IECE Transactions on Internet of Things | Volume 2, Issue 4: 95-112, 2024 | DOI:10.62762/TIOT.2024.918236
Abstract
This study focuses on optimizing multimodal robot route planning in intelligent logistics management by integrating Transformer models, Graph Neural Networks (GNNs), and Generative Adversarial Networks (GANs). Using a graph structure representing map information, cargo distribution, and robot states, spatial and resource constraints are considered to optimize paths. Extensive simulations based on real logistics datasets demonstrate significant improvements over traditional methods, with an average 15\% reduction in path length, 20% improvement in time efficiency, and 10% reduction in energy consumption. These results underscore the effectiveness and superiority of the proposed multimodal pat... More >
Graphical Abstract
