Scalable RF Simulation in Generative 4D Worlds

2025-08-16

AI Summary

Addressing the challenge of acquiring high-quality radio-frequency (RF) data in dynamic indoor environments, this paper introduces WaveVerse—the first language-guided framework for large-scale 4D RF data generation. Methodologically, it comprises: (1) a language-driven 4D world generator leveraging a state-aware causal Transformer to synthesize human motion sequences that satisfy both spatial constraints and natural-language descriptions; and (2) a phase-consistent ray-tracing simulator enabling high-fidelity RF signal modeling. WaveVerse is the first framework to enable controllable, scalable RF imaging–oriented data synthesis. Empirically, it substantially improves model performance across four RF sensing tasks—respiratory monitoring, beamforming, high-resolution imaging, and human activity recognition—under both few-shot and multi-shot regimes. By providing a reliable, semantically rich, and physically accurate data foundation, WaveVerse advances the training and evaluation of RF perception algorithms.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Radio Frequency (RF) sensing has emerged as a powerful, privacy-preserving alternative to vision-based methods for indoor perception tasks. However, collecting high-quality RF data in dynamic and diverse indoor environments remains a major challenge. To address this, we introduce WaveVerse, a prompt-based, scalable framework that simulates realistic RF signals from generated indoor scenes with human motions. WaveVerse introduces a language-guided 4D world generator, which includes a state-aware causal transformer for human motion generation conditioned on spatial constraints and texts, and a phase-coherent ray tracing simulator that enables the simulation of accurate and coherent RF signals. Experiments demonstrate the effectiveness of our approach in conditioned human motion generation and highlight how phase coherence is applied to beamforming and respiration monitoring. We further present two case studies in ML-based high-resolution imaging and human activity recognition, demonstrating that WaveVerse not only enables data generation for RF imaging for the first time, but also consistently achieves performance gain in both data-limited and data-adequate scenarios.

Problem

• Simulating realistic RF signals in dynamic indoor environments
• Generating human motions conditioned on spatial constraints and texts
• Enabling data generation for RF imaging and activity recognition

Innovation

• Language-guided 4D world generator
• State-aware causal transformer for motion
• Phase-coherent ray tracing RF simulator