Mitigating Concept Drift in QoS Prediction for Teleoperation of Autonomous Vehicles Using Historic Data

2026-10-06

AI Summary

This study addresses the problem of concept drift in Quality-of-Service (QoS) prediction caused by mobile network fluctuations during the remote operation of autonomous vehicles. Based on empirical measurement data, this work proposes an uplink throughput and latency prediction framework that integrates historical information. Methodologically, historical data are leveraged to mitigate performance degradation induced by distribution shifts, while a critical scenario detection metric is designed to accurately assess prediction reliability. Technically, the approach combines machine learning, time series modeling, and 5G network Key Performance Indicator (KPI) analysis. Experimental results demonstrate that the proposed framework significantly enhances predictive robustness on unseen data, thereby effectively improving the operational resilience of remote driving systems.

Abstract

Teleoperation serves as the fallback solution to autonomous driving but reliable functions of the teleoperation require a certain amount of mobile network resources, which cannot be guaranteed at all times. Therefore, predictive quality of service (pQoS) is introduced as a concept to increase the resilience of the teleoperation. In this paper, based on a data measurement campaign, we propose a prediction framework to prediction two important network KPIs of teleoperation: uplink data-rate and round-trip latency. Furthermore, we introduce a method to alleviate the performance degradation of machine-learning-based prediction models on previously unseen data due to concept drift by incorporating historic data into the prediction pipeline. Additionally, we introduce the metric of critical scenario detection to evaluate the prediction performance specifically for teleoperation.

Problem

• Concept Drift
• QoS Prediction
• Teleoperation
• Autonomous Vehicles
• Predictive Quality of Service

Innovation

• Concept Drift
• Quality of Service Prediction
• Teleoperation
• Historic Data
• Critical Scenario Detection