations are conducted in three areas: static avoidance and planning in restricted sea areas, avoidance under conditions of mixed static and dynamic obstacles, and avoidance in situations of multiple ship encounters. These serve to illustrate the feasibility and efficacy of the proposed algorithm in achieving dynamic ship collision avoidance while simultaneously completing path-planning tasks.

Continuous-flow microfluidic large-scale integration (mLSI) shows increasing importance in biological/chemical fields, thanks to its advantages in miniaturization and high throughput. Current mLSI is designed manually, which is time-consuming and error-prone. In recent years, design automation research for mLSI has evolved rapidly, aiming to replace manual labor by computers. However, previous design automation approaches used to design each microfluidic layer separately and over-simplify the layer interactions to various degrees, which resulted in a gap between realistic requirements and automatically generated designs. In this paper, we propose a module model library to accurately model microfluidic components involving layer interactions; and we propose a co-layout synthesis tool, Columba, which generates AutoCAD-compatible designs that fulfill all designs rules and can be directly used for mask fabrication. Columba takes plain-text netlist descriptions as inputs, and performs simultaneous placement and routing for multiple layers while ensuring the planarity of each layer. We validate Columba by fabricating two of its output designs. Columba is the first design automation tool that can seamlessly synchronize with the manufacturing flow.

Predicting ship trajectories plays a vital role in ensuring navigational safety, preventing collision incidents, and enhancing vessel management efficiency. The integration of advanced machine learning technology for precise trajectory prediction is emerging as a new trend in sophisticated geospatial applications. However, the complexity of the marine environment and data quality issues pose significant challenges to accurate ship trajectory forecasting. This study introduces an innovative trajectory prediction method, combining data encoding representation, attribute correlation attention module, and long short-term memory network. Initially, we process AIS data using data encoding conversion technology to improve representation efficiency and reduce complexity. This encoding not only preserves key information from the original data but also provides a more efficient input format for deep learning models. Subsequently, we incorporate the attribute correlation attention module, utilizing a multi-head attention mechanism to capture complex relationships between dynamic ship attributes, such as speed and direction, thereby enhancing the model’s understanding of implicit time series patterns in the data. Finally, leveraging the long short-term memory network’s capability for processing time series data, our approach effectively predicts future ship trajectories. In our experiments, we trained and tested our model using a historical AIS dataset. The results demonstrate that our model surpasses other classic intelligent models and advanced models with attention mechanisms in terms of trajectory prediction accuracy and stability.

The increasing complexity and size of design space poses significant challenges for integrated circuit (IC) design. This article discusses the potential of machine learning (ML) methods to address these challenges and provides a comprehensive survey of the current state of knowledge along both IC design problems and ML-based solutions. The article also summarizes the open problems at the intersection of advanced IC design and ML.

As global economies continue to expand, maritime trade is projected to double by the year 2050. In this context, the development of a new generation of maritime intelligent supervision systems, which rely on precise information perception and machine learning-based technologies, is crucial for ensuring the safety of maritime navigation. Traditional methods for detecting abnormal ship behavior often suffer from inadequate feature extraction capabilities, leading to ineffective and inaccurate anomaly detection. To address this issue, this paper introduces a Transformer-GSA encoder detection model. This model enhances ship information data through BCE-GAN, extracts multi-layer convolutional features, and utilizes the Transformer-GSA module to capture the dependencies between trajectory features and time-series data, thereby effectively identifying abnormal ship behaviors. An evaluation conducted using AIS data from the Yantai-Qingdao route in January 2021 demonstrates that the model achieves an accuracy of 96.26%, with a reduced parameter count of 12.11M. These results confirm the model’s efficacy and superiority in detecting abnormal ship trajectories, contributing to the reduction of maritime accidents and illegal activities, alleviating the management burden on duty personnel, and enhancing the quality of intelligent ship traffic services and port operation efficiency under the maritime Internet of Things architecture.