Video Quality Monitoring for Remote Autonomous Vehicle Control

2025-05-27

AI Summary

To address degraded video quality and increased latency in remote autonomous driving applications over 4G/5G networks—caused by signal fluctuations, frequent handovers, and transient congestion—this paper proposes an end-to-end video quality monitoring system. Methodologically, it introduces a multimodal AI prediction framework integrating real-world and synthetic data, enabling online benchmarking of LSTM, GRU, and encoder-only Transformer models; further, it designs an explainable AI (XAI)-enhanced QoE proactive adaptation mechanism that anticipates network degradation to adjust bitrate and encoding parameters preemptively. Key contributions include: (i) the first lightweight, multi-source data-driven QoE prediction paradigm; (ii) empirical validation of optimal trade-offs in edge-vehicle collaborative inference; and (iii) superior performance across 20 model benchmarks, balancing prediction accuracy and ultra-low latency. Experiments demonstrate significant improvements in video availability and control responsiveness.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The delivery of high-quality, low-latency video streams is critical for remote autonomous vehicle control, where operators must intervene in real time. However, reliable video delivery over Fourth/Fifth-Generation (4G/5G) mobile networks is challenging due to signal variability, mobility-induced handovers, and transient congestion. In this paper, we present a comprehensive blueprint for an integrated video quality monitoring system, tailored to remote autonomous vehicle operation. Our proposed system includes subsystems for data collection onboard the vehicle, video capture and compression, data transmission to edge servers, real-time streaming data management, Artificial Intelligence (AI) model deployment and inference execution, and proactive decision-making based on predicted video quality. The AI models are trained on a hybrid dataset that combines field-trial measurements with synthetic stress segments and covers Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and encoder-only Transformer architectures. As a proof of concept, we benchmark 20 variants from these model classes together with feed-forward Deep Neural Network (DNN) and linear-regression baselines, reporting accuracy and inference latency. Finally, we study the trade-offs between onboard and edge-based inference. We further discuss the use of explainable AI techniques to enhance transparency and accountability during critical remote-control interventions. Our proactive approach to network adaptation and Quality of Experience (QoE) monitoring aims to enhance remote vehicle operation over next-generation wireless networks.

Problem

• Ensuring high-quality low-latency video for remote autonomous vehicle control
• Overcoming 4G/5G network challenges like signal variability and congestion
• Balancing onboard vs edge-based AI inference for video quality prediction

Innovation

• Integrated video quality monitoring system
• AI models with hybrid dataset training
• Onboard and edge-based inference trade-offs