Search papers, labs, and topics across Lattice.
This paper introduces an AI-augmented digital twin framework for optimizing 5G/6G RAN densification by integrating high-resolution 3D modeling, object detection via vision transformers, and deterministic ray tracing. The framework addresses the limitations of traditional manual planning and stochastic RF simulations by leveraging aerial and ground imagery to construct detailed, material-aware 3D models. Experiments in urban and campus environments demonstrate improved prediction accuracy and reduced manual effort compared to conventional methods, facilitating more efficient and cost-effective network deployments.
Ditch the clipboard: AI-powered digital twins can automate and improve 5G/6G network planning, slashing costs and boosting accuracy compared to manual methods.
The rapid growth of 5G and future 6G networks requires efficient and scalable radio access network (RAN) densification, especially in dense urban and industrial areas. Traditional planning uses manual surveys and simple propagation models, but these lack spatial accuracy and adaptability. Stochastic RF simulation tools often fail to model real-world conditions, such as material properties and geometry. This leads to poor site selection, higher costs, and rollout delays.This paper proposes an AI-based framework that combines high-resolution 3D modeling, Digital Twin technology, and deterministic ray tracing. It uses aerial and ground imagery to build detailed 3D models, enhanced with object detection and material classification through segmentation models. These models enable automatic feature extraction for RF simulation and planning. The system uses open-source 3D tools, vision transformers for segmentation, and a simulation engine with antenna radiation patterns and material-aware propagation. Tests in urban and campus settings show better prediction accuracy, less manual work, and lower costs than traditional methods. Results show that AI and Digital Twins improve and automate network deployment.
