BRAVR: An AP-Assisted Online DRL Mechanism for Interactive VR Bitrate Adaptation over Wi-Fi

2026-06-23

AI Summary

This study addresses the challenge of simultaneously achieving low latency, high reliability, and real-time bitrate adaptation for interactive VR streaming over dynamic Wi-Fi shared channels. The authors formulate this problem as a network-aware online decision-making task and propose BRAVR, a decentralized deep reinforcement learning framework that, for the first time, leverages lightweight wireless statistics from access points (APs) to augment application-layer observations for precise online bitrate control. By integrating such AP-side channel insights, BRAVR maintains high visual quality and streaming performance while enhancing airtime fairness among multiple users. Extensive experiments on a real-world Wi-Fi testbed demonstrate that BRAVR significantly outperforms heuristic baselines and ablation variants without AP assistance, effectively preventing channel overload and consistently delivering high-quality VR experiences.

Abstract

Interactive virtual reality (VR) streaming over Wi-Fi requires stringent latency and reliability guarantees, which become increasingly difficult to achieve under dynamic channel conditions and shared medium contention. These challenges make real-time bitrate adaptation a critical yet fundamentally difficult control problem, particularly under limited visibility of the underlying network conditions. This paper formulates VR bitrate adaptation as a network-aware, online decision-making problem and proposes BRAVR, a decentralized deep reinforcement learning (DRL) mechanism designed to optimize visual quality while maintaining streaming performance and promoting airtime fairness in multi-user scenarios. BRAVR integrates application-layer observations with lightweight wireless network statistics collected at the Wi-Fi access point (AP) serving the VR client, enabling more informed bitrate adaptation decisions. We implement BRAVR in a real VR streaming system and evaluate it on a physical Wi-Fi testbed against a strong heuristic baseline and an ablated BRAVR variant without AP assistance. Experimental results show that BRAVR consistently achieves its design objectives, delivering robust quality of service (QoS) and preventing sustained airtime overutilization. It also outperforms its ablated counterpart, highlighting the benefits of incorporating network-level information into the bitrate adaptation control loop. Overall, these results demonstrate the effectiveness of AP-assisted online learning for decentralized interactive VR streaming over commodity Wi-Fi and provide practical insights into bitrate adaptation in shared wireless environments.

Problem

• VR streaming
• bitrate adaptation
• Wi-Fi
• latency
• network dynamics

Innovation

• bitrate adaptation
• deep reinforcement learning
• Wi-Fi access point assistance
• interactive VR streaming
• airtime fairness