HawkRover: An Autonomous mmWave Vehicular Communication Testbed with Multi-sensor Fusion and Deep Learning
Ethan Zhu, Haijian Sun, Mingyue Ji
TL;DR
The paper addresses the overhead of mmWave beam alignment in high-mobility V2X scenarios by proposing HawkRover, a low-cost autonomous testbed that collects co-located mmWave and multimodal sensor data. It employs a DL-based sensor fusion pipeline (CNN/RNN with a fusion block) to predict the optimal mmWave beam pair directly from perception inputs, bypassing pilot-based channel estimation. Key contributions include a ROS-Docker-MQTT-based data pipeline, a cost-effective mmWave-enabled platform, and a DL fusion approach with indoor results achieving Top-1 65.5% and Top-5 90.6% accuracy, demonstrating significant potential to reduce beam-training overhead in future V2X mmWave networks. The work provides a practical dataset and methodology to accelerate real-time mmWave V2X beam alignment, with implications for scalable, high-throughput CAV communications.
Abstract
Connected and automated vehicles (CAVs) have become a transformative technology that can change our daily life. Currently, millimeter-wave (mmWave) bands are identified as the promising CAV connectivity solution. While it can provide high data rate, their realization faces many challenges such as high attenuation during mmWave signal propagation and mobility management. Existing solution has to initiate pilot signal to measure channel information, then apply signal processing to calculate the best narrow beam towards the receiver end to guarantee sufficient signal power. This process takes significant overhead and time, hence not suitable for vehicles. In this study, we propose an autonomous and low-cost testbed to collect extensive co-located mmWave signal and other sensors data such as LiDAR (Light Detection and Ranging), cameras, ultrasonic, etc, traditionally for ``automated'', to facilitate mmWave vehicular communications. Intuitively, these sensors can build a 3D map around the vehicle and signal propagation path can be estimated, eliminating iterative the process via pilot signals. This multimodal data fusion, together with AI, is expected to bring significant advances in ``connected'' research.