Demonstrations & DataSets
DeepSense 6G (Radar-Aided Beam Prediction): Developing efficient solutions for sensing-aided beam prediction and accurately evaluating them requires the availability of a large-scale real-world dataset. The DeepSense 6G dataset is the large-scale real-world multi-modal dataset with co-existing communication and sensing data.
In this radar-aided beam prediction task, the development/challenge datasets is built based on the DeepSense data from scenario: a Vehicle-to-Infrastructure (V2I) mmWave communication setup.
It comprises the 3D complex raw FMCW radar data and the corresponding 64×1 power vectors obtained by performing beam training with a 64-beam codebook at the receiver (with omni-transmission at the transmitter). The radar data comprises of the radar measurements of the wireless environment captured by the FMCW radar installed at the basestation. The dataset also provides the optimal beam indices as the ground-truth labels.
- DeepSense Core Team：Ahmed Alkhateeb（Director, Wireless Intelligence Lab）、Gouranga Charan（Ph.D. Student, Wireless Intelligence Lab）、Tawfik Osman（Ph.D. Student, Wireless Intelligence Lab）、Nikhil Srinivas（M.S. Student, Wireless Intelligence Lab）、Andrew Hredzak（B.S.E., Wireless Intelligence Lab）
- Link: https://deepsense6g.net/radar-aided-beam-prediction/
Demonstration and Datasets Working Group (WG5):
Taneli Riihonen (ETI Vice-chair, ex-officio), Tampere University
Bhavani Shankar M. R, University of Luxembourg
Kumar Vijay Mishra, Padmanava Sen, Chao Shen, Kaifeng Han, André Noll Barreto, Rui Wang, Shuai Wang