A Vision-based Framework for Intelligent gNodeB Mobility Control

TL;DR

This paper introduces a vision-based framework for controlling mobile gNodeBs in wireless networks, utilizing novel service models, a deep learning-based control app, and a digital twin for training and validation, significantly reducing LoS blockages.

Contribution

It presents a novel vision-enabled architecture, a deep reinforcement learning control app, and a digital twin environment for intelligent gNB mobility management.

Findings

Reduces LoS blockage duration by up to 75%.

Validates system with real vision data and emulated radio.

Demonstrates the feasibility of multimodal perception in RAN control.

Abstract

This paper proposes a vision-based framework for the intelligent control of mobile Open Radio Access Network (O-RAN) base stations (gNBs) operating in dynamic wireless environments. The framework comprises three innovative components. The first is the introduction of novel Service Models (SMs) within a vision-enabled O-RAN architecture, termed VisionRAN. These SMs extend state-of-the-art O-RAN-based architectures by enabling the transmission of vision-based sensing data and gNB positioning control messages. The second is an O-RAN xApp, VisionApp, which fuses vision and radio data, and uses this information to control the position of a mobile gNB, using a Deep Q-Network (DQN). The third is a digital twin environment, VisionTwin, which incorporates vision data and can emulate realistic wireless scenarios; this digital twin was used to train the DQN running in VisionApp and validate the overall system. Experimental results, obtained using real vision data and an emulated radio, demonstrate that the proposed approach reduces the duration of Line-of-Sight (LoS) blockages by up to 75% compared to a static gNB. These findings confirm the viability of integrating multimodal perception and learning-based control within RANs.