In this letter, we explore the link-adding method to improve communication robustness of networks. Firstly, a robustness measure called communication robustness (CR) is presented, which not only confirms the global effect of the largest connected component on the network communicability, but captures the local communicability of all small connected components. Secondly, we respectively put forward a simulated annealing algorithm, a heuristic algorithm called r-Weak Interconnection Algorithm (r-WIA) and a greedy algorithm to improve CR of networks, where the 2-WIA can fast improve the network robustness with low time complexity O(N2). Finally, the experimental results verify the effectiveness of the proposed algorithms.

Traffic sign detection is a crucial task for autonomous driving perception systems, as it directly impacts vehicle path planning and safety decisions. Existing algorithms face challenges such as feature information attenuation and model lightweighting requirements in the detection of small traffic signs at long distances. To address these issues, this paper proposes a dual-pooling dynamic grouping (DPDG) module. This module dynamically adjusts the number of groups to adapt to different input features, combines global average pooling and max pooling to enhance channel attention representation, and uses a lightweight 3 × 3 convolution-based spatial branch to generate spatial weights. Based on a hierarchical optimization strategy, the DPDG module is integrated into the YOLOv10n network. Experimental results on the traffic sign dataset demonstrate a significant improvement in the performance of the YOLO-DPDG network: Compared to the baseline YOLOv10n model, mAP@0.5 and mAP@0.5:0.95 improved by 8.77% and 10.56%, respectively, while precision and recall were enhanced by 6.16% and 6.62%, respectively. Additionally, inference speed (FPS) increased by 11.1%, with only a 4.89% increase in model parameters. Compared to the YOLOv10-Small model, this method achieves a similar detection accuracy while reducing the number of model parameters by 64.83%. This study provides a more efficient and lightweight solution for edge-based traffic sign detection.

Emergency material planning and scheduling aims to schedule emergency material to destination efficiently to reduce property losses and personal casualties caused by material shortage. Existing researches usually rely on optimization of transportation routes. They ignore the rich scenarios in which human and material resources participate in scheduling simultaneously. Moreover, sudden emergencies may involve the supply of multiple material demand points. To address these issues, we propose an AI planning approach to model emergency material scheduling domain and construct a standard planning task using PDDL. Then a state-of-the-art planner is employed to solve the generated planning task. Experimental results show that the proposed approach can fit the actual situation of emergencies and give high-quality instruction to guide emergency material planning and scheduling.

The primary objective of logistics transportation vehicle scheduling is to guide transportation vehicles to complete logistics tasks in the shortest possible time while minimizing logistics costs. However, traditional research in logistics transportation vehicle scheduling has been criticized for its narrow focus, limited consideration of constraints, and often sub-optimal route planning, which hinder its practical applicability. To address these issues, we propose an AI Planning method to simulate logistics transportation vehicle scheduling scenarios. We utilize the PDDL language to construct standard planning tasks, and then employ the state-of-the-art planner to solve these tasks, generating planning solutions which are used as vehicle scheduling schemes. The experimental results demonstrate that our proposed method is capable of generating scheduling schemes in a relatively short time, guiding transport vehicles to complete logistics transportation tasks.