Model-Driven End-to-End Learning for Integrated Sensing and Communication
Authors:
- 28 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5695-5700
Abstract
Integrated sensing and communication (ISAC) is envisioned to be one of the pillars of 6G. However, 6G is also expected to be severely affected by hardware impairments. Under such impairments, standard model-based approaches might fail if they do not capture the underlying reality. To this end, data-driven methods are an alternative to deal with cases where imperfections cannot be easily modeled. In this paper, we propose a model-driven learning architecture for joint single-target multi-input multi-output (MIMO) sensing and multi-input single-output (MISO) communication. We compare it with a standard neural network approach under complexity constraints. Results show that under hardware impairments, both learning methods yield better results than the model-based standard baseline. If complexity constraints are further introduced, model-driven learning outperforms the neural-network-based approach. Model-driven learning also shows better generalization performance for new unseen testing scenarios.Keywords
Funding Information
- European Commission (101015956,888913)
- Swedish Research Council (2020-04718)
This publication has 26 references indexed in Scilit:
- MAP Ratio Test Detector for Radar SystemIEEE Transactions on Signal Processing, 2020
- Deep Unfolding for Communications Systems: A Survey and Some New Directions2019
- Model-Driven Deep Learning for Physical Layer CommunicationsIEEE Wireless Communications, 2019
- Multibeam for Joint Communication and Radar Sensing Using Steerable Analog Antenna ArraysIEEE Transactions on Vehicular Technology, 2018
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Radar-Communications Convergence: Coexistence, Cooperation, and Co-DesignIEEE Transactions on Cognitive Communications and Networking, 2017
- Fast Unit-Modulus Least Squares With Applications in BeamformingIEEE Transactions on Signal Processing, 2017
- Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular SystemsIEEE Journal of Selected Topics in Signal Processing, 2014
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993
- Pruning algorithms-a surveyIEEE Transactions on Neural Networks, 1993