In recent years, the safety issues of high-speed railways have remained severe. The intrusion of personnel or obstacles into the perimeter has often occurred in the past, causing derailment or parking, especially in the case of bad weather such as fog, haze, rain, etc. According to previous research, it is difficult for a single sensor to meet the application needs of all scenario, all weather, and all time domains. Due to the complementary advantages of multi-sensor data such as images and point clouds, multi-sensor fusion detection technology for high-speed railway perimeter intrusion is becoming a research hotspot. To the best of our knowledge, there has been no review of research on multi-sensor fusion detection technology for high-speed railway perimeter intrusion. To make up for this deficiency and stimulate future research, this article first analyzes the situation of high-speed railway technical defense measures and summarizes the research status of single sensor detection. Secondly, based on the analysis of typical intrusion scenarios in high-speed railways, we introduce the research status of multi-sensor data fusion detection algorithms and data. Then, we discuss risk assessment of railway safety. Finally, the trends and challenges of multi-sensor fusion detection algorithms in the railway field are discussed. This provides effective theoretical support and technical guidance for high-speed rail perimeter intrusion monitoring.

In this paper, the path planning problem of goods transportation is formulated as a traveling salesman problem (TSP). A novel path planning algorithm for warehouse robots based on a two-dimensional (2D) grid model is proposed to solve this type of TSP. Firstly, we simplified the traditional pile type warehouse as a node-based 2D grid model. Then, a new concept called the largest convex polygon (LCP) is introduced to illustrate the shortest path to traverse all goods locations in an ideal condition. Next, the remaining locations are classified by their relationship with LCP and designed path planning rules separately. Finally, we merged the paths of different types of cargo locations to get the final path. The experimental results show that, compared with ant colony optimization (ACO) and genetic algorithm (GA), our proposed algorithm could effectively reduce the computation time and total path length.

This paper explores the development of elastic LiDAR technology, focusing specifically on key components relevant to solid target scanning applications. By analyzing its fundamentals and working mechanisms, the advantages of elastic LiDAR for precise measurement and environmental sensing are demonstrated. This paper emphasizes innovative advances in emitters and scanning systems, and examines the impact of optical design on performance and cost. Various ranging methods are discussed. Practical application cases of elastic LiDAR are presented, and future trends and challenges are explored. The purpose of this paper is to provide a comprehensive perspective on the technical details of elastic LiDAR, the current state of application, and future directions. All instances of “LiDAR” in this paper specifically refer to elastic LiDAR.

Railway intrusion detection systems face significant challenges across diverse environmental conditions, including day-night illumination variations and adverse weather such as rain and fog. Traditional detection methods experience substantial performance degradation in multi-environmental scenarios, creating safety risks during railway operations. This study proposes DN-LSK-EMA-Net, a unified dual-stream framework for multi-environmental railway intrusion detection that processes day images and night images with rainy and foggy conditions simultaneously. The framework integrates six key innovations: Illumination-Adaptive Preprocessing (IAP), Large Selective Kernel (LSK) backbone, Efficient Multi-scale Attention (EMA) neck, FreqFusion modules, Context Anchor Attention (CAA) heads, and Cross-Domain Consistency (CDC) regularization. Comprehensive experiments across five environmental scenarios demonstrate superior performance with IoU of 0.72±0.003 and mAP of 0.76±0.002 on daytime datasets, IoU of 0.66±0.005 and mAP of 0.72±0.004 under nighttime conditions, and robust performance under rainy and foggy conditions. The unified architecture eliminates separate models for different environments, providing a practical solution for real-world railway safety applications.