Toward an AI-enabled Connected Industry: AGV Communication and Sensor Measurement Datasets

TL;DR

Industrial wireless networks require reliable, low-latency QoS for real-time control, but ML-based pQoS development hinges on domain-specific data. This work presents two measurement campaigns, bosch iV2V sidelink and enway iV2I+ with sensor data, underpinned by detailed methodologies and publicly available, labeled datasets. The datasets couple sidelink/V2V channel measurements with localization and AGV sensor streams, enabling ML tasks such as fingerprinting, LOS detection, QoS prediction, channel charting, and proactive resource management. Together, the work provides a practical foundation for ML-enabled industrial connectivity and supports ML-driven optimization toward future campus networks and radio-map-based approaches.

Abstract

This paper presents two wireless measurement campaigns in industrial testbeds: industrial Vehicle-to-vehicle (iV2V) and industrial Vehicle-to-infrastructure plus Sensor (iV2I+), together with detailed information about the two captured datasets. iV2V covers sidelink communication scenarios between Automated Guided Vehicles (AGVs), while iV2I+ is conducted at an industrial setting where an autonomous cleaning robot is connected to a private cellular network. The combination of different communication technologies within a common measurement methodology provides insights that can be exploited by Machine Learning (ML) for tasks such as fingerprinting, line-of-sight detection, prediction of quality of service or link selection. Moreover, the datasets are publicly available, labelled and prefiltered for fast on-boarding and applicability.

Figures (3)

• Figure 1: bosch testbed.
• Figure 2: Illustration of measurement scenarios A & B in bosch.
• Figure 3: enway testbed.