Artificial Intelligence Techniques for Deep Convolutional U-Shape Network with Jump Attention-Based Vision Transformer for Integrated Sequence Scheduling and Trajectory Planning with Obstacle Avoidance in Wireless Rechargeable Sensor Networks: Trends and

Abstract

Wireless Rechargeable Sensor Networks (WRSNs) have emerged as an effective solution to address the energy constraints of traditional Wireless Sensor Networks (WSNs), yet challenges such as sequence scheduling, trajectory planning, and obstacle avoidance remain complex due to dynamic environments. Recent advances in Artificial Intelligence (AI), particularly deep learning, have significantly enhanced these processes. This paper reviews Deep Convolutional U-Shape Networks (U-Net) integrated with Jump Attention-based Vision Transformers (ViTs) for efficient WRSN management. U-Net enables robust spatial feature extraction, while transformers capture long-range dependencies through attention mechanisms, improving trajectory prediction and decision-making. Hybrid models such as TransUNet and Swin-based U-Net further enhance performance by combining convolutional and attention-based learning. Additionally, reinforcement learning and optimization techniques contribute to adaptive scheduling and efficient resource utilization. Despite these improvements, challenges such as high computational cost, scalability, and real-time implementation persist. This review highlights recent advancements, compares techniques, and emphasizes the need for lightweight and edge-based intelligent solutions for next-generation WRSNs.